url stringlengths 37 208 | title stringlengths 4 148 | author stringclasses 173
values | publish_date stringclasses 1
value | categories listlengths 0 12 | tags listlengths 0 27 | featured_image stringlengths 0 272 | content stringlengths 0 56.1k | comments_count int64 0 900 | scraped_comments_count int64 0 50 | comments listlengths 0 50 | scraped_at float64 1.76B 1.76B |
|---|---|---|---|---|---|---|---|---|---|---|---|
https://hackaday.com/2023/07/27/a-simple-one-handed-solder-feeder/ | A Simple One-Handed Solder Feeder | Lewin Day | [
"Misc Hacks",
"Tool Hacks"
] | [
"solder",
"soldering",
"tools"
] | Soldering can get frustrating when you’re working fast. It often feels like you don’t have enough hands, particularly on jobs where you need to keep feeding solder in a hurry. To solve that issue,
[mulcmu] developed a simple one-handed solder feeder.
The solder is fed out of the tip by simply dragging it with the thumb.
The intended use-case is for busy work like soldering long pin headers. The one-handed device allows solder to be continually fed while the other hand uses the soldering iron. It solves a long-running problem for [mulcmu], after their experiments with techniques inspired by TIG welding came to nought.
The design uses a pen-like form factor. A 3D-printed hollow tube has a wire ferrule inserted in the end, which serves as the tip of the device through which solder is fed. The tube has a cutaway, which allows the user to feed solder through using an easy motion of the thumb. The solder itself is fed from a spool in a regular bench top holder. If more slack is required in the solder feed, one simply pins the solder down in the device and tugs to draw more out.
If you find yourself regularly soldering repetitive jobs by hand, this could be a gamechanger for you. Those
working in through-hole
would be perhaps best served by this device. Meanwhile, if you’ve got nifty tool hacks of your own to share,
don’t hesitate to let us know! | 46 | 19 | [
{
"comment_id": "6666524",
"author": "wibble",
"timestamp": "2023-07-27T20:18:00",
"content": "eh? I can just hold the solder in one hand and the iron in the other. What on earth does feeding it through a pen add to the equation. Utterly baffled. Reads like an April Fool.",
"parent_id": null,
... | 1,760,372,221.870396 | ||
https://hackaday.com/2023/07/27/magnetic-gearbox-part-2-axial-flux-improves-performance/ | Magnetic Gearbox, Part 2: Axial Flux Improves Performance | Dan Maloney | [
"Parts"
] | [
"axial",
"flux",
"gearbox",
"magent",
"neodymium",
"rotor",
"stator",
"torque"
] | The number of interesting and innovative mechanisms that 3D printing has enabled always fascinates us, and it’s always a treat when one of them shows up in our feeds.
This axial flux magnetic gearbox
is a great example of such a mechanism, and one that really makes you think about possible applications.
The principles of [Retsetman]’s gearbox are simple for anyone who has ever played with a couple of magnets to understand, since it relies on that powerful attractive and repulsive force you feel when magnets get close to each other. Unlike
his previous radial flux gearbox
, which used a pair of magnet-studded cylindrical rotors nested one inside the other, this design has a pair of disc-shaped printed rotors that face each other on aligned shafts. Each rotor has slots for sixteen neodymium magnets, which are glued into the slots in specific arrangements of polarity — every other magnet for the low-speed rotor, and groups of four on the high-speed rotor. Between the two rotors is a fixed flux modulator, a stator with ten ferromagnetic inserts screwed into it.
In operation, which the video below demonstrates nicely, the magnetic flux is coupled between the rotors by the steel inserts in the stator so that when one rotor moves, the other moves at a 4:1 (or 1:4) ratio in the opposite direction. [Retsetman] got the gearbox cranked up to about 8,500 RPM briefly, but found that extended operation at as little as 4,000 RPM invited disaster not due to eddy current heating of the inserts or magnets as one might expect, but from simple frictional heating of the rotor bearings.
Torque tests of the original gearbox were unimpressive, but [Retsetman]’s experiments with both laminated stator inserts and more powerful magnets really boosted the output — up to a 250% improvement! We’d also like to see what effect
a Halbach array
would have on performance, although we suspect that the proper ratios between the two rotors might be difficult to achieve. | 13 | 7 | [
{
"comment_id": "6666559",
"author": "Petter",
"timestamp": "2023-07-27T22:45:21",
"content": "Well have you seen a non 3dprinted one?And it’s sort of in the article that it’s an enabler, you could of course make the same thing with a spoon and a log of wood but it’s simply simpler with 3d printing.... | 1,760,372,222.256473 | ||
https://hackaday.com/2023/07/27/did-tetra-have-a-backdoor-hidden-in-encrypted-police-and-military-radios/ | Did TETRA Have A Backdoor Hidden In Encrypted Police And Military Radios? | Lewin Day | [
"Hackaday Columns",
"Radio Hacks",
"Slider"
] | [
"backdoor",
"radio",
"tetra",
"tetra radio",
"trunked radio"
] | Encrypted communications are considered vital for many organizations, from military users to law enforcement officers. Meanwhile, the ability to listen in on those communications is of great value to groups like intelligence agencies and criminal operators. Thus exists the constant arms race between those developing encryption and those desperately eager to break it.
In a startling revelation
, cybersecurity researchers have found a potentially intentional backdoor in encrypted radios using the TETRA (TErrestrial Trunked RAdio) standard. TETRA equipment is used worldwide by law enforcement agencies, military groups, and critical infrastructure providers, some of which may have been unintentionally airing sensitive conversations for decades.
Sneaky, Sneaky
Using an SDR and a regular laptop, TETRA transmissions using TEA1 encryption can be easily compromised. Credit:
Midnight Blue
If you’re unfamiliar with TETRA, it’s a trunked radio system designed for professional use by groups like government agencies, emergency services, infrastructure and rail operators, and military and law enforcement. It’s uses time-division multiple access (TDMA) for channel sharing, and is capable of carrying both voice and digital data. It can be used in direct communication modes, or in a trunked system with switching where infrastructure is available. By virtue of its networked nature, it can provide far greater communication without the usual range limitations of handheld portable radios.
The researchers from Midnight Blue, a cybersecurity firm, were the first to perform a detailed, publicly-available analysis of the TETRA standard, which has turned up vulnerabilities within its underlying cryptography. TETRA features a number of encryption methodologies, all proprietary. The researchers uncovered a serious vulnerability specifically in the TEA1 encryption algorithm.
Although not all TETRA radio users are using TEA1, those who do are likely at risk of having their communications intercepted and decrypted. TEA1 is primarily intended for commercial users. The three other encryption methods, TEA2, TEA3, and TEA4, have different intended applications. TEA2 is reserved for police, emergency services, military, and intelligence users in Europe only. TEA3 is restricted to similar users in countries considered “friendly” by the EU, like Mexico and India. Users in other countries, like Iran, are forced to make do with TEA1. TEA4 is another algorithm intended for commercial users, though is hardly used, according to Midnight Blue.
The list of TETRA users is long
, with the system used in 114 countries by 2009. While many have access to the stronger encryption methods, few would want to hear they use a compromised radio system. TETRA is used by police forces across the Middle East, including Iran, Iraq, Lebanon, and Syria, along with Polish and Finnish military forces. Dutch police are a major user too, and Midnight Blue has met directly with the organization to discuss the breach.
The Backdoor
The vulnerability, which has been termed a “backdoor” by the researchers, is essentially a “secret reduction step” in the encryption process. This reduces the initial encryption key’s entropy from 80 bits to just 32 bits. This makes cracking the key trivial with a modern computer. It enables an attacker to decrypt traffic easily with consumer-grade gear and a software-defined radio dongle for interception. This decryption process is not only swift, taking less than a minute, but also undetectable when done by a passive listener.
Notably, TETRA’s proprietary nature has meant that public analysis of its encryption has been difficult to pursue. Midnight Blue researchers got around this by simply purchasing a Motorola MTM5400 TETRA radio off eBay to perform their analysis. Code execution was achieved on the main application processor via a vulnerable interface, which then allowed the team to dive into the workings of the signal processing chip. The team was then able to reverse-engineer the cryptographic operations going on inside, and crack the TEA1 encryption wide open. The team have termed the series of vulnerabilities
TETRA:BURST.
The team also developed a decryption oracle that affects all TETRA platforms, which can be circumvented with a firmware update. Credit:
Midnight Blue
The controversy surrounding the intentional or unintentional existence of this backdoor has raised eyebrows. While the researchers insist on its deliberate design, the European Telecommunications Standards Institute (ETSI), responsible for the TETRA standard, refutes this claim, attributing it instead to export controls dictating encryption strength.
According to reports published by
Wired
, the 32-bit limit in the TEA1 algorithm was intended to meet export requirements for equipment to be used outside Europe.
Brian Murgatroyd, chair of the body responsible for TETRA in ETSI, stated that at the time of development in 1995, 32-bit keys were still considered relatively secure. He also claimed that the most this would allow would be the decryption and eavesdropping of communications. However, Midnight Blue researchers point out that TETRA does not digitally sign or authenticate individual transmissions. Thus, once a radio is authenticated onto a TETRA network, it can inject any desired transmissions at will.
It’s a curious statement, though, given that the key reduction hack the group found was not publicly available. Ostensibly, TEA1 relied on 80-bit encryption. Regardless, there are hints that this weakness was well-known as far back as 2006.
A leaked diplomatic cable
regarding U.S. pushback on the export of Italian TETRA radio equipment to Iran noted that the encryption included was “less than 40-bits,” a threshold considered below the level suitable for military use.
Regardless of intentionality, the possibility of the backdoor’s existence and its potential exploitation over decades cannot be overlooked.
What does this revelation mean for the countless entities using TETRA standard radios? For starters, it points to a significant and alarming risk to public safety and national security. Confidential and sensitive information could have been or could still be intercepted and decrypted by potential adversaries. This discovery also shines a spotlight on the inherent vulnerabilities in relying on proprietary cryptographic systems which cannot be easily scrutinized by external security experts. It also shows how international relations play a big role in technology exports, and tells us just how little different countries really trust each other.
The organizations affected by this vulnerability have significant challenges ahead. First and foremost, they need to determine the extent of potential breaches that might have occurred due to this backdoor. Given that this backdoor has been around for decades, this could be an arduous task with far-reaching implications. Additionally, these organizations will need to plan immediate countermeasures, such as implementing firmware updates and migrating to other TEA ciphers or applying end-to-end encryption to secure their communications. Notably, Midnight Blue has been long planning a talk at the 2023 Black Hat event on this very matter, but it has been listed
under a redacted name
to protect TETRA users while the group made disclosures to affected parties.
However, the issue runs deeper than merely fixing this one vulnerability. The discovery has further fuelled the debate over the use of “closed, proprietary crypto” versus “open, publicly scrutinized standards.” In the interest of avoiding such security pitfalls in the future, organizations might have to reassess their security infrastructure and lean towards adopting open cryptographic systems, which can be vetted by external experts and the wider security community.
In conclusion, this revelation serves as a stark reminder of the inherent risks of proprietary cryptography and the urgent need for a shift towards more open, transparent, and scrutinized security standards. After all, in an increasingly interconnected world, the cost of complacency towards cybersecurity can be catastrophically high. | 42 | 19 | [
{
"comment_id": "6666445",
"author": "irox",
"timestamp": "2023-07-27T17:08:28",
"content": "https://hackaday.com/2023/07/26/serious-vulnerability-in-european-trunked-radio-system/",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6668829",
"author": "p... | 1,760,372,222.344997 | ||
https://hackaday.com/2023/07/27/esp32-freezer-alarm-keeps-tabs-on-tricky-door/ | ESP32 Freezer Alarm Keeps Tabs On Tricky Door | Lewin Day | [
"home hacks",
"Microcontrollers"
] | [
"alarm",
"freezer",
"fridge"
] | Leaving your freezer door open accidentally is a great way to make a huge mess in the kitchen. [Guy Dupont] had a freezer that would regularly fail to close properly, and was sick of the regular meltdown events. Thus, he
whipped up a very digital solution.
The build combines an ESP32 with a reed switch, which is activated by a magnet on the freezer door. If the freezer door is open, the reed switch similarly remains open. The ESP32 checks the switch status every few minutes, and if the door remains open for two consecutive checks, it raises the alarm. A notification is sent to [Guy] via WiFi so that he can rectify the situation. The rig runs off a 400 mAh battery, which lasts for just over three weeks running door checks at two minute intervals.
Based on [Guy]’s
YouTube video
, it appears the freezer door is jamming up against the wall. Perhaps shoving the freezer into a better position would help, though we suspect he would have thought of that first. And, in his own words, “That would be a very boring YouTube video, wouldn’t it?”
It’s not the first fridge alarm we’ve featured
, and it won’t be the last, refrigeration gods willing. | 31 | 14 | [
{
"comment_id": "6666400",
"author": "k-ww",
"timestamp": "2023-07-27T15:48:41",
"content": "Why not use the reed switch to bias a FET off when it is closed, and power up the ESP32 to time out after tow minutes and then send an alarm? That battery should last almost forever thatr way?",
"parent... | 1,760,372,221.787745 | ||
https://hackaday.com/2023/07/28/color-can-triple-qr-code-capacity/ | Color Can Triple QR Code Capacity | Chris Lott | [
"Tech Hacks"
] | [
"bar code",
"Micro QR code",
"qr code",
"rMQR"
] | Recently [mit41301] wondered about increasing the data capacity of QR codes, and was able to
successfully triple the number of bits using color
. He chose the new rectangular micro QR code (rMQR) standard which was adopted last year as ISO/IEC 23941:2022. This rectangular-shaped QR code is designed to be used on narrow spaces, with an aspect ratio similar to that of a traditional 1D bar code. There are quite a few variations of rMQR, but the largest can hold 361 bytes. The basic idea is to generate three different rMQR codes, coloring them as red, green, blue, and merging the result. Decoding is performed by separating the color image into its RGB components and then decoding the resulting three images.
To do these experiments, [mit41301] took advantage of readily available tools. Generating rMQR codes can be done with
this Python module
by [Takahiro Tomita], who also makes the generator available
online
. Or if you’re more comfortable with Go, check out
this repository
by [Ichinose Shogo]. As a proof-of-concept, [mit41301] takes the first 449 digits of pi, plus the decimal point, and splits them into three each 150 byte chunks. Then he uses the image manipulation program
ImageJ
, an open-source Java program developed at the National Institutes of Health, to implement the combination and deconstruction processes.
The first 449 digits of pi expressed as a colorful rMQR code
There might be a few pitfalls if you want to do this outside the laboratory, however. First of all, this standard is reasonably new, and after a brief search this author couldn’t find any decoder that would recognize rMQR codes, nor any software modules or libraries. Research into colorization of QR codes, known as HCC2D (High Capacity Colored 2-Dimensional) codes
has been ongoing
. One issue is that correcting for arbitrary chromatic abnormalities in a scanner’s lens requires a baseline color palette in the code, which eats up some of the newly-gained data capacity.
Nonetheless, we really do like this concept. Do you have any applications of QR codes in your projects where coloring could be helpful? Is anyone using (monochrome) rMQR codes and if so, how are you scanning them? Check out our overview of barcodes, their history, and their future, in
this recent article
. | 49 | 22 | [
{
"comment_id": "6666838",
"author": "Jac Goudsmit",
"timestamp": "2023-07-28T18:47:21",
"content": "It should be obvious that it probably makes more sense to use Cyan Magenta and Yellow instead of Red Green Blue for a multicolor code that’s printed on paper.",
"parent_id": null,
"depth": 1,... | 1,760,372,222.433273 | ||
https://hackaday.com/2023/07/28/would-we-recognize-extraterrestrial-technology-if-we-saw-it/ | Would We Recognize Extraterrestrial Technology If We Saw It? | Maya Posch | [
"Featured",
"Science",
"Slider",
"Space"
] | [
"alien",
"extraterrestrial"
] | There’s a common critique in science fiction series like Star Trek about the extraterrestrial species not looking ‘alien’ enough, as well as about their technology being strangely similar to our own, not to mention compatible to the point where their widgets can be integrated into terrestrial systems by any plucky engineer. Is this critique justified, or perhaps more succinctly put: if we came across real extraterrestrial life with real extraterrestrial technology, would we even notice? Would an alien widget borrowed of an alien spacecraft even work with our own terrestrial spacecraft’s system?
Within the domain of exobiology there are still plenty of discussions on the possible formation and evolutionary paths conceivable within the Universe, but the overarching consensus seems to be that it’s hard to escape the herding effect of fundamental physics. For lifeforms, carbon-based chemistry is the only reasonable option, and when it comes to technology, it’s hard to not end up at technology using the same physical principles which we presume to exist across the Universe, which would practically guarantee some level of interoperability.
What’s notable here is that over the past years, a number of people have claimed to have observed potential alien technology in our Solar System, in particular the
ʻOumuamua
asteroid in 2017 and a
more recent claim
by astrophysicist
Abraham Loeb
regarding an interstellar meteor that impacted Earth in 2019, which he says could be proof of ‘alien technology’. This raises the question of whether we are literally being pummeled by extraterrestrial spacecraft these days.
Space Is Boring
Most of space is literally just that: seemingly endless stretches with nothing but some electromagnetic radiation and potentially virtual particle pairs briefly zipping about in a vacuum. From the center of the Sun to Neptune’s orbit is 30.11 AU, or approximately 4.5 billion km, and outside the cozy confines of our Solar System it’s a trip of more than 4.2 light years to the next planetary system in the form of Proxima Centauri.
Traveling beyond the bounds of the Milky Way galaxy, distances to other galaxies are measured in millions of light years, meaning that even when traveling at 1 c, traveling to these galaxies would take longer than humans have existed in any form. This means effectively that all the space probes like Voyager 1 and Voyager 2 – which we sent into interstellar space at a relatively leisurely pace of over 30 km/s – will not approach another planetary system until many thousands of years into the future.
Simulated view of the Voyager probes relative to the solar system and heliopause on August 2, 2018. (Credit: NASA)
What this sobering realization also shows us is just how unlikely it is that an extraterrestrial spacecraft would somehow end up in our neighborhood, all the way here in a sparsely populated region of the Milky Way. Perhaps ironically, the likelihood of this happening would be much higher if it was deliberate, rather than a derelict alien space probe. Yet even then in the absence of faster-than-light traveling capacity, such a spacecraft would likely have been underway long before humanity had begun to differentiate itself from the other ape species on Earth, or mammals had begun to throw off the shackles of dinosaur tyranny.
Ultimately, planetary systems even within the same galaxy are rather isolated. This makes the possibility of having even something as mundane as another civilization’s space trash zip through our neighborhood both exceedingly unlikely and extremely exciting. But exactly how do we tell the difference between a comet rich in metals and a sophisticated extraterrestrial probe?
Is It A Rock? Is It A UFO?
Hyperbolic trajectory of ʻOumuamua through the inner Solar System, with the Sun at the focus, showing its position every 7 days. The planet positions are fixed at the perihelion on September 9, 2017. Shown from a three-quarter perspective, roughly aligned to the plane of ʻOumuamua’s path. (Credit:
Tomruen, Wikipedia
)
When a large enough object enters our solar system, we are likely to pick it up using telescopes, after which we can begin to figure out what exactly it is that we’re dealing with. The easiest clue as to whether we’re dealing with anything interesting is the trajectory and speed of the object, which is why ʻOumuamua was considered to be so interesting, as based on its calculated trajectory it came from far beyond the solar system, making it a rare visitor from probably another solar system within the Milky Way, or even far beyond.
From what we can determine, this particular object has likely been moving through the Milky Way for at least hundreds of thousands and likely billions of Earth years, yet its somewhat unusual elongated shape invited speculation about it being more than just a rocky asteroid, with Abraham Loeb pitching the idea that
it was in fact a spaceship
. Part of this speculation came from oddities in the asteroid’s velocity as it neared our solar system, but subsequent observations showed the object to be consistent with other, non-extrastellar asteroids. Attempts to detect any radio frequency emissions also led to nothing, and with the asteroid being too far removed from Earth to get a close-up look, much of what we know about it is based on its spectra.
A few years after ʻOumuamua passed silently through our solar system, another interstellar visitor made its presence known in the form of
2I/Borisov
, or Borisov for short. This was a comet that made an even briefer visit, finding its path deflected by the Sun before it continued on its trajectory through the Milky Way. Making interstellar visitors even less rare is
CNEOS 2014-01-08
, which is the meteor that Abraham Loeb got excited about since it’s an interstellar object which not just passed through the solar system, but which actually crashed onto Earth.
After obtaining the 10 km radius of the meteor’s suspected crash site off the coast of Papua New Guinea, Loeb and colleagues recovered some metallic spherules in the area, which he claims to have a composition that points towards the meteor having been an extraterrestrial spacecraft of some type with astounding alien properties. Whether these spherules are in fact connected to the meteor is still left up for interpretation, as they are not composed out of any alien metals, just the same iron, silicon, magnesium and titanium you’d expect to find on and outside Earth.
Axiom Vs Infinity
Perhaps what drives some of us to believe in ‘alien technology’ to be somehow magical is the belief that there must be something beyond the boring physics which we are currently trapped in. When we consider for example that many people put their faith in supernatural beings, fantastic existences beyond anything we can observe or measure, the ability of crystals, magnets and even plain water to effect reality in ways beyond any reasonable explanation, not to mention harmful effects of things long after no negative effect has been demonstrated.
To the rational, scientific mind, the Universe we have found ourselves in can be a source of marvel, but it’s nevertheless a purely rational and deterministic system. Through the scientific method we are able to convert observations into theorems and theories which we can then subject to validation through experimental and observational data. If the data fits the theory’s prediction, it passes, if it does not, either the theory is wrong, or the way the data was obtained was flawed.
Where some may question whether we really know anything is when they learn about the concept of
axioms
, which are essentially assumptions, and the
axiomatic systems
that underlies much of today’s mathematics and ultimately also some elements of physics. Yet as flawed as it may seem that we would hold certain truths to be self-evident, they’re a practical way to prevent issues like
infinite regression
as we try to define a set of terms. If not, one could conceivably discard the axiom that ‘1 equals 1’ by dismantling the axiomatic definitions underlying the property of one term equaling another.
Self-evidence here is not a sign of laziness, but rather one of fundamental understanding. This is exemplified by the fundamental electrical components which were postulated and gradually proven to exist based on an increasing understanding of electrical circuits and their potential properties. Of these the components, the resistor, capacitor and inductor were first discovered, followed eventually by the
memristor
.
What this demonstrates is how improved understanding of one part of a system can allow us to predict that which we have yet to discover, even if it’s something that defies intuitive understanding like
magnetic monopoles
.
Alien Is Relative
As someone once put it: “Where are all the time travelers?” in reference to the concept of time travel being possible, which is a statement that should put to rest the idea of either time travel being invented, or humanity going extinct before it is able to do so. Part of existing in this universe is to accept that there’s so much that we do not know, and perhaps will never know. All we know today is that even within the minuscule time period of a hundred rotations of the Earth around the Sun, humankind has fought a number of world wars, discovered modern medicine, invented computer technology and semiconductors.
To our ancestors and even to those who are living well into their twilight years today, the world we inhabit today seems alien in many ways. What will human technology look like in a hundred years, or a thousand? What about 100,000 years from now? Within the timescale of the Universe, those are still tiny numbers during which a particularly shaped space rock can leisurely zip around the Milky Way a few times, each time passing by a specific solar system in which over billions of years some goop turned into multicellular organisms which eventually turned into mammals that invented sliced bread and computers.
Is there truly extraterrestrial life out there, or is it mostly what we keep telling ourselves
to feel less lonely
in this grand and yet so empty Universe? Whatever may be the case, if we ever do meet up, we’re likely to be able to exchange technology, even if it’s the equivalent of wiring up a 1930s vacuum tube radio to a 2020s super computer. Which will naturally be just where we have that plucky engineer jump in. | 92 | 21 | [
{
"comment_id": "6666801",
"author": "schlem",
"timestamp": "2023-07-28T17:29:28",
"content": "I want to believe, but our location in the vast dimensions of time and space are discouraging. Meanwhile, can we teach whales and dolphins to speak to us (or vice versa) How about cephalopods? It might... | 1,760,372,222.006918 | ||
https://hackaday.com/2023/07/28/hackaday-podcast-229-diy-vr-gutting-voice-assistants-and-chatgpt-failing-its-summer-internship/ | Hackaday Podcast 229: DIY VR, Gutting Voice Assistants, And ChatGPT Failing Its Summer Internship | Kristina Panos | [
"Hackaday Columns",
"Podcasts",
"Slider"
] | [
"Hackaday Podcast"
] | This week, Editor-in-Chief Elliot Williams and Kristina Panos braved the slight cold and the high heat respectively to bring you the best hacks of the previous seven days. In the news this week:
you’ve got a second and final chance to get your Supercon talk proposals in
! So get on that, because we need YOU to help make Supercon awesome.
We can chalk up a win for Kristina on What’s That Sound this week (finally!). Will you get it right? Will you get it
exactly
right? Time and Elliot’s fancy dice will tell.
Then it’s on to the hacks, where we check out a cool RFID emulator e-paper badge, discuss whether a certain type of record player is better off as a cyberdeck, and look through the eye of a Gameboy-style camera for the Playdate console.
From there we take a look at gutting and rooting voice assistants, a solenoid keyboard, and a beautifully rebuilt VR headset that now does AR as well. Finally we talk autonomous solar boats, lambast ChatGPT as the worst summer intern ever, and ponder what makes a thing count as Linux or not.
Check out the links below if you want to follow along, and as always, tell us what you think about this episode in the comments!
Download and savor at your leisure
.
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 229 Show Notes:
News:
Procrastinators Rejoice! 2023 Supercon Call For Participation Extended
Serious Vulnerability In European Trunked Radio System
VanMoof E-Bike Bankruptcy: The Risks Of Cloud-Connected Transport
What’s that Sound?
Know the sound?
Let us know
!
Interesting Hacks of the Week:
RFID Emulator + E-paper Badge Can Be Programmed With Sound
GGWave Sings The Songs Of Your Data
Multi Frequency Shift Keying (MFSK) – Signal Identification Wiki
You Can Learn A Lot From A Blinkenrocket
2023 Cyberdeck Contest: Crosberry Pi Loves Lo-Fi Hip Hop
Google Nest Mini Gutted And Rebuilt To Run Custom Agents
Root, On An Amazon Echo Dot
Solenoid Keyboard Sounds Very Much Like A Typewriter
This Negative Reinforcement Keyboard May Shock You
Beautifully Rebuilding A VR Headset To Add AR Features
Behold A Gallery Of Sony’s PS VR2 Prototypes
VR Prototypes Reveal Facebook’s Surprisingly Critical Research Directions
Game Boy-Style Camera For Playdate
Quick Hacks:
Elliot’s Picks:
Turning A Quartz Clock Module Into A Time Reference
Text-to-Speech Model Can Do Music, Background Noises, And Sound Effects
Mapping The Depths With An Autonomous Solar Boat
Where Old Files Go To Die
Kristina’s Picks:
Selectric Typewriter Goes From Trash Can To Linux Terminal
That Ultra-White Paint That Helps Cool Surfaces? Make Your Own!
Restoring The Cheapest TRS-80 At The Swap Meet
Can’t-Miss Articles:
ChatGPT, The Worst Summer Intern Ever
Ask Hackaday: What’s Linux Anyway? | 1 | 1 | [
{
"comment_id": "6669452",
"author": "Jim",
"timestamp": "2023-08-04T01:42:53",
"content": "I often say Android is Linux but maybe saying “Android is a user interface for SE Linux” would be more accurate.",
"parent_id": null,
"depth": 1,
"replies": []
}
] | 1,760,372,221.718818 | ||
https://hackaday.com/2023/07/28/pizza-elevator-is-the-most-vital-pandemic-technology-of-all/ | Pizza Elevator Is The Most Vital Pandemic Technology Of All | Lewin Day | [
"home hacks"
] | [
"food",
"pandemic",
"Pizza",
"pizza elevator"
] | Remember the darkest days of lockdown and the pandemic? We were trying to distance ourselves from strangers wherever possible. [scealux]’s pizza elevator was spawned at this time to
make apartment pizza deliveries as contactless as possible
, and it’s charmingly branded to boot.
The build was intended to loft a pizza from street level to a third-floor balcony (by the American convention, ground floor is numbered one). Built with CNC-cut wooden parts, the elevator frame snap-fits on to the balcony railing. From there, a single spool runs out wire to four corners of the elevator platform.
As the crank is turned, the platform lowers under its own weight. The pizza can then be placed on the platform, and dinner can be lifted back up to the apartment. It’s a simple design, and one that manages to lift the pizza in a stable and flat fashion. With that said, we’d still like to see some anti-tip railings on a potential revision two.
Mock the branding all you will, it’s actually a smart design choice. The recognizable logo made the device’s purpose super obvious to the pizza delivery person, easing the introduction of the technology to a new user base.
If you want to make your own pizza instead of ordering out,
you can automate that too
. | 14 | 8 | [
{
"comment_id": "6666774",
"author": "Twisty Plastic",
"timestamp": "2023-07-28T15:39:11",
"content": "Not “mocking” the branding but honestly curious. Did it get awkward when you tired of having the same pizza and ordered from elsewhere?",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,222.106594 | ||
https://hackaday.com/2023/07/28/this-week-in-security-zenbleed-web-integrity-and-more/ | This Week In Security: Zenbleed, Web Integrity, And More! | Jonathan Bennett | [
"Hackaday Columns",
"Security Hacks",
"Slider"
] | [
"This Week in Security",
"ubuntu",
"Zenbleed"
] | Up first is
Zenbleed
, a particularly worrying speculative execution bug, that unfortunately happens to be really simple to exploit. It leaks data from function like
strlen
,
memcpy
, and
strcmp
. It’s vulnerable from within virtual machines, and potentially from within the browser. The scope is fairly limited, though, as Zenbleed only affects Zen 2 CPUs: that’s the AMD Epyc 7002 series, the Ryzen 3000 series, and some of the Ryzen 4000, 5000, and 7020 series of CPUs, specifically those with the built-in Radeon graphics.
And at the heart of problem is a pointer use-after-free — that happens inside the CPU itself. We normally think of CPU registers as fixed locations on the silicon. But in the case of XMM and YMM registers, there’s actually a shared store of register space, and the individual registers are mapped into that space using a method very reminiscent of pointers.
XMM registers are 128 bits long, and YMM registers are 256 bits long. As a performance optimization, compilers often use the
vzeroupper
instruction to set the upper half of a YMM register to 0, letting the CPU run the rest of the instructions using 128-bit calculations. The important thing to understand is that the underlying memory isn’t set to zero, but the pseudo-pointer is just flagged as equaling zero.
Now here’s the speculative execution: The CPU executes code ahead of time that includes a
vzeroupper
. If the CPU guesses wrong, it rolls back the execution, including that
vzeroupper
instruction, but the underlying storage may have already been assigned to one of the other XMM registers. The data is still there, and can simply be read back from the register. Note, this isn’t a side-channel attack, the data is just there, ready to be accessed.
What’s interesting is the sorts of data that is found in those registers. Modern compilers use these vector processing instructions for some essential functions, like
strcmp
,
memcpy
, and
srtlen
. Those routines deal with keys, passwords, log messages, and more.
I tested this on my server, powered by an AMD 7302P, and confirmed that from within a virtual machine, the
proof of concept
code was able to access log messages from the bare-metal Alma Linux install. That’s
really
not good. Thankfully, AMD has published a microcode patch for these server series processors, and
AlmaLinux has made that patch available
. I did repeat the test after installing, and the microcode patch does indeed shut down the data leak.
What about desktop and mobile chips? Well unfortunately,
those updates aren’t out yet
, and don’t have a target date until later this year — December in the worst case. It appears that the server patch from AMD came way ahead of schedule and let the cat out of the proverbial bag, explaining the less than coordinated disclosure we’re seeing.
Google’s Web Environment Integrity
The Internet is up in arms over a project at Google to
add Web Environment Integrity (WEI) to Google Chrome
. The purpose of the WEI proposal is
spelled out in the draft specification
. It allows a website to have confidence that a connection is coming from a real user, and a validated web environment, without violating that user’s privacy by fingerprinting them.
The way this would work is through attestation, where a trusted third party has access to the browser, and then attests that it is approved. This seems to be essentially an anti-cheat scheme, or another layer of DRM. Which is where we get into the weeds of possibly being a terrible idea.
This is
the argument made by Vivaldi
, there is no guarantee this new system won’t be terribly abused to keep other browsers out of the marketplace. And whither Linux? Anti-cheat measures have been very difficult to implement in a sane way on Linux. If the standard takes off, will Linux browsers just be locked out of the fun? Is it a better world when third parties get to determine the software you are allowed to run? It’s fair to say that we have more questions than answers.
Ubuntu’s Overlay
In a bit of research cleverly named “Game Over(lay)”, [Sagi Tzadik] and [Shir Tamari] of Wiz
describe a flaw they found in Ubuntu
‘s patches on top of OverlayFS. The short version is that the Linux kernel had a vulnerability in the OverlayFS kernel module in 2020. Fixes were added to the
vfs_setxattr
function, but Ubuntu exposes more functionality by skipping this function, and directly calling
__vfs_setxattr_noperm
. Because of the Ubuntu-specific changes, the fixes in the upstream kernel are bypassed in Ubuntu’s kernels.
The exact issue is the ability to set file capabilities.
setcap
is the newer, better approach to the
setuid
bit, which allows an unprivileged user to run a binary with greater capabilities. Take a look at
fping
:
[jbennett@Celeborn Downloads]$ getcap /usr/sbin/fping
/usr/sbin/fping cap_net_raw=ep
The key to making that secure is that only root can assign capabilities. Except inside container filesystems, where the process of building them sometimes requires file capabilities. The unprivileged user can launch a new namespace and create the more capable executable in the “lower” directory. Where this goes wrong is when the OverlayFS filesystem is mounted, and the executable gets
touch
ed. The system makes a copy of the file, to the “upper” half of the OverlayFS, but that copy exists outside the created namespace, escaping the sandbox.
The estimate is that
almost 40% of Ubuntu installs are vulnerable
to this exploit. Thankfully it’s a local-only escalation of privilege flaw. It’s still quite a menace as part of an attack chain, so go forth and patch!
Bits and Bytes
The Spring Java framework has an issue in the WebFlux component, where a double asterisk
**
pattern can hit an edge case in the security coverage,
potentially allowing for security bypass
. It clocks in at a CVSS 9.1 base score, and 8.8 overall.
And finally, don’t miss
our coverage of the intentional weakness in the TETRA radio standard
. The whole story reminds me quite a bit of
Operation Rubicon
, where Crypto AG shipped similarly compromised devices under the direction of the US and German governments. | 9 | 4 | [
{
"comment_id": "6666759",
"author": "anonymous",
"timestamp": "2023-07-28T14:34:34",
"content": "> What about desktop and mobile chips? Well unfortunately, those updates aren’t out yet…The mainline linux kernel already sets this “chicken bit”, which mitigates the issue, for any affected Ryzen proce... | 1,760,372,222.05917 | ||
https://hackaday.com/2023/07/28/solar-powered-game-of-life-follows-the-suns-rhythm/ | Solar PoweredGame Of LifeFollows The Sun’s Rhythm | Robin Kearey | [
"Misc Hacks"
] | [
"conways game of life",
"ESP32",
"ESP32 ULP",
"game of life",
"solar cell"
] | Conway’s
Game of Life
is a beautiful example of how complex behavior can emerge from a few very simple rules. But while it uses biological terminology such as “cells”, “alive” and “generation”, the basic game is too simplistic to be a model for any real-world biological process. It’s easy to add features to make it a bit more life-like, however, as [David Hamp-Gonsalves] has done by
giving the Conway’s creation something of a circadian rhythm
.
The basic idea is that the speed at which [David]’s
Game of Life
evolves is governed by the amount of ambient light. The game runs off a solar cell that charges a battery, with the battery’s voltage determining how long it takes to advance the game by one generation. The system is therefore highly active in full sunlight, and grinds almost to a complete halt at night.
An ESP32 runs the simulation and outputs the result to a 400 x 300 pixel e-ink display. The display is extremely power-efficient by its very nature; the ESP’s main processor core, on the other hand, is deliberately placed into deep sleep mode most of the time to save as much power as possible. The Ultra Low Power (ULP) co-processor, meanwhile, keeps an eye on the lithium battery’s voltage as it’s slowly being charged by the solar cell. When the voltage reaches 3.3 V, the main CPU wakes up and computes the
Game’s
new state. In bright sunlight this happens every few seconds, while on an overcast day it could take minutes or even hours.
[David]’s interesting idea of changing
Life
‘s activity based on the amount of energy available turns the
Game
into something resembling a cold-blooded animal. We’ve seen a similar approach in a “solar creature” that
runs a
Life
-life simulation on a seven-segment LCD
. If it’s speed you care about however, you’re better off
implementing
Life
in an FPGA
. | 6 | 5 | [
{
"comment_id": "6666721",
"author": "70sJukebox",
"timestamp": "2023-07-28T11:37:23",
"content": "Very nice work",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6666734",
"author": "Alex",
"timestamp": "2023-07-28T12:30:21",
"content": "Very elegan... | 1,760,372,221.680998 | ||
https://hackaday.com/2023/07/28/a-deep-dive-on-battery-life/ | A Deep Dive On Battery Life | Bryan Cockfield | [
"Battery Hacks",
"News"
] | [
"battery",
"battery life",
"embedded",
"firmware",
"IoT",
"lithium",
"measurement",
"metrics",
"software",
"testing"
] | There are all kinds of old wives’ tales surrounding proper battery use floating around in the popular culture. Things like needing to fully discharge a battery every so often, unplugging devices when they’re fully charged, or keeping batteries in the fridge are all examples that have some kernel of truth to them but often are improperly applied. If you really want to know the truth about a specific battery, its behavior, and its features,
it helps to dig in and actually take some measurements directly like [Tyler] has done
with a vast array of embedded batteries in IoT devices.
[Tyler] is a firmware engineer by trade, so he is deeply familiar with this type of small battery. Battery performance can change dramatically under all kinds of scenarios, most important among them being temperature. But even the same type of battery can behave differently to others that are otherwise identical, which is why it’s important to have metrics for the batteries themselves and be able to measure them to identify behaviors and possible problems. [Tyler] has a system of best practices in place for monitoring battery performance, especially after things like firmware upgrades since small software changes can often have a decent impact on battery performance.
While working with huge fleets of devices, [Tyler] outlines plenty of methods for working with batteries, deploying them, and making sure they’re working well for customers. A lot of it is extremely useful for other engineers looking to develop large-scale products like this but it’s also good knowledge to have for those of us rolling out our own one-off projects that will operate under battery power. After all,
not caring for one’s lithium batteries can have disastrous consequences
. | 12 | 3 | [
{
"comment_id": "6666691",
"author": "Elliot Williams",
"timestamp": "2023-07-28T09:02:51",
"content": "Love that a deep-dive in battery performance optimization ends with “everything would be better if it were just plugged into the wall”. :)",
"parent_id": null,
"depth": 1,
"replies": ... | 1,760,372,222.528342 | ||
https://hackaday.com/2023/07/26/hackaday-prize-2023-homebrew-spin-coater-makes-micrometer-thin-layers/ | Hackaday Prize 2023: Homebrew Spin Coater Makes Micrometer-Thin Layers | Robin Kearey | [
"Tool Hacks"
] | [
"dc motor controller",
"ESP32",
"laser cut cases",
"spin coat",
"spin coater"
] | One of the great things about the Gearing Up challenge of the 2023 Hackaday Prize is that it lets you discover tools that you don’t encounter every day. We had never given much thought to spin coaters, for example, until we saw
[Jeroen Delcour]’s neat homebrew example
. As it turns out, spin coating has lots of applications in fields like optics, semiconductor manufacturing or even art projects, where a thin, even layer of a material is required on top of a flat substrate.
The basic idea behind a spin coater is simple: you dispense a few drops of a solution containing the material to be deposited on top of the thing you want to coat, then spin the thing around at a constant speed. The balance between the centripetal force and the liquid’s surface tension ensures that the liquid turns into a film with a consistent thickness all across the substrate. The solvent evaporates, and you’re left with a nice solid layer just a few microns thick.
[Jeroen] built his spin coater out of a brushless DC drone motor, a programmable motor controller, and an ESP32. A rotary pushbutton and an OLED form the user interface, allowing the user to select the speed and spin times. The electronics are all mounted inside a laser-cut wooden enclosure, with the motor sticking out the top, surrounded by a 3D-printed splash guard.
Professional spin coating equipment typically comes with a vacuum chuck to hold the sample in place, but [Jeroen] wasn’t too excited about implementing vacuum systems on a spinning platform and decided instead to simply clamp down the sample using screws in a laser-cut piece of acrylic. This works well enough, and is easy to customize for different sample sizes.
In the video embedded below, [Jeroen] experiments with applying a layer of silicone rubber onto a PCB. Spin coating is an essential step when you’re making your own semiconductor devices
such as solar cells
, though you might also need more complicated equipment such as
an electron microscope
. [Jeroen]’s spin coater is at least able to process much larger objects than
one we saw earlier
.
The
Hackaday
Prize 2023
is Sponsored by: | 11 | 5 | [
{
"comment_id": "6666147",
"author": "NurseBobIsRetired",
"timestamp": "2023-07-26T18:07:39",
"content": "I hope he has access to a good hand surgeon… Seems that the “barrier” is maybe PLA or PETG. If things fly apart, I do wonder about the safety. Aside from that, pretty cool project.",
"parent... | 1,760,372,222.482097 | ||
https://hackaday.com/2023/07/26/adding-two-axes-makes-cnc-router-more-than-the-sum-of-its-parts/ | Adding Two Axes Makes CNC Router More Than The Sum Of Its Parts | Dan Maloney | [
"cnc hacks"
] | [
"5-Axis",
"automation",
"bearing",
"cnc",
"herringbone",
"pitch",
"production",
"rol",
"router",
"spindle"
] | The problem with building automated systems is that it’s hard to look at any problem and not see it in terms of possible automation solutions. Come to think of it, that’s probably less of a bug and more of a feature, but it’s easy to go overboard and automate all the things, which quickly becomes counterproductive in terms of time and money.
If you’re clever, though, a tactical automation solution can increase your process efficiency without breaking the budget. That’s where [Christopher Helmke] seems to have landed with
this two-axis add-on fixture for his CNC router
. The rig is designed to solve the problem of the manual modification needed to turn off-the-shelf plastic crates into enclosures for his line of modular automation components,
aspects of which
we’ve featured before. The crates need holes drilled in them and cutouts created in their sides for displays and controls. It’s a job [Christopher] tackled before with a drill and a jigsaw, with predictable results.
To automate the job without going overboard, [Christopher] came up with a tilting turntable that fits under the bed of the CNC router and sticks through a hole in the spoil board. The turntable is a large, 3D printed herringbone gear driven by a stepper and pinion gear. A cheap bearing keeps costs down, while a quartet of planetary gears constrain the otherwise wobbly platform. The turntable also swivels 90 degrees on a herringbone sector gear; together, the setup adds pitch and roll axes to the machine that allow the spindle access to all five sides of the crates.
Was it worth the effort? Judging by the results in the video below, we’d say so, especially given the number of workpieces that [Christopher] has to process. Add in the budget-conscious construction that doesn’t sacrifice precision too much, and this one seems like a real automation win. | 20 | 5 | [
{
"comment_id": "6666112",
"author": "Gravis",
"timestamp": "2023-07-26T15:58:28",
"content": "*sigh* disappointed it only has more than one axis and not a single axe.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6666173",
"author": "RPM",
... | 1,760,372,222.628547 | ||
https://hackaday.com/2023/07/26/chatgpt-the-worst-summer-intern-ever/ | ChatGPT, The Worst Summer Intern Ever | Dan Maloney | [
"Current Events",
"Featured",
"Interest",
"Original Art",
"Rants",
"Slider"
] | [
"ai",
"ChatGPT",
"freecad",
"intern",
"LLM",
"openscad",
"sheet metal"
] | Back when I used to work in the pharma industry, I had the opportunity to hire summer interns. This was a long time ago, long enough that the fresh-faced college students who applied for the gig are probably now creeping up to retirement age. The idea, as I understood it, was to get someone to help me with my project, which at the time was standing up a distributed data capture system with a large number of nodes all running custom software that I wrote, reporting back to a central server running more of my code. It was more work than I could manage on my own, so management thought they’d take mercy on me and get me some help.
The experience didn’t turn out quite like I expected. The interns were both great kids, very smart, and I learned a lot from them. But two months is a very tight timeframe, and getting them up to speed took up most of that time. Add in the fact that they were expected to do a presentation on their specific project at the end of the summer, and the whole thing ended up being a lot more work for me than if I had just done the whole project myself.
I thought about my brief experience with interns recently with a project I needed a little help on. It’s nothing that hiring anyone would make sense to do, but still, having someone to outsource specific jobs to would be a blessing, especially now that it’s summer and there’s so much else to do. But this is the future, and the expertise and the combined wisdom of the Internet are but a few keystrokes away, right? Well, maybe, but as you’ll see, even the power of large language models has its limit, and trying to loop ChatGPT in as a low-effort summer intern leaves a lot to be desired.
Lock Up Those Chickens
This chicken coop door needs a latch to prevent raccoons from sliding the aluminum door up. And yes, I could have built the whole thing from scratch, but I was in a hurry.
The specific task I needed help with was simple: a latch on the automatic door of my chicken coop. The details of why I need this are better left unsaid, but I will say that the latch is my attempt to deal with the cruel equation “11 Chickens + 1 Raccoon = 8 Chickens.” The first part for the latch that I had in mind was a simple bracket — something with two arms rising from a base that could be attached to the coop door (a sheet of 2-mm aluminum). This bracket will support a spring-loaded arm to engage a crossbar in the frame of the coop door, and hopefully prevent anything with clever little claws and a taste for take-out chicken from working under the lower edge of the sliding door and getting into the coop.
From my experience with Fusion 360, I knew it would be pretty easy to whip up a couple of sketches, extrude the arms up from the base, drill some holes, and tidy things up with the proper chamfers and fillets. The trouble with that is that I moved to Linux quite a few years ago, so Fusion 360 isn’t really a viable option. Yes, I know there are workarounds using Wine or VMs, but I’m also not interested in playing in Autodesk’s cloud. Of course, there’s FreeCAD, too; in fact, just prior to this project I had started fiddling with it, but I’m still in the early part of the learning curve and not terribly productive with it yet.
That final point gets to the crux of the matter, though. When I was learning Fusion 360, I found that it quickly became the case that perfecting the 3D model was mentally more important to me than what I was designing. I would spend hours getting everything just right, only to find out that something didn’t quite line up, or I had some constraint wrong, and I’d have to start all over again. I have every expectation that my mind will treat FreeCAD the exact same way, not as a means to an end but as the end itself. That’s a slippery slope, especially when there’s so much else I have to do.
The Mysteries of OpenSCAD
This is when I had the idea to outsource my design to someone — or some
thing
— else. Credit where it’s due; I got the idea to enlist ChatGPT after seeing
[ROFLhoff]’s Hackaday.io project about repairing a broken Toyota speedometer
. The project required a knob to easily spin the speed sensor that drives the speedo for bench testing. With just a brief description of the part needed, [ROFLhoff] was able to prompt ChatGPT to generate OpenSCAD code to create a model of the knob.
I thought that was pretty slick and decided to do the same. The bracket seemed like the best place to start, so I gave ChatGPT the following prompt:
My first attempt at getting ChatGPT to do my dirty work. Sorry if the units upset you — it’s how I think.
I know I wasn’t terribly specific — I didn’t say how far in from the corners the mounting holes should be, for instance — but I figured that was something I could tweak later. And besides, when you hand a job over to a subordinate, you should be able to just vaguely describe what you want, and let them run with it. Right?
Maybe not, because here’s what I got back from ChatGPT:
// Bracket dimensions
base_size = 1; // One inch square base
hole_radius = 1/16; // 1/8 inch hole radius
arm_width = 1/4; // 1/4 inch arm width
arm_height = 1/2; // 1/2 inch arm height
arm_gap = 1/4; // 1/4 inch gap between arms
// Base
base = cube([base_size, base_size, 1]); // 1 unit height
// Holes
hole_offset = hole_radius + 1/16; // Offset from base edges
hole = cylinder(h = 1, r = hole_radius);
// Calculate arm positions
arm_x = (base_size - arm_width) / 2;
arm_y = (base_size - arm_height) / 2;
// Arms
arm1 = cube([arm_width, arm_height, 1]); // 1 unit height
arm2 = translate([arm_width + arm_gap, 0, 0]) cube([arm_width, arm_height, 1]);
// Combine all parts
bracket = base - translate([hole_offset, hole_offset, 0]) hole +
translate([hole_offset, base_size - hole_offset, 0]) hole +
translate([base_size - hole_offset, hole_offset, 0]) hole +
translate([base_size - hole_offset, base_size - hole_offset, 0]) hole +
translate([arm_x, arm_y, 1]) arm1 +
translate([arm_x, arm_y, 1]) arm2;
// Render the bracket
render(bracket);
Now, it’s important to note that at the time, I had even less experience with OpenSCAD than I did with FreeCAD. And by less, I mean zero — I’d never used OpenSCAD before. So the code ChatGPT created didn’t mean all that much to me. But it sure looked reasonable, especially to someone who used to code for a living — I could see all the parameters up at the top like constants, the calculations used to figure out where to put the arms, and the creation of the cylindrical holes. But I had no idea what
translate
was, and I couldn’t really see how the holes would be punched through the base.
Strictly speaking, though, that wasn’t my problem. In the ideal world, I would just copy the AI-generated code into OpenSCAD and get a 3D model ripe for tweaking, right? Perhaps, but in the reality-based world, I had no such luck. The code ChatGPT generated didn’t work in OpenSCAD — it just threw a syntax error on line 21. I told ChatGPT about the error and asked to have it fixed, but the code that came back was essentially the same and threw the same error. Disappointing.
If You Want Something Done Right…
At this point, I figured I had two choices: either keep fiddling with the ChatGPT prompt, or start learning enough OpenSCAD to figure out what ChatGPT was doing wrong. All things considered, the latter seemed like the smarter route, so that’s the way I went. It was quickly apparent that ChatGPT didn’t have the slightest idea how to program OpenSCAD — for example, note the complete lack of
difference()
commands, which are needed to make the holes, from the AI-generated code. This led me down the very rabbit hole I was trying to avoid, and I spent a few hours learning enough OpenSCAD to do the job myself:
// dimensions in mm [width, depth, height]
base_size = 25;
base_thickness = 3;
upper_size = base_size - 10;
upper_height = upper_size;
base = [base_size,base_size,base_thickness];
upper = [upper_size,upper_size,upper_height];
slot_width = upper_size/3;
slot = [upper_size + 2,slot_width, upper_height];
hole_dm = 3;
hole_margin = 1.5;
axle_dm = 4;
module bracket() {
difference() {
cube( base );
abs_margin = hole_margin + hole_dm / 2;
x_hole_dist = base.x - 2 * abs_margin;
y_hole_dist = base.y - 2 * abs_margin;
x_values = [abs_margin : x_hole_dist : base.x - abs_margin];
y_values = [abs_margin : y_hole_dist : base.y - abs_margin];
// holes
$fn = 25;
for (x = x_values, y = y_values)
translate( [x, y, -1] )
cylinder( d = hole_dm, h = base.z + 2);
}
translate([(base_size-upper_size)/2, (base_size-upper_size)/2,0])
difference() {
cube( upper );
translate([-1,upper_size/3,upper_size/3]) cube( slot );
translate([(upper_size/2),-1, (base_size/2)-2])
{
$fn = 25;
rotate([-90,0,0]) cylinder(d=axle_dm, upper_size + 2 );
}
}
}
module latch() {
$fn=25;
difference() {
union() {
cube([35.5, (axle_dm + 5)/2,slot_width-1]); // main arm
translate([35.5,(axle_dm + 5)/2 -0.8,0]){
rotate([0,0,-185]) cube([(axle_dm + 5)/2, 10, slot_width-1]);
}
translate([0,(axle_dm + 5)/2,0]){ // lever
rotate([0,0,135]) cube([15, (axle_dm + 5)/2,slot_width-1]);
}
cylinder(d=axle_dm + 5, h= slot_width-1); // pivot body
}
cylinder(d=axle_dm, h=slot_width+1); // pivot hole
}
}
bracket();
translate([0,50,0])
latch();
Here’s what I finally came up with in OpenSCAD.
Was It Worth It?
Granted, my OpenSCAD code has both the bracket and the latch, but even accounting for the added complexity, I feel like ChatGPT’s first pass at doing what I wanted was half-assed at best. This is about the point where I realized that ChatGPT was behaving like an earnest and eager-to-please but somewhat clueless summer intern. Given the same instructions, such an intern might go off and spend a few hours Googling how to do the job, maybe hitting StackExchange or r/openscad for some help, and coming up with some code that they figured would do the job. That they didn’t even bother to see if OpenSCAD would interpret the code would be grounds for a Stern Talking-To™ with a meatspace intern; but with a virtual intern, what recourse did I have?
Honestly, although I didn’t get the magic help from ChatGPT that I was hoping for, this experiment in AI-assisted design wasn’t a complete loss. The original code may have been crap, but it at least gave me the impression that OpenSCAD programming wasn’t entirely foreign territory for me; flawed though it was, I could see that it’s just a combination of coding and 3D modeling, and intuitive enough to take a stab at. So now I know just enough OpenSCAD to be dangerous, all thanks to ChatGPT — the worst summer intern ever.
And as for the coop door latch, that project went in an entirely different direction once I realized that I could make the bracket and the latch from bent sheet aluminum — which forced me to learn not only FreeCAD but the Sheet Metal workbench as well. So ChatGPT actually forced me down two rabbit holes I’d hoped to avoid. | 71 | 29 | [
{
"comment_id": "6666092",
"author": "Klaws",
"timestamp": "2023-07-26T14:35:02",
"content": "Simple: ChatGPT has sided with the racoons.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6666113",
"author": "Paul d'Aoust",
"timestamp": "2023-07... | 1,760,372,223.0542 | ||
https://hackaday.com/2023/07/26/serious-vulnerability-in-european-trunked-radio-system/ | Serious Vulnerability In European Trunked Radio System | Bryan Cockfield | [
"Radio Hacks"
] | [
"infrastructure",
"radio",
"SCADA",
"security",
"tetra",
"trunked radio",
"trunking",
"vulnerability"
] | Trunked radio systems can be difficult to wrap one’s mind around, and that’s partially by design. They’re typically used by organizations like police, firefighters, and EMS to share a limited radio frequency band with a much larger number of users than would otherwise be able to operate. From a security standpoint, it also limits the effectiveness of scanners who might not know the control methods the trunked systems are using. But now a global standard for encrypted trunked radio systems, known as TETRA,
has recently been found to have major security vulnerabilities
, which could result in a lot more headache than disrupted voice communications.
One of the vulnerabilities in this radio system was a known backdoor, which seems to have been protected largely via a “security through obscurity” method. Since the system has been around for about 25 years now, it was only a matter of time before this became public knowledge. The backdoor could allow non-authorized users to snoop on encrypted radio traffic. A second serious vulnerability, unrelated to this backdoor, would further allow listening to encrypted voice traffic. There are a few other minor vulnerabilities recently uncovered by the same security researchers who found these two major ones, and the current recommendation is for anyone using a TETRA system to take a look to see if they are impacted by any of these issues.
Part of the reason this issue is so concerning is that these systems aren’t just used for encrypted voice among first responders. They also are used for critical infrastructure like power grids, rail networks, and
other systems controlled by SCADA
.
This article from Wired
goes into much more detail about this vulnerability as well, and we all know that
most of our infrastructure already needs significant help
when it comes to vulnerabilities to all kinds of failure modes.
Thanks to [cfacer] and [ToniSoft] who sent these tips!
Photo via
Wikimedia Commons
. | 41 | 12 | [
{
"comment_id": "6666044",
"author": "Foo",
"timestamp": "2023-07-26T11:10:37",
"content": "Wired link requires 12ft:https://12ft.io/proxy?&q=https%3A%2F%2Fwww.wired.com%2Fstory%2Ftetra-radio-encryption-backdoor",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6... | 1,760,372,222.711103 | ||
https://hackaday.com/2023/07/26/where-old-files-go-to-die/ | Where Old Files Go To Die | Elliot Williams | [
"Art",
"Software Hacks"
] | [
"art",
"files",
"graveyard"
] | We all lead digital lives, and we work in and on files of one sort or another. And sometimes we get attached to them. That long manifesto you poured your heart into, but nonetheless probably shouldn’t see the light of day? Love letters from former flames? Your first favorite video game that you can’t play any more, but it just sits there eating up drive space?
These are the files that are important enough that they deserve better than just a drag-and-drop into the trashcan. They deserve to be buried with dignity, and that’s just what [Ulf Schleth]’s
/death/null
offers us – a
digital graveyard where our files no longer exist as they were
, but still are allowed to linger in memory.
This is an old project, but one that tickled our funny and poignant bones in equal parts. The pun on
/dev/null
probably works just a little better if you read both filepaths with a German accent in your head, but the idea translates anyway.
To use it, you simply upload your file and it gets sent to the great trashcan in the sky, but along the way a 4 x 5 matrix of colored blocks is created that represents the file, and it is registered forever in the graveyard, where you can check up on it any time you like. Of course you can’t read it – only 20 RGB triples remain – but you have the digital “gravestone” as commemoration.
Even if you don’t have any loved ones in [Ulf]’s graveyard, you can walk by and see which files others have chosen to remember. Swing on by and pay your respects to
notepad.exe
. | 30 | 13 | [
{
"comment_id": "6666018",
"author": "Merser",
"timestamp": "2023-07-26T08:42:40",
"content": "Haha, I still use notepad for like sticky notes. But notepad++ has become a much more awesome replacement.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6666031",
... | 1,760,372,222.886716 | ||
https://hackaday.com/2023/07/25/beautifully-rebuilding-a-vr-headset-to-add-ar-features/ | Beautifully Rebuilding A VR Headset To Add AR Features | Donald Papp | [
"Virtual Reality"
] | [
"3d printed",
"3d scanning",
"ar",
"augmented reality",
"custom",
"hand tracking",
"Quest",
"Stereolabs",
"Ultraleap",
"virtual reality",
"vr"
] | [PyottDesign] recently wrapped up a personal project to create himself a custom AR/VR headset that could function as an AR (augmented reality) platform, and make it easier to develop new applications in a headset that could do everything he needed. He succeeded wonderfully, and published
a video showcase of the finished project
.
Getting a headset with the features he wanted wasn’t possible by buying off the shelf, so he accomplished his goals with a skillful custom repackaging of a Quest 2 VR headset, integrating a
Stereolabs Zed Mini
stereo camera (aimed at mixed reality applications) and an
Ultraleap IR 170
hand tracking module. These hardware modules have tons of software support and are not very big, but when sticking something onto a human face, every millimeter and gram counts.
[PyottDesign]’s work reveals quite a few nice build details. He 3D scanned his face in order to create parts with a custom fit and made great use of 3D printing, even dyeing parts as needed. Other structural components were cut from thin carbon fiber inlay sheets, which provided great strength with very little mass.
Main components
A simple AR application demo
The end result does require three separate USB cables (one for each of the main hardware components) so a possible improvement would be to integrate some kind of hub, but for now [PyottDesign] is just going to enjoy the fruits of his labors. The video showcasing the end result (embedded below, under the page break) gives a summary of the build process, but if you’d like to delve into aspects of the project in more detail, check out the
10-video series
covering everything from concept to finished unit.
Speaking of DIY VR headsets, we recently saw
another custom headset build
that took a much more ground-up approach, but also serves as a reminder of just how much work goes into building something like this. Like they say, developing hardware is just like software, except every time you hit “compile” it costs money and takes weeks. | 12 | 3 | [
{
"comment_id": "6666011",
"author": "ono",
"timestamp": "2023-07-26T07:46:28",
"content": "Can´t wait to see all commuters fitted with such a thing (and some cheap versions with ads). A bright future for dehumanity !",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment... | 1,760,372,222.938489 | ||
https://hackaday.com/2023/07/25/no-fish-left-behind/ | No Fish Left Behind | Bryan Cockfield | [
"chemistry hacks"
] | [
"100% fish project",
"biology",
"Chemistry",
"fish",
"fisheries",
"graft",
"Iceland",
"skin",
"waste"
] | For hundreds of years, Icelanders have relied on the ocean for survival. This is perhaps not surprising as it’s an isolated island surrounded by ocean near the Arctic circle. But as the oceans warm and fisheries continue to be harvested unsustainably, Iceland has been looking for a way to make sure that the fish they do catch are put to the fullest use, for obvious things like food
and for plenty of other novel uses as well
as they work towards using 100% of their catch.
After harvesting fish for food, most amateur fishers will discard around 60% of the fish by weight. Some might use a portion of this waste for fertilizer in a garden, but otherwise it is simply thrown out. But as the 100% Fish Project is learning, there are plenty of uses for these parts of the fish as well. Famously, cod skin has been recently found to work as skin grafts for humans, while the skin from salmon has been made into a leather-type product and the shells of crustaceans like shrimp can be made into medicine. The heads and bones of fish can be dried and made into soups, and other parts of fish can be turned into things like Omega-3 capsules and dog treats.
While we don’t often feature biology-related hacks like this, out-of-the-box thinking like this is an important way to continue to challenge old ideas, leave less of a footprint, improve human lives, and potentially create a profitable enterprise on top of all of that. You might even find that life in the seas can be used for things you never thought possible before,
like building logic gates out of crabs
.
Thanks to [Ben] for the tip! | 25 | 7 | [
{
"comment_id": "6665966",
"author": "echodelta",
"timestamp": "2023-07-26T02:22:08",
"content": "Title should be no parts of fished fish left behind. No fish left… scary.Fish heads fish heads, eat ’em up yum.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6... | 1,760,372,222.819543 | ||
https://hackaday.com/2023/07/25/486-gets-animated-turbo-button-thanks-to-arduino/ | 486 Gets Animated Turbo Button Thanks To Arduino | Tom Nardi | [
"Arduino Hacks",
"Retrocomputing"
] | [
"486",
"arduino pro mini",
"turbo button"
] | There was a point in time, excruciatingly brief, in which desktop computers often had a large “TURBO” button on their front panel. Some even featured an LED display that would indicate the current CPU frequency, providing visual conformation that your machine had leaped to a blistering 66 MHz.
The 486 that [someyob] is restoring had the Turbo button, but sadly there was just a simple LED to show whether or not it was engaged. But there
was
a window in the front panel where it seemed like a numerical display was intended to go, so they
decided to wire up their own CPU indicator
by sensing the state of the Turbo LED with an Arduino Pro Mini.
Now to modern audiences, this might seem like cheating. After all, the Arduino isn’t actually measuring the CPU speed, nor is it directly controlling it (that’s still done by the original Turbo button wiring). But the truth is, even back in the day, the CPU frequency displays faked it — they just toggled between showing two predefined frequencies depending on the state of the button. The arrangement [someyob] has come up with does the same thing, except now there’s some extra processing power in the mix, so the display can show some slick animations as it switches between 33 and 66 Mhz.
In the GitHub repository, [someyob] has provided the Arduino source code and schematics showing how the microcontroller was shoehorned into the existing front panel wiring without compromising its functionality. There’s even a brief video below that shows the display in operation.
Like the idea but don’t have a 486 laying around? Don’t worry. We’ve seen a
similar panel built for modern machines
that just doesn’t look the part, it actually manages to be functional. | 27 | 6 | [
{
"comment_id": "6665942",
"author": "Piecutter",
"timestamp": "2023-07-25T23:26:12",
"content": "Pedantic comments regarding LCD vs LED, begin here.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665946",
"author": "TG",
"timestamp": "2023-... | 1,760,372,223.116819 | ||
https://hackaday.com/2023/07/25/debian-officially-adds-risc-v-support/ | Debian Officially Adds RISC-V Support | Bryan Cockfield | [
"Linux Hacks"
] | [
"architecture",
"arm",
"debian",
"debian 13",
"linux",
"RISC-V",
"trixie"
] | As time goes on, more and more computer manufacturers are moving towards the ARM architecture and away from the bloated and outdated x86 instruction set. Apple is the most prominent producer to take this step, but plenty others are using ARM for its flexibility and efficiency. The only problem with ARM is that it’s licensed, so if you want to go even further down the open-source path the RISC-V instruction set is the next logical step. Now
at least one mainline Linux distribution will officially support this architecture
.
While Debian did have some support for RISC-V before this as a Debian port, which was not officially part of Debian. However, the official support will begin with the release of Debian 13, which is currently in the testing phase and hasn’t seen a stable release yet. To that end, the current state of this official version is extremely limited, being described as “almost empty” but with planned support for an initial 90 packages in the coming days. Most users working on a RISC-V platform will most likely to continue to use their Debian ports version.
It might be a little while before the RISC-V version is as full-featured as the ARM or x86 versions of this Linux distribution, but we are happy to see it move in this direction at all. And don’t think that RISC-V is limited to embedded systems or otherwise limited computing platforms, either. We’ve seen
full Linux desktops with RISC-V processors since at least 2019
. | 21 | 5 | [
{
"comment_id": "6665899",
"author": "Truth",
"timestamp": "2023-07-25T20:13:48",
"content": "Looking at the history of official Debian releases, Version 13, codename “Trixie” will be sometime during summertime 2025. Lots of time to get everything in good order. Hopefully on a shiny new longterm Lin... | 1,760,372,223.174365 | ||
https://hackaday.com/2023/07/25/car-security-system-monitors-tiny-voltage-fluctuations/ | Car Security System Monitors Tiny Voltage Fluctuations | Bryan Cockfield | [
"Security Hacks",
"Transportation Hacks"
] | [
"can-bus",
"car",
"security",
"vehicle",
"voltage",
"voltage drop",
"voltage sag"
] | As the old saying goes, there’s no such thing as a lock that can’t be picked. However, it seems like there are plenty of examples of car manufacturers that refuse to add these metaphorical locks to their cars at all — especially when it comes to securing the electronic systems of vehicles. Plenty of modern cars are essentially begging to be attacked as a result of such poor practices as unencrypted CAN busses and easily spoofed wireless keyfobs. But even if your car comes from a manufacturer that takes basic security precautions, you still might want to check out
this project from the University of Michigan that is attempting to add another layer of security to cars
.
The security system works like many others, by waiting for the user to input a code. The main innovation here is that the code is actually a series of voltage fluctuations that are caused by doing things like turning on the headlights or activating the windshield wipers. This is actually the secondary input method, though; there is also a control pad that can mimic these voltage fluctuations as well without having to perform obvious inputs to the vehicle’s electrical system. But, if the control pad isn’t available then turning on switches and lights to input the code is still available for the driver. The control unit for this device is hidden away, and disables things like the starter motor until it sees these voltage fluctuations.
One of the major selling points for a system like this is the fact that it doesn’t require anything more complicated than access to the vehicle’s 12 volt electrical system to function. While there are some flaws with the design, it’s an innovative approach to car security that, when paired with a common-sense approach to securing modern car technology, could add some valuable peace-of-mind to vehicle ownership in areas prone to car theft. It could even alleviate the problem of
cars being stolen via their headlights
. | 43 | 17 | [
{
"comment_id": "6665874",
"author": "KD9KCK",
"timestamp": "2023-07-25T19:02:34",
"content": "This makes me think of stories my dad told be about wiring stuff up so you have to have say an annoying back blower (that had a rear HVAC thing) on to start the van, as a security measure, since a random t... | 1,760,372,223.414713 | ||
https://hackaday.com/2023/07/25/retrotechtacular-the-computer-center-of-1973/ | Retrotechtacular: The Computer Center Of 1973 | Al Williams | [
"Retrotechtacular",
"Slider"
] | [
"bell labs",
"ibm",
"IBM 370"
] | You might expect Bell Labs would have state-of-the-art computers, and they did. But it is jarring to realize just how little that was in 1973, fifty years ago. If you started work at Bell’s Holmdel Computing Center back then, you might have
watched one of the orientation videos below
. Your first clue about how far things have come might be the reference to the IBM 370/165, which had “3 million bytes of core, 2 million of which are available for programmer use.” Even our laptops today have at least 8 gigabytes of RAM. There were at least two other smaller IBM 370s, too. Plenty of 029 card punches are visible.
If you were trying to run something between 8:00 AM and 5:30 PM, you had to limit your job run time to three minutes, 4,000 lines of output, and no more than 1,000 cards in and 5,000 cards out. Oh, and don’t use more than 384 kB of that core memory, either. If you fell within those limits, you could hand your card deck over at the express counter and get your results in only five or ten minutes. If you were not in the express line but still rated “premium” service, you could expect to wait a half hour.
The main desk had a card reader that could read 200 80-column cards a minute. The cards didn’t directly feed the computer, though. They were written to a hard drive for later processing by the computer. If you needed a lot of storage, though, you opted for magnetic tape. The tapes could hold a whopping 1,600 bytes per inch. The blistering tape data transfer speed was 320 kB/s. Latency could be a problem, though, since a nice lady had to find your tape and put it on a counter for an operator to load onto a tape drive.
The disk drives were cool for 1973 if you could handle the $80,000 price tag, although most companies leased them. Since the video was made in 1973, we assume this was the older disk packs that held about 100 MB of data, although later units could store 200 MB per disk pack. The 11.2 MB fixed disks were much faster.
The computing center generated 2.8 million lines of printouts on about 1,000 pounds of paper a day. They also punched about 40,000 cards a day. But that was all batch processing.
The real modern computer was a timeshare system centered around an IBM 370/155. It only had 2 MB of core, half of which was “low-speed” memory. The computer could do APL, word processing, and even picture phone calls.
Can’t get enough of the old computer video? Then check out
part 2
of the video, too. There, you’ll see the 1973 equivalent of Stack Overflow — a real library with librarians. They could help you write code in Assembly, FORTRAN, PL/I, APL, SNOBOL, SPITBOL, and more. We can’t really say we miss these days, although having someone entering your data for you seems like a nice luxury.
If the IBM 370 is too modern for you, there’s
always the 360
. If card punching is your thing, you can
read more about it and even punch your own virtual cards
. | 35 | 10 | [
{
"comment_id": "6665868",
"author": "Simon",
"timestamp": "2023-07-25T18:13:24",
"content": "Ha, they have a pinup girl taped to the main console, probably wouldn’t make it into the industrial promo film these days.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_... | 1,760,372,223.339177 | ||
https://hackaday.com/2023/07/25/procrastinators-rejoice-2023-supercon-call-for-participation-extended/ | Procrastinators Rejoice! 2023 Supercon Call For Participation Extended | Elliot Williams | [
"cons",
"News"
] | [
"2023 Hackaday Supercon",
"2023 Hackaday Superconference",
"call for participation"
] | When we closed the official Call for Participation for both workshops and talks last week, a good handful of folks wrote to us and asked if they could slip their presentation application in after the deadline. Who are we to say “no” to potential presenters? We want to see all the ideas!
We’re officially extending the
Call for Speakers
and the
Call for Workshops
for another week. Get your outline in before Aug. 1st at 9:00 AM PDT, and it’ll be in the selection for Supercon. (And no, we’re not going to extend it twice!)
The Hackaday Superconference is really and truly our favorite event of the year. It’s small, but not too small. The ideas everyone brings with them, however, are big. It’s like the absolute best of Hackaday live and in person. If you’re looking for a place to give a technical talk, or just to regale us all with the trials and triumphs of hacking, you won’t find a more receptive audience anywhere. Plus, presenters get in free.
Behind the scenes, we’re still working on the badge, but we’ve got many of the details fully hammered down. Expect tickets to go on sale in the second week of August – early bird tickets sell out fast. Keep your eyes on Hackaday for the announcement post when it goes live.
We know that November seems a long way out, but we’re looking forward to seeing you all already. Hooray for Supercon! | 4 | 3 | [
{
"comment_id": "6667544",
"author": "aquahoodch",
"timestamp": "2023-07-30T18:23:14",
"content": "Can you have an International Supercon as you must be aware that 1. As Hackers / Makers / Tinkers m, we don’t have much money. 2. The United States only makes up a portion of your readers, supporter, l... | 1,760,372,223.461777 | ||
https://hackaday.com/2023/07/25/tivoli-teardown-disappoints/ | Tivoli Teardown Disappoints | Chris Lott | [
"home entertainment hacks",
"Radio Hacks"
] | [
"fm radio",
"Model One",
"teardown",
"Tivoli"
] | [Fran] has been curious about the innards of Tivoli Audio’s Model One radio, but was reluctant to shell out $200 just to tear it apart. But she found one recently on eBay, won the auction, and
proceeded to do a review and teardown
. Spoiler alert, she was disappointed.
Physically speaking, the radio looks great and has quite an array of I/O connections. The geared tuning knob looks cool, but is heavily damped which [Fran] isn’t keen about. Turning it on, a few more quirks are discovered. The volume control is out-of-whack — it appears they substituted a linear taper potentiometer where a logarithmic taper was called for.
Another problem, at least in the RF-dense metropolitan areas like Philadelphia, is the FM tuner’s station-lock feature. It is so strong that it can be impossible to tune in weak stations. This is especially ironic since, according to Wikipedia, that was one of audio engineer Henry Kloss’s main goals when founding Tivoli Audio back in 2000:
Their first product was the Model One, a simple to use mid-century modern designed table top radio with a high-performance tuner, receiving FM radio in congested urban locations, while maintaining the ability to pick out distant or low power stations. Kloss had noted that the mid 60’s wave of Japanese radios lacked the ability to receive FM stations in congested locations, and this became a defining goal of his radio designs throughout his career.
Interestingly, many folks in the YouTube comments say their Model One radios have none of these issues. We wonder if [Fran] has obtained a damaged radio, or maybe a newer version produced with less attention to detail. If you have a broken Model One radio, before tossing it, consider
the hack we wrote about last year
, turning it into an internet radio. | 32 | 16 | [
{
"comment_id": "6665837",
"author": "Andre Bryx",
"timestamp": "2023-07-25T15:52:25",
"content": "The hyped and overpriced “Tivoli” is nothing more than a bad designed over 20 yr old 08/15 Receiver on the cheapest way. They´re nothing worth the prices are called today.So many of my small cheap Germ... | 1,760,372,223.53364 | ||
https://hackaday.com/2023/07/25/pcie-for-hackers-our-m-2-card-is-done/ | PCIe For Hackers: Our M.2 Card Is Done | Arya Voronova | [
"Featured",
"News",
"Skills",
"Slider"
] | [
"layout",
"PCB design",
"PCIe",
"routing"
] | We’ve
started designing a PCIe card last week
, an adapter from M.2 E-key to E-key, that adds an extra link to the E-key slot it carries – useful for fully utilizing a few rare but fancy E-key cards. By now, the schematic is done, the component placement has been figured out, and we only need to route the differential pairs – should be simple, right? Buckle up.
Getting Diffpairs Done
PCIe needs TX pairs connected to RX on another end, like UART – and this is non-negotiable. Connectors will use host-side naming, and vice-versa. As the diagram demonstrates, we connect the socket’s TX to chip’s RX and vice-versa; if we ever get confused, the laptop schematic is there to help us make things clear. To sum up, we only need to flip the names on the link coming to the PCIe switch, since the PCIe switch acts as a device on the card; the two links from the switch go to the E-key socket, and for that socket’s purposes, the PCIe switch acts as a host.
While initially routing this board, I absolutely forgot about one more important thing for PCIe – series capacitors on every data pair, on the host TX side of the link. We need three capacitor pairs here – on TX of the PCIe switch uplink, and two pairs on TX side of the switch – again, naming is host-side. I only remembered this after having finished routing all the diffpairs, and, after a bit of deliberation, I decided that this is my chance to try 0201 capacitors. For that, I took
the footprints
from
[Christoph]
‘s wonderful project, called
“Effect of moon phase on tombstoning”
– with such a name, these footprints have got to be good.
We’ve talked about differential pair calculations before in one of the PCIe articles, and there was a demo video too! That said, let’s repeat the calculations on this one – I’ll show how to get from “PCB fab website information” to “proper width and clearance diffpairs”, with a few fun shortcuts. Our setup is, once again, having signals on outer layers, referenced to the ground layer right below them. I, sadly, don’t yet understand how to calculate differential impedance for signal layers sandwiched between two ground planes, which is to say – if there’s any commenters willing to share this knowledge, I’d appreciate your input tremendously! For now, I don’t see that there’d be a tangible benefit to such an arrangement, anyway.
Different Stackup Might Help
This time, I’m going with a 4-layer 0.8 mm stackup – otherwise the board won’t fit into an M.2 socket. According to the design rules, I can go down to 3.5 mil (0.09 mm) traces and spacings, as opposed to the usual 6 mil (0.16 mm) traces I’m used to when doing generic 2-layer boards. Initially, I’m choosing the 7628 stackup variant here – the main difference between stackups here is the prepreg thickness and the dielectric constant, which impacts minimum possible diffpair thickness and spacing.
I went by parameters on
the JLCPCB stackup page,
and took via parameters from the ordering page – you can put these parameters into the “File => Board Setup” window, in the “Net Classes” tab. After replacing the default parameters there with the 4-layer impedance controlled process ones – clearance, minimum trace width, via size and such, – we get some pretty lovely parameters that we can drop down to if there’s ever a tight spot, and an ability to do reasonably dense component placement.
Let’s aim for on-point 85 ohm differential impedance today – a great target wherever you can afford it. Again, traces on top, uninterrupted ground plane right under them, along the entire length of the pairs. For “7628” stackup, that means there’s 0.21 mm of material with 4.6 Er between the pairs and the ground – punch these two values into the calculator, leave copper thickness at 35 um (1oz copper), and we can play around with trace space and width values, down to our 0.09 mm limit – which leads us to a 0.225 mm width / 0.09 mm space option. This isn’t all that great space-wise, however.
You don’t have to stick with the default stackup, though! After little deliberation, I switched to the “3313” stackup – with 4.05 Er and 0.1 mm thick prepreg between top and middle layers. It seems to be a tad more expensive, but it does look a bit easier to route in the small amount of space that I have. This led me to 0.135 mm / 0.09 mm pairs, while keeping the same 85 ohms differential impedance. Now, all I need to do is to enter these parameters into the “Net Classes” table, and whenever I press ‘6’, I’ll immediately start drawing a 85 ohm impedance differential pair.
Diffpair Drawing
The IC is placed, the diffpair parameters are tuned – we can start drawing. Remember, flipping the PCIe pair polarity isn’t a crime, it’s an obligation to make routing easier on yourself. Somehow, in this design it wasn’t needed even once.
You do, however, need a bit of patience – KiCad’s differential pair drawing experience isn’t always smooth; if you’re having weird problems where one end of the pair doesn’t quite connect to another end, you’re not alone. For me, drawing these pairs was a tad infuriating. It’s conceivable that what I’m dealing with something commonly referred to as a skill issue – perhaps, there’s a setting I’m not noticing, as sometimes such “does not connect” problems are caused by DRC constraints. However, in that case, there will be a warning shown to you on the bar above.
Remember, whenever your diffpair crosses from top to bottom layer or vice-versa, it also changes reference layers, from In1 to In2 respectively – and you’ll want to add ground vias near the diffpair vias, so that the ground return current can travel along the pair, too. As usual, four vias are ideal, three are good, two are okay, and one is non-ideal but better than zero.
Once we’ve drawn diffpairs and added ground vias, there’s one last thing to take care of. While PCIe pairs don’t have to all be the same length, the two traces that each pair consists of, do have to be the same end to end. For that, you can use the differential pair skew correction tool – mapped to 9 on the keyboard. It will add a wiggle to the longer track, in the spot where a wiggle would fit best.
All The Layers
When drawing boards, you can often use one GND and one VCC internal layer – as technically, both VCC and GND can be used as reference planes for high-speed signals. However, since we’re crossing diffpairs between top and bottom layers, they would then have different references, and this is still unexplored territory for me – I’m not sure whether there’d be return current problems. I’ve started out with one 1.2 V and one GND internal plane, but afterwards, as I was sanity-checking my boards and writing this article, I talked with other engineers, re-read an interesting comment thread under the first PCIe diffpair article, and decided to switch to having both internal planes as GND.
When it comes to the outer layers where diffpairs go, you’ll want to remove the ground fill or move it away, so that the ground fill around the pair will affect the diffpair’s impedance – you are highly likely see a ground keepout if you take a look at any PCIe card you own. Here, I am going to route diffpairs on the outer layers, but I’m not not going to completely remove ground on these, using keepouts instead. First off, having ground is cool – it’s extra copper that can help dissipate heat from the switch, or the switching regulator, or both. Second thing is – JLCPCB has been weird about ground fills on dense boards recently, and I’ll want to avoid that.
How far should the keepout go, then? The 5L rule (five trace widths away) is a good one, or you can just keepout the entire area where you’re pulling the differential pairs. For us, 5L means 5 * 0.135 mm, or 0.685 mm distance between the pair/via and the ground fill. The 5L rule isn’t a hard limit – keep to it as much as possible, but don’t stress about having a few vias here and there. Remember, when wiring up PCIe, it’s important that the string is wet.
For power wires, use your thickest traces possible wherever you have space. Of course, you don’t need to pull a 2 mm track wherever you want to put 3.3 V, but having 0.6 mm or 1 mm tracks on a 3.3 V 1 A path is pretty ordinary – some will say it’s overkill, but if you have enough space, there’s hardly a benefit to not doing it. If you’re wondering what you can get away with, there are trace width calculators that will give you temperature increase and inductance values, but most of the time, making the trace thicker is a no-brainer.
After we wire up PCIe and power signals, there are a few things left. It might be tempting to route them on the inner ground layers – do your best to fight the temptation, however, as there’s usually a better way; having unbroken inner planes is widely accepted to be good mojo for diffpairs, and for signals in general. Instead, consider other nonstandard options that are less of a sin – for instance, it’s okay to remove solder pads from a footprint if the pad is unused, and that’s what I’m going to do to pull one of the PERST signals through the top layer.
Mistakes And Problems
In many aspects, this design hits the bullseye. It’s compact, it fits everything it should fit with space to spare, and the onboard power delivery is more than reasonable. Of course, there are a few possible hiccups I can foresee happening that I will check for once these boards are manufactured.
A PCIe switch functions at high speeds, so it makes sense that power consumption could be a bit harsh, and same would go for heat dissipation – indeed, you will see higher-port-count chips like these covered with glued-on heatsinks on Chinese adapters; My main concern is power consumption – a M.2 E-key card is expected to consume 2 A at most, and the peak power consumption of the switch, together with the inserted card itself, might exceed this budget for sure.
To solve that, I’m adding a separate power input, and drawing traces in a way that, if needed, it’s easy to separate the 1.2V regulator 3.3 V input from the E-key card power. My second concern about the power consumption, however, is thermal dissipation – there isn’t much thermal mass in this PCB, and the ground path isn’t too straightforward, so the chip could theoretically overheat under load. There wouldn’t really be place for a heatsink once the adapter’s plugged into a laptop, either – we’ll see just how much of a problem this is in practice.
Every board can be a small experiment, and this one’s definitely got a few things I’ve never tried before. I’ve added this board to my last PCB order, and once it arrives, I’ll share the end result with you all, one way or another. Until then, the files are on GitHub, and I hope that this board’s story gives you plenty of insights into designing with PCIe! | 18 | 14 | [
{
"comment_id": "6665816",
"author": "ftg",
"timestamp": "2023-07-25T14:31:23",
"content": "Both of these PCIe and m.2 article series have been excellent.This has given some new motivation to revisit some old project ideas that involve one or the other.",
"parent_id": null,
"depth": 1,
"... | 1,760,372,223.591948 | ||
https://hackaday.com/2023/07/25/selectric-typewriter-goes-from-trash-can-to-linux-terminal/ | Selectric Typewriter Goes From Trash Can To Linux Terminal | Dan Maloney | [
"Retrocomputing"
] | [
"ibm",
"interposer",
"linux",
"rs-232",
"Selectric",
"solenoid",
"teletype",
"terminal",
"tty",
"whiffletree"
] | If there’s only lesson to be learned from [alnwlsn]’s
conversion of an IBM Selectric typewriter into a serial terminal for Linux
, it’s that we’ve been hanging around the wrong garbage cans. Because that’s where he found the donor machine for this project, and it wasn’t even the first one he’s come across in the trash. The best we’ve ever done is a nasty old microwave.
For being a dumpster find, the Selectric II was actually in pretty decent shape. The first couple of minutes of the video after the break show not only the minimal repairs needed to get the typewriter back on its feet, but also a whirlwind tour of the remarkably complex mechanisms that turn keypresses into characters on the page. As it turns out, knowing how the mechanical linkages work is the secret behind converting the Selectric into a teletype, entirely within the original enclosure and with as few modifications to the existing mechanism as possible.
Keypresses are mimicked with a mere thirteen solenoids — six for the “latch interposers” that interface with the famous
whiffletree mechanism
that converts binary input to a specific character on the typeball, and six more that control thinks like the cycle bail and control keys. The thirteenth solenoid controls an added bell, because every good teletype needs a bell. For sensing the keypresses — this is to be a duplex terminal, after all — [alnwlsn] pulled
a page from the Soviet Cold War fieldcraft manual
and used opto-interrupters to monitor the positions of the latch interposers as keys are pressed, plus more for the control keys.
The electronics are pretty straightforward — a bunch of MOSFETs to drive the solenoids, plus an AVR microcontroller. The terminal speaks RS-232, as one would expect, and within the limitations of keyboard and character set differences over the 50-odd years since the Selectric was introduced, it works fantastic as a Linux terminal. The back half of the video is loaded with demos, some of which aptly demonstrate why a lot of Unix commands look the way they do, but also some neat hybrid stuff, like a ChatGPT client.
Hats off to [alnwlsn] for tackling a difficult project while maintaining the integrity of the original hardware. | 20 | 12 | [
{
"comment_id": "6665765",
"author": "Antron Argaiv",
"timestamp": "2023-07-25T11:16:55",
"content": "We used to have the “official” version of these – the IBM 2741 terminal – when I was at school. They were always down. Apparently, the mechanism wasn’t up to taking the abuse that college kids whose... | 1,760,372,223.694449 | ||
https://hackaday.com/2023/07/25/grab-your-scopes-screen-from-the-command-line/ | Grab Your ‘Scope’s Screen From The Command Line | Jenny List | [
"computer hacks",
"Software Hacks"
] | [
"computer controlled",
"oscilloscope",
"serial port"
] | Many of us have oscilloscopes and other instruments with built-in digital interfaces, but how many of us use them? [Andrej Radović] has a Tektronix TDS2022 which can print its screen to any of its various interfaces,
and he set about automating the process of acquisition with a Bash script
.
The easiest interface to use was the trusty serial port — hardly the fastest but definitely the best supported. But how does one retrieve an image fired down a serial port? Most of the post is devoted to spotting file headers in a Bash script monitoring the serial port, and streaming the result to a local file. There’s a discussion of the various formats supported by the Tek, with an ancient PCX bitmap format being chosen over Postscript for speed. The result is a decent quality screen grab, making the ‘scope that little bit more useful and perhaps extending its life.
Perhaps your instrument isn’t a TEK, but the chances are you can still make it bend to your will from a PC.
Try it, with the magic of VISA
. | 9 | 7 | [
{
"comment_id": "6665772",
"author": "ardencaple",
"timestamp": "2023-07-25T11:58:20",
"content": "If you have a VISA or LXI based scope, then the chances are that the excellent LXI Tools (https://github.com/lxi-tools/lxi-tools) already have you covered.I use the CLI tools a lot to debug VISA instru... | 1,760,372,223.637964 | ||
https://hackaday.com/2023/07/24/restoring-the-cheapest-trs-80-at-the-swap-meet/ | Restoring The Cheapest TRS-80 At The Swap Meet | Tom Nardi | [
"Repair Hacks",
"Retrocomputing"
] | [
"swap meet",
"trs-80",
"Vintage Computer Federation"
] | We don’t know if you’ve looked into it recently, but the prices for vintage computers are through the roof right now. These classic machines are going through something of a renaissance at the moment, with even relatively commonplace computers commanding several hundred dollars if they’re in good condition. For those looking to start a collection without breaking the bank, you may need to accept some specimens that have seen better days.
That’s the situation [Vlado Vince] recently found himself in — he wanted to get his hands on a TRS-80 Model I, but wasn’t willing to spend eBay prices. So he waited until the Vintage Computer Federation’s swap meet in June and was able to snag a “fully functional” example for $95. Unfortunately the seller must have been using some form of that phrase which we were previously unaware of, as it took a
considerable amount of work to get it back online
.
Getting the machine home [Vlado] was only able to get a very faint video signal out of it, and even then, it had no horizontal sync. Upon opening it up he found considerable corrosion, in addition to signs of previous repairs and bodges. Doing some research he found that one of the corroded ICs was indeed part of the video circuit, so it was carefully extracted and replaced with a socket to take the new chip. He also removed a hacked together memory upgrade that was likely installed in the 1980s, figuring it being there would only complicate the repair.
This still didn’t give him a useful video signal, so he started a closer examination of the board. It turns out there were subtle modifications all over the place, with traces cut and whole components removed for reasons unknown. With the board schematics in hand, [Vlado] started undoing the changes and returning the circuits to their stock arrangement. He also repaired the badly damaged keyboard connector, as the previous owner’s bodge wires didn’t seem to be up to the task. These efforts paid off as he was finally able to get the machine to boot, though the video was erratic.
At a loss for the continuing display problems, [Vlado] started replacing components in the video circuit hoping to luck out. He swapped out the electrolytic capacitors and variable resistors, and even tried replacing components in the power supply, but the issue remained.
He eventually got the oscilloscope out and started poking around the board, looking for anything that seemed out of the ordinary. He found that the signal coming from that very first video IC he replaced was out of spec; as it turned out he had replaced the original 74C04 with a 74
LS
04, but what he actually needed was a 74
HC
04. With the correct chip in place the image stabilized, and the machine was finally in the “fully functional” condition that he was promised in the first place.
Ultimately [Vlado] had set out to get his hands on a TRS-80 so he could get a better understanding of how it inspired Voja Antonić’s design of the Galaksija. Considering the amount of effort he put into this repair, we’re willing to bet he got all the insight he was looking for. Especially when combined with the experience of
building his own Galaksija replica
.
Incidentally, if you take a look at our
video from the VCF swap meet
, you can actually see the TRS-80 [Vlado] ended up buying at around the 0:50 mark. If you happen to have grabbed one of the other computers covered in that video and got it back up and running,
we’d love to hear about it
. | 20 | 12 | [
{
"comment_id": "6665714",
"author": "Ostracus",
"timestamp": "2023-07-25T05:40:48",
"content": "Nostalgia is a powerful thing.https://www.youtube.com/@RecollectionRoad",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665747",
"author": "TG",
... | 1,760,372,223.802212 | ||
https://hackaday.com/2023/07/24/doom-on-iphone-os-on-android/ | DOOMOn IPhone OS, On Android | Elliot Williams | [
"Android Hacks",
"Software Hacks"
] | [
"android",
"doom",
"emulation",
"ios"
] | So you want to play some games from the early days of 32-bit iPhone OS that no longer run on recent OS versions? [Hikari-no-yume] wrote a sweet high-level emulator, touchHLE, to do so on modern iOS phones. But maybe you don’t have an iPhone? [Ciciplusplus] has your back.
He ported the iPhone OS emulator, written in Rust,
to Android
, and then
ported a version of
DOOM
that runs on iPhone OS to go with it
.
[Ciciplusplus] also made a video (embedded below) where he documented the trials and tribulations of porting Rust code to the Android platform – an intensely Java environment. It doesn’t sound like it was at all trivial. Of course, this couldn’t have been accomplished without [Hikari-no-yume]’s
original work on touchHLE
, which was made essentially to fulfill [Hikari-no-yume]’s long-time obsession with the game
Super Monkey Ball
.
So for now, touchHLE can boast the ability to run a few old 32-bit games on Android and desktop operating systems. What other games from the first years of gaming on smart phones (and iPods) do you need to see ported? Get involved in the project if you’ve got an itch you need scratched. | 7 | 6 | [
{
"comment_id": "6665697",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-25T02:37:26",
"content": "Interesting video!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6665708",
"author": "Misterlaneous",
"timestamp": "2023-07-25T... | 1,760,372,223.734383 | ||
https://hackaday.com/2023/07/24/2023-hackaday-prize-a-smart-powermeter-that-you-actually-want/ | 2023 Hackaday Prize: A Smart Powermeter That You Actually Want | Elliot Williams | [
"classic hacks",
"contests"
] | [
"2023 Hackaday Prize",
"current sensing",
"esphome",
"green hacks",
"home automation",
"power management"
] | [Jon] wanted to
keep track of his home power use
, but didn’t want to have to push his data up to some cloud service that’s just going to leave him high and dry in the future. So he went completely DIY.
This simple and sweet build is now in its third revision, and the refinements show. A first prototype was nothing more than an ESP32 with a screen and some current transformer (CT) sensors to read the current flowing in the wires in his breaker box. The next version added a PCB and a color screen, and the most recent version swapped up to eInk and a nice local power supply, all sized to fit a nice clear power box.
What’s really cute about this design is the use of standard
phono
headphone jacks to plug the CT sensors into, and the overall sweet combination of a local display and interactivity with [Jon]’s ESPHome-based home automation setup. This design isn’t super complicated, but it doesn’t need to be. It has one job, and it does it nicely. What more do you want?
If you’re interested in getting into ESPHome and/or home automation, check out
this great ESPHome resource
. It’s probably a lot easier than you think, and you can build your system out one module at a time. If you’re like us, once you get started, you’ll find it hard to stop until everything falls under your watchful eyes, if not your control. | 19 | 9 | [
{
"comment_id": "6665667",
"author": "ian 42",
"timestamp": "2023-07-24T23:04:10",
"content": "with the original post a few days ago – with comments – herehttps://hackaday.com/2023/07/20/smart-powermeter-uses-e-paper-display/Must be a slow news day at HaD",
"parent_id": null,
"depth": 1,
... | 1,760,372,223.956749 | ||
https://hackaday.com/2023/07/24/nail-meet-kicad/ | Nail, Meet KiCad | Matthew Carlson | [
"PCB Hacks"
] | [
"KiCAD",
"pcb",
"repair"
] | You know the old saying. When all you have open is KiCad, everything looks like a PCB. That was certainly true for [Evan], who needed to replace a small part recently and
turned to PCBs to get the job done
.
The part in question was a sheered apart detent cam from a retractable cord reel. Glue and epoxy might have worked, and [Evan] was worried about how a 3D printed PLA part would have held up. The part is an extruded 2D shape, making PCBs a non-traditional but viable choice. Using the
old scanner trick
, he traced the outline in KiCad 7 (which adds image references). Then with the five boards stacked up, solid core wire, solder, and a propane torch worth of heat fused it. Ultimately, this machine’s tolerances are generous, so it worked wonderfully.
Was it the “right” tool for the job? Right or wrong, it is hard to argue that in terms of durability and ease per dollar, this doesn’t come out on top. PCB files are on
GitHub
if you have a 5020TF-4c retractable cord reel that needs a new cam. PCBs have a fun way of adopting different use cases
like enclosures
, but perhaps the idea of PCBs as a mechanical part could be applied elsewhere. | 25 | 10 | [
{
"comment_id": "6665622",
"author": "Jeff",
"timestamp": "2023-07-24T20:25:12",
"content": "Good job getting the job done. I would have just stuck with 3D printed PLA or PETG, though. If a straight printed part didn’t hold up, I would try printing it at 100% infill and then remelt it in packed salt... | 1,760,372,224.020373 | ||
https://hackaday.com/2023/07/24/text-to-speech-model-can-do-music-background-noises-and-sound-effects/ | Text-to-Speech Model Can Do Music, Background Noises, And Sound Effects | Donald Papp | [
"Artificial Intelligence",
"Software Hacks"
] | [
"ai",
"generative",
"LLM",
"text to speech",
"tts"
] | Bark
is a universal text-to-audio model that can not only create realistic speech, it can incorporate music, background noises, and sound effects. It can even include non-speech sounds like laughter, sighs, throat clearings, and similar elements. But despite the fact that it can deliver such complex results, it’s important to understand some of the peculiarities.
The model takes a prompt and generates the resulting sound from scratch. Results might sometimes be unexpected.
Bark is not a conventional text-to-speech program, and how it works has a lot more in common with
large language model
AI chatbots. This means that results can deviate from expectations, and outputs aren’t necessarily going to be studio-quality speech. As the project’s README points out, “(generated outputs can) be anything from perfect speech to multiple people arguing at a baseball game recorded with bad microphones.” That being said, there is some support for
voice presets
as a way to help guide the model with some consistency.
Bark was designed by a company called Suno for research purposes and is available under the MIT License. It can be installed and run locally, and has some demos available as well as
an online implementation
.
The ability to install and run Bark locally is promising territory for incorporating it into projects. And should you be more interested in speech-to-text instead, don’t forget about this
plain C/C++ implementaion of AI-powered speech recognition
. | 8 | 5 | [
{
"comment_id": "6665599",
"author": "Robert Chadwick",
"timestamp": "2023-07-24T18:55:44",
"content": "Perfect for robotic telemarketers that sound more and more like real people.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665609",
"author": "T... | 1,760,372,224.073504 | ||
https://hackaday.com/2023/07/24/retro-gadgets-the-real-desktop-computer/ | Retro Gadgets: The Real Desktop Computer | Al Williams | [
"Hackaday Columns",
"Retrocomputing",
"Slider"
] | [
"8080",
"noval",
"retrocomputing"
] | People argue about the first use of the computer desktop metaphor. Apple claims it. Xerox probably started it. Yet, when I think of computer desktops, I think of the NOVAL 760. Not a household name, to be sure, but a big ad spread in a June 1977 Byte magazine was proud to introduce it. At $2995, we doubt many were sold, but the selling point was… well… it was built into a “handsome wood desk, designed to compliment any decor.” The desk folded down when you were not using the computer, and the keyboard recessed into a drawer.
The computer itself was no slouch for 1977, but nothing you couldn’t find elsewhere. An 8080, speed unspecified, had 16 kB of RAM and 3 kB of PROM. There was also a display with a few kB of memory hanging around, too. And just in case you were worried, the bottom of the page entitled “The Ultimate in Home Computers” reads, “The NOVAL 760 COMPUTER. A fully-assembled, fully-tested personal computer … not a kit!” Of course, for us, that’s not really a selling point. If you wonder why the computer was memory limited, this is the time that Extensys bragged in an ad: 64 kB for $1495! If you ordered one, you could have it in 15 to 30 days, too!
There were options for more memory, and it wasn’t clear how many of the I/O devices in the ad were actually included in the advertised price. Some of the devices seemed very specialized, so we are guessing the basic system didn’t include some of them.
Input/Output
The Noval looked good, but upgrades would be tough!
According to the ad, you did get a lot of I/O devices, apparently, and they seemed to understand that software was the key to selling computers, although there wasn’t much of it about yet in 1976. The computer had a 12-inch monochrome monitor with 28 lines of 32 characters. If you used an external color monitor, the display could handle it. Don’t get too excited, though. An EPROM held four “schemes” of eight pairs of image and background colors. You could select any of the four schemes you wanted, but if you wanted anything else, you needed to burn an EPROM.
For mass storage, the computer had a “professional” mag tape system: a PhiDeck that could do about 2,500 bits per second. There was an audio tone generator that could have been anything from a buzzer to a crude sound card. A paper tape reader and, apparently, an EPROM burner — maybe for the color schemes, but we doubt they included an eraser. There was also a film reader, but it isn’t clear from the ad if that could scan film images (doubtful) or if it was some sort of read-only mass storage that they planned to use for distributing software.
Diskless
Notably lacking was a disk drive. They don’t mention a printer in the ad, but one was visible in the pictures — we guess it might have been an add-on and not included in the $3,000 price tag. The standard printer was an LRC printer that printed a raster image generated by the computer itself and matched the 32-character width of the monitor. Forward-looking but slow on a 1977-era 8080. Even the fact that the I/O drivers were in a ROM (what we would call a BIOS) and didn’t require fixed addresses to call was a selling point in 1977.
Games
Games were better in color, but that needed an upgraded monitor. The interactive assembler would have been fun, but not super friendly for a home computer
Interestingly, the company couldn’t decide if it was a high-end business workstation or a game system. It had “dual hand-held keyboards for competitive game action, for the first time on a home computer,” according to the ad. They mention TELEMATH, a game where the computer presents math problems to two players, scoring for the first player to answer correctly.
They had some form of games from
Gremlin Industries
, apparently “the leader in commercial computer videographic and wall games” in 1977. We know them better as “a company bought by Sega.” Apparently, Gremlin was a “sister company,” although we don’t know the history there. We doubt Sega acquired it along with Gremlin since there is little information about the company after a big splash in 1977.
Assembly Required After All
The other software they seemed proud of was the editor assembler which was interactive and caught errors immediately. Back then, no one was sure what was happening with the computer industry. Maybe people were going to all learn assembly language. Maybe PCs would be sold in furniture stores. Maybe.
We wonder how many of these were ever out in the world.
At least one still lives at the Computer History Museum
. We don’t know exactly what happened to the company or if someone still has one of these in their spare bedroom collecting dust.
While computers did wind up in every home, it wasn’t like we imagined in 1977. At least they were closer
than we were in 1962
. The Noval was a big step up from
a desktop computer of 1965
. | 27 | 15 | [
{
"comment_id": "6665585",
"author": "hartl",
"timestamp": "2023-07-24T17:50:39",
"content": "This is a silly construction, the desk cannot be closed if there’s anything connected to the expansion ports on the left.btw, better pictures can be found here:https://archive.org/details/byte-magazine-1977... | 1,760,372,224.295587 | ||
https://hackaday.com/2023/07/24/circuitpython-happenings-hack-chat-with-adafruit/ | CircuitPython Happenings Hack Chat With Adafruit | Dan Maloney | [
"Hackaday Columns",
"Slider"
] | [
"Hack Chat"
] | Join us on Wednesday, July 26 at noon Pacific for the
CircuitPython Happenings Hack Chat
with The folks from Adafruit!
It’s always a party when the good folks from Adafruit stop by the Hack Chat, and we expect no less than that this time around. It’s hard to predict where the conversation will go when [LadyAda], [pt], and [Scott] roll in, but we strongly suspect it’ll center on what’s new in the world of CircuitPython.
We’ve heard that they’ve got some cool stuff going on with CircuitPython on the RP2040, which just might lead to a Python-based fix for the current Bus Pirate supply chain problem. It’ll be a swashbucklingly good time, so make sure you stop by.
Our Hack Chats are live community events in the
Hackaday.io Hack Chat group messaging
. This week we’ll be sitting down on Wednesday, July 26 at 12:00 PM Pacific time. If time zones have you tied up, we have a
handy time zone converter
. | 29 | 14 | [
{
"comment_id": "6665632",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-24T20:53:29",
"content": "You mean pink hair?",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6665642",
"author": "Andrew",
"timestamp": "2023-07-24T21:23:... | 1,760,372,224.227344 | ||
https://hackaday.com/2023/07/24/a-vintage-transistor-radio-gets-a-repair/ | A Vintage Transistor Radio Gets A Repair | Jenny List | [
"Radio Hacks"
] | [
"am radio",
"radio repair",
"transistor radio"
] | Here in 2023 the field of electronics covers a breathtaking variety of devices and applications, but if we were to go back in time far enough we’d enter an age in which computers were few and far between, and any automated control systems would have been electromechanical at best. Back in the 1950s the semiconductor industry was in relative infancy, and at the consumer end electronics were largely synonymous with radio.
[Shango066] brings us a transistor radio from that era
, a Jewel TR1 from about 1958, that despite its four-transistor simplicity to our eyes would have been a rare and expensive device when new.
As you’d expect, a transistor radio heading toward its 70th birthday requires a little care to return to its former glory, and while this one is very quiet it does at least work after a fashion. The video below the break is a long one that you might wish to watch at double speed, but it takes us through the now-rare skill of fault-finding and aligning an AM radio receiver. First up are a set of very tired electrolytic capacitors whose replacement restores the volume, and then it’s clear from the lack of stations that the set has a problem at the RF end. We’re treated to the full process of aligning a superhet receiver through the relatively forgiving low-frequency medium of a medium-wave radio. Along the way, he damages one of the IF transformers and has to replace it with a modern equivalent, which we would have concealed under the can from the original.
The video may be long, but it’s worth a look for the vintage parts if not for the quality of radio stations on the air today in California. For many readers,
AM broadcast is becoming a thing of the past
, so we’re not sure we’ll see this very often. | 19 | 8 | [
{
"comment_id": "6665565",
"author": "VCSMaster",
"timestamp": "2023-07-24T16:42:26",
"content": "I love Shango’s videos, especially the TV resurrections. I highly recommend watching a few, if you have any interest in real diagnosis and repair.",
"parent_id": null,
"depth": 1,
"replies":... | 1,760,372,224.162663 | ||
https://hackaday.com/2023/07/24/displayport-tapping-the-altmode/ | DisplayPort: Tapping The Altmode | Arya Voronova | [
"Engineering",
"Featured",
"News",
"Skills",
"Slider"
] | [
"displayport",
"reverse engineering",
"USB C"
] | Really, the most modern implementation of DisplayPort is the USB-C DisplayPort altmode, synonymous with “video over USB-C”, and we’d miss out if I were to skip it. Incidentally, our
last
two
articles about talking USB-PD have given a few people a cool new toy to play with – people have commented on the articles, reached out to me for debugging help, and I’ve even seen people build the FUSB302B into their projects! Hot on the heels of that achievement, let’s reach further and conquer one more USB-C feature – one that isn’t yet openly available for us to hack on, even though it deserves to be.
For our long-time readers, it’s no surprise to see mundane capabilities denied to hackers. By now, we all know that many laptops and phones let you get a DisplayPort connection out of a USB-C port. Given that the USB-C specifications are openly available, and we’ve previously implemented a PD sink using those specifications, you’d expect that we could do DisplayPort with the same ease. Yet, the DisplayPort altmode specification is behind a VESA membership paywall, with a hefty pricetag – a practice of theirs that
has been widely criticized,
counter to their purpose as a standards organization and
having resulted in some of their standards failing.
Not to worry, however – we can easily find an assortment of PDFs giving a high-level overview and some details of the DisplayPort altmode, and
here’s my favorite!
I also have a device running MicroPython with a FUSB302 chip connected, and a few DisplayPort altmode devices of mine that I can disassemble. This, turns out, is more than enough for us to reverse-engineer our way into an open-source DisplayPort altmode library!
DisplayPort Over USB-C Basics
The USB-C port has four high-speed pairs, and one auxiliary lower-speed pair (SBU). This beautifully maps onto the DisplayPort requirements, with up to four high-speed data transfer pairs, and one AUX configuration channel. One small quirk – there’s no pin for the HPD signal; instead, its status is forwarded inside of DisplayPort altmode messages over the PD channel. As a result, you can plug your device into a DisplayPort-capable USB-C, write a few magic words over PD, and get a DisplayPort signal on the USB-C TX/RX pins! No need to delve into DisplayPort internals whatsoever; the most you will need is to forward HPD as a PD message, and if your device uses a USB-C socket, have a cheap mux flip the signals according to the way your USB-C cable is plugged in.
Captive cable $10 dock with a DisplayPort to HDMI chip, a USB3 port, and a charging input. Two ICs total, including HDMI – no mux needed.
Aside from DisplayPort, you also get USB 2.0 on the good old USB2 pins – perfect for plugging in a keyboard and mouse alongside your monitor. That’s not all you can extract, however – if you’re content with two-lane DisplayPort, you can ask the upstream device to provide you two lanes of DisplayPort on one pair of pins, and a USB3 port on another! This is how the majority of cheap USB-C docks work – they get two lanes of DisplayPort used for VGA or HDMI, USB3 for a high-speed port or a few peripherals, and USB2 for a whole bunch of other stuff, handling your power input on the side.
Judging from
the PDF we have from ST,
there are seven kinds of PD messages that we need to answer if we want to build a DisplayPort device – the diagram on page 13 shows them all. In the
“All About USB-C: Replying Low-Level PD” article,
we’ve learned two types of messages –
Source_Capabilities
, which a USB-C PSU power profile advertisement, and the
Request
message, which we’ve crafted to get one of those power profiles and get a higher voltage out of a USB-C port. From two to seven – this is well within our reach!
What do we need to do to reverse-engineer it, at the bare minimum? I’d say, the PDF seems to contain more than enough info on its own – the communication flow, different command codes and contents are described there. However, it will be way more comfortable if we are to have packet captures to reference!
Packets In Captivity
USB-C communications sniffing is an underexplored field – especially if high-speed signals are involved. For those, you need an interposer board that preserves signal integrity while letting you tap into the CC pins, and those aren’t quite dime a dozen. When it comes to commercial tools for USB-C sniffing, I feel like most of those are priced accounting for the fact that many people don’t understand USB-C. However, there’s certainly ways around it – in the comment section of the first PD talking article, [WF] has pointed us towards
a way to sniff arbitrary USB-C packets with a logic analyzer and a simple extra circuit,
with help of sigrok and Pulseview! We are making a device that can talk DisplayPort altmode, not just sniff it, but if you’d like to tap into a device of yours as you follow alongside this article, this ought to be enough.
That said, there might be an even simpler solution, if you’ve been following along, you might just own a FUSB302B, which is a USB-C PHY IC. Since the “Replying PD” article got published, I’ve been slowly building upon the capabilities of
my personal MicroPython USB-PD “stack”
– assortment of PD functions and code, rather, but I’ll call it a stack until a more fitting name is found. First, I’ve added packet listening capability – switching the FUSB302 into receive-only mode, reading its input FIFO as quickly as possible, and parsing the data on the fly. I’ve also added packet information parsing, so that you can see USB-C communications in the serial console, without having to read them first.
There’s a caveat, of course – I can’t easily do passthrough capture of USB-C packets, since I didn’t want to design an open-source passthrough board with CC tapping capability, and these boards aren’t quite available. That said, someone should do that – it’s a bit of a shame that the
USB-C-Thru device
never got funded! Instead, I’ve started by disassembling captive cable devices I own, then tapping into the CC pin – since, with a captive cable device, there’s only one CC pin possible. This means I don’t need to autodetect rotation, which is nice because, given the time that my MicroPython code could take to figure out the rotation, the USB-PD conversation might be over by that point already. So, my board’s CC1 wired to one of my USB dock’s CC pin, CC1 hardcoded to be the listening pin – what else?
You’ll want to disable the FUSB pullups – they’re going to be counterproductive here, as we’re tapping into an existing pullup/pulldown arrangement, and introducing one more pulldown will result in VBUS getting switched off. You’ll also want to disable GoodCRC responses – FUSB302 does them automatically, which helps when we use it as a sink, but here they’ll conflict with GoodCRC responses from both sides of the USB-C conversation; disabling the transmitter is even better. I’ve also enabled SOP’/” packet reception – these packets are used for emarkers, and while we don’t normally need to receive them, being able to sniff them now is good.
Now, we’re ready! Mind you, USB-C communications happen seriously fast. My MicroPython code isn’t speedy either – I use MicroPython because I chose hackability over execution speed. However, as a consequence, I can’t quite parse packets as they arrive – I will miss out on parts of the USB-C conversation if I do that, as, remember, even print statements take a bit of time. Instead, I read the input FIFO contents as quickly as possible, store packets in RAM, and parse them afterwards. On the upside, having packet captures in RAM also means that I end up with PD conversation recordings I can easily store and replay later, and you get a few of these captures as well!
There’s downsides to using this method of packet capture, of course – I might still not be able to capture communications that happen too fast, I only capture packets with valid CRC and will miss out on any garbled packets, and I don’t have timestamps for the packets received; using a logic analyzer would negate all of these. However, for our DisplayPort RE purposes, it’s more than good enough, and any parsing code I write, will be super helpful when building a library. CC pin wired up, code running and ready, let’s go!
This Is VDM Turf
Here you can see a power profile negotiation happening –
Source_Capabilities
,
Request
,
Accept
and
PS_RDY
, things we’ve already done before. These are required if you are to talk PD for any purpose, so it’s not much of a surprise. However, there’s also a whole bunch of
Vendor_Defined
messages, and these might put you on edge. Do not be afraid, though – be grateful to the USB-C standard instead, because, with the way it tells vendors to implement vendor-specific communications, these messages are better documented than you’d expect!
Full communications from my sniffer code, partially parsed
VDMs, or Vendor-Defined Messages, are responsible for any altmode summoning that goes beyond the regular “USB3, USB2 and PD” things you can get – you can use VDMs for anything that falls outside the standard, from custom altmodes to firmware updates. You can have them unstructured or structured – unstructured messages are basically freeform, while structured messages are kind of a template for a typical conversation that a vendor might actually want to implement. DisplayPort negotiation uses structured messages, and out of the seven commands involved in setting up the DisplayPort altmode, five of them are commands already defined in the USB-C standard! As for the two remaining ones, the PDF we have, very helpfully mentions their codes on page 8, and describes them in more detail on page 10-12.
These commands are a bit special – it’s not just that a GoodCRC response is required, the FUSB302B will take care of it for us, anyway. It’s also that every command can be either a request or a response, and either of the directions can carry extra data, depending on the specific command being used! Thankfully, all of this optional data is described in the PDF – which has been proving more and more helpful the deeper we go.
All in all, we won’t need to reverse-engineer that much, specifically – the main problem, in my assessment, would be the bitfields. Also, since we don’t have the full specification, we might make a crucial mistake or two – for instance, we don’t know how quickly we must answer these commands, or the specifics of handling the DisplayPort HPD signal properly. We can figure these out however, and I’ve got quite a variety of USB-C DisplayPort devices to get packet captures from!
Replay Works – Proper Implementation Time
Well, now we have DisplayPort conversation commands, captured from a real-life device – if we wanted to make a DisplayPort sink right now, we can just replay them, only adjusting small things like message ID! In fact,
here’s a piece of code which does just that
– sends back the commands that we captured, and I’ve successfully made it summon the DisplayPort altmode on my own laptop! Now, I didn’t verify the high-speed DisplayPort output, but I got voltage on SBU pins, which means that the AUX diffpair has been wired up to those – something that only happens after the DisplayPort altmode has been successfully summoned.
The fundamental part of the replay code is the request-response loop, which does rely on our parsing code to answer incoming messages. This is great for us – we’ll need exactly this kind of loop once we can actually construct our own replies, just that we’ll need a bit more sophisticated one. Until then, this is enough to get me by when it comes to a personal project of mine.
The next tasks are to actually make sense of these commands and implement a meaningful DisplayPort library! We’ll go through the seven commands required, explain each one of them, parse the ones we’ll receive, and implement the ones we’ll have to send back. Afterwards, we’ll tie them all together into the already existing loop, figure out USB-C high-speed lane rotation handling, and we’ll be ready to build open-source DisplayPort handling devices for any capable USB-C port in sight. After all, these days, even a PinePhone can do DisplayPort! | 11 | 7 | [
{
"comment_id": "6665554",
"author": "Ostracus",
"timestamp": "2023-07-24T15:56:52",
"content": "I imagine funding of their operation is why there’s a hefty price-tag.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665571",
"author": "Arya Voronova"... | 1,760,372,224.444421 | ||
https://hackaday.com/2023/07/24/hp1973-project-highlights-workings-of-hp-45-calculator/ | HP1973 Project Highlights Workings Of HP-45 Calculator | Chris Lott | [
"Retrocomputing"
] | [
"calculator",
"debugger",
"emulator",
"hp-35",
"HP-45",
"rom"
] | [Sarah K Marr] dabbles in retrocomputing and has a fascination with the Hewlett Packard HP-45 calculator, the second calculator in HP’s series introduced in 1973. Over a year ago, she wrote an HP-45 emulator for use on a terminal, dubbed HP45TERM. Not content with success, she upped the challenge and decided to build an even better emulator with a full-featured GUI written in Python. Oh, and she made it multi-platform as well. The result is the
HP1973 project
.
[Sarah] thought it would take just a few days, but it grew into a much bigger project, as often happens. We’re glad it did because the results are fantastic. The emulator gives you access not only to the calculator itself but can see everything under the hood. The emulator provides full ROM visibility, hardware registers, and standard debugging operations like single stepping. ROM images are available for the HP-45, the HP-35, and the HP-80. The GUI display is configurable, and there’s a plethora of help and information explaining the calculator’s internals. Pre-built binaries are available for MacOS, Windows, and Python source code (3.10.10+) for all operating systems (you’ll need to `pip install numpy` first). The emulation is faithful to the original calculator, and even the hidden timer function can be accessed.
Check this out if you’re into retro calculators. Our own Al Williams wrote about
the history of the HP-35
back in 2018 if you want to learn more. Thanks to [J Peterson] for sending in the tip. | 3 | 1 | [
{
"comment_id": "6665516",
"author": "Ostracus",
"timestamp": "2023-07-24T13:16:52",
"content": "Any decapping of the Saturn CPU?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665535",
"author": "jawnhenry",
"timestamp": "2023-07-24T14:05:3... | 1,760,372,224.484255 | ||
https://hackaday.com/2023/07/24/weather-in-wartime-the-importance-of-british-meteorology-in-wwii/ | Weather In Wartime: The Importance Of British Meteorology In WWII | Donald Papp | [
"History"
] | [
"meteorology",
"RAF",
"retrotechtactular",
"weather",
"wwii"
] | Weather can have a significant impact on transport and operations of all kinds, especially those at sea or in the air. This makes it a deeply important field of study, particularly in wartime. If you’re at all curious about how this kind of information was gathered and handled in the days before satellites and computer models,
this write-up on WWII meteorology
is sure to pique your interest.
Weather conditions were valuable data, and weather
forecasts
even more so. Both required data, which relied on human operators for instruments to be read and their readings transmitted.
The main method of learning weather conditions over the oceans is to persuade merchant ships to report their observations regularly. This is true even today, but these days we also have the benefit of things like satellite technology. Back in the mid-1900s there was no such thing, and the outbreak of WWII (including the classification of weather data as secret information due to its value) meant that new solutions were needed.
The aircraft of the Royal Air Force (RAF) were particularly in need of accurate data, and there was little to no understanding of the upper atmosphere at the time. Eventually, aircraft flew regular 10-hour sorties, logging detailed readings that served to provide data about weather conditions across the Atlantic. Readings were logged, encoded with
one-time pad (OTP) encryption
, then radioed back to base where charts would be created and updated every few hours.
The value of accurate data and precise understanding of conditions and how they could change was grimly illustrated in a disaster called the
Night of the Big Wind
(March 24-25, 1944). Forecasts predicted winds no stronger than 45 mph, but Allied bombers sent to Berlin were torn apart when they encountered winds in excess of 120 mph, leading to the loss of 72 aircraft.
The types of data recorded to monitor and model weather are nearly identical to those in modern weather stations. The main difference is that instruments used to be read and monitored by human beings, whereas today we can rely more on
electronic readings and transmission that need no human intervention
. | 10 | 4 | [
{
"comment_id": "6665477",
"author": "Jan",
"timestamp": "2023-07-24T10:53:39",
"content": "I’m confused as some sources report that “the night of the big wind” happened on 6 January 1839https://en.wikipedia.org/wiki/Night_of_the_Big_Wind",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,224.532755 | ||
https://hackaday.com/2023/07/23/superconducting-tape-leads-to-a-smaller-tokamak/ | Superconducting Tape Leads To A Smaller Tokamak | Jenny List | [
"Science"
] | [
"nuclear fusion",
"superconductor",
"tokamak"
] | Attempts to make a viable nuclear fusion reactor have on the whole been the domain of megabucks projects supported by countries or groups of countries, such as the European JET or newer ITER projects. This is not to say that smaller efforts aren’t capable of making their own advances, operations in both
the USA
and
the UK
are working on new reactors that use a novel superconducting tape to achieve a much smaller device.
The reactors in the works from both Oxfordshire-based Tokamak Energy and Massachusetts-based Commonwealth Fusion Systems, or CFS, are tokamaks, a Russian acronym describing a toroidal chamber in which a ring of high-temperature plasma is contained within a spiral magnetic field. Reactors such as JET or ITER are also tokamaks, and among the many challenges facing a tokamak designer is the stable creation and maintenance of that field. In this, the new tokamaks have an ace up their sleeve, in the form of a high-temperature superconducting tape from which those super-powerful magnets can be constructed. This makes the magnets easier to make, cheaper to maintain at their required temperature, and smaller than the low-temperature superconductors found in previous designs.
The world of nuclear fusion is a particularly exciting one to follow in these times of climate crisis, with competing approaches
from laser-based devices
racing with
the tokamak projects
to produce the research which will eventually lead to safer carbon-free power. If the CFS or Tokamak Energy reactors lead eventually to a fusion power station on the edge of our cities then it may just be some of the most important work we’ve ever reported. | 80 | 11 | [
{
"comment_id": "6665396",
"author": "tomás zerolo",
"timestamp": "2023-07-24T05:50:20",
"content": "Fusion won’t “solve” the climate crisis. Not in the naive way media like to depict, at least.Don’t get me wrong — I like cheap energy as the next gal or guy. But if we don’t get our act together *rig... | 1,760,372,224.661453 | ||
https://hackaday.com/2023/07/23/steel-for-your-fighting-robot/ | Steel For Your Fighting Robot | Jenny List | [
"Robots Hacks"
] | [
"battle bot",
"metallurgy",
"steel"
] | The job of processing video after a large event must be a thankless one for whichever volunteer upon whose shoulders it falls, and thus it’s not unusual for talks at larger events to end up online much later than the event itself. Electromagnetic Field 2022 was last year, but they have continued to drop new videos. Among the latest batch is one from [Jennifer Herchenroeder],
in which she discusses the steel used in her team’s BattleBot, Hijinx
(Edit: her EMF talk was cut short due to time pressures, so she re-recorded it in full after the event and we’ve replaced the link. The EMF video meanwhile is
here
). The result is a fascinating introduction to the metallurgy of iron and steel, and is well worth a watch.
To fully understand the selection of armor steel it’s necessary to start from first principles with iron, to look at its various allotropes, and understand something of how those allotropes form and mix in the steel making and metalworking processes. We’re treated to a full description of the various tempering and hardening processes, before a panel-by-panel rundown of the various steels used by Hijinx.
For a Hackaday writer
with a past in robot combat
it’s fascinating to see how the design of robots has evolved over the decades since the British Robot Wars, and it’s particularly nice to see the current generation as part of our community. However, if you’ve tempted yourself, bear in mind that
it’s not all plain sailing
. | 8 | 3 | [
{
"comment_id": "6665371",
"author": "Kim C",
"timestamp": "2023-07-24T02:37:39",
"content": "It seems Jen uploaded a higher quality cut of the video to her channel too.https://www.youtube.com/watch?v=n3kWQf4E1hU",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "... | 1,760,372,224.705972 | ||
https://hackaday.com/2023/07/23/hackaday-links-july-23-2023/ | Hackaday Links: July 23, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"Australia",
"edge",
"flint",
"fusion",
"hackaday links",
"IBM PCjr",
"knapped",
"meteor",
"meteoroid",
"obsidian",
"Oppenheimer",
"sharpness",
"space junk",
"thermonuclear",
"uptime",
"V20"
] | It may be midwinter in Perth, but people still go to the beach there, which led to the surprising discovery earlier this week of what appears to be
a large hunk of space debris
. Local authorities quickly responded to reports of a barnacle-encrusted 2.5-m by 3-m tank-like object on the beach. The object, which has clearly seen better days, was described as being made of metal and a “wood-like material,” which on casual inspection is clearly a composite material like Kevlar fibers in some sort of resin. Local fire officials teamed up with forensic chemists to analyze the object for contamination; finding none, West Australia police cordoned off the device to keep the curious at bay. In an apparently acute case of not knowing how the Internet works, they also “urge[d] everyone to refrain from drawing conclusions” online, which of course sent the virtual sleuths into overdrive.
An r/whatisthisthing thread
makes a good case for it being part of the remains of the third stage of an Indian Polar Satellite Launch Vehicle (PSLV); reentry of these boosters is generally targeted at the East Indian Ocean for safe disposal, but wind and weather seem to have brought this artifact back from the depths.
Also in possible space junk news, a woman in France joined a very select club by
being struck with apparent meteor fragments
during a sunrise coffee break. The woman describes the encounter, which has about a one in 20,000,000,000,000 chance of occurring, as a rebound from a meteor hitting a nearby roof. The shrapnel hit her in the ribs, whereupon she has the admirable presence of mind to go collect as much of the projectile’s remains as possible. Thinking it to be a piece of cement at first, she took it to a friend in the roofing trade for an opinion. The roofer realized it was something else entirely, so the woman took it to a geologist who identified it as an iron/silicon meteor. But not so fast — others have taken a look at
photos of the object
and concluded that
it couldn’t possibly be a meteor
. We’ve got to admit that the doubters seem to have a point, especially since it has always been our impression that meteors are incredibly dense, and seem more like something that would punch a hole through a roof rather than breaking into pieces while landing upon it.
In the world of high-availability servers, 2,700 hours of uptime might not sound like much. But when
your web server is a nearly 40-year-old IBM-PCjr
that has been running continuously since March 2023, it’s something very much worth celebrating. The beige box — complete with a period-correct embossed tape label — contains a few things that wouldn’t have been seen in the 1980s, like an IDE adapter and a 240-GB SATA SSD and a whopping 768-kB of RAM, which would have cost a small fortune back then. But the motherboard still sports the 4.77-MHz V20 CPU, and the OS is PC-DOS 5.02 — the BIOS date is June of 1983! — so even with a few expansions, this is very much a machine of its time. We almost hate to call attention to the machine and
its current status page
, lest it receive too much Hackaday love and spoil the uptime. So tread carefully, please.
The
Oppenheimer
hype train is rolling right along, with movie-related content pouring into our news feeds on a daily basis. The attempt to coerce us into shelling out money to see this particular flick is wasted on us; we made up our minds to see this one in the theater a long time ago. But the exertions of the “Oppen-hypers” haven’t been for naught, as we’ve gleaned some interesting Manhattan Project content from the noise. One of the most interesting is
this video
which takes a deeper dive into the whole “we could have set the atmosphere on fire” worry that Oppenheimer and his team had before the Trinity test. We’d heard plenty about that, but never the physics or the math, which turn out to be pretty fascinating. Basically, the fear was that the heat of the plutonium implosion bomb would cause atmospheric nitrogen to fuse into magnesium and cause a thermonuclear chain reaction that would turn the world into a cinder. It didn’t turn out that way, of course, but the math shows that the margin for error was way, way too close for comfort.
And finally, a far less apocalyptic video for your weekend viewing pleasure:
A look into the sharpness of obsidian flakes
. We’d always heard that the volcanic glass could be flaked into edges that rival the finest surgical steel, and allowed Stone Age cultures to develop some surprisingly advanced cutting technologies. The video compares knapped flint and obsidian to modern steel edges — both a commercial razor blade and a fine double-bevel-sharpened woodworking chisel. Using a micrometer to advance the edges into a single human hair under a microscope, it turns out that while natural materials are certainly sharp, they’re no match for the toughness of steel edges. Which begs the question:
Why is obsidian used as a cutting edge in modern specialty surgical scalpels
? If an obsidian edge nicks when forced against a human hair, how does it stand up against even the tenderest of skin? | 4 | 2 | [
{
"comment_id": "6665382",
"author": "Alex",
"timestamp": "2023-07-24T03:43:24",
"content": "Here’s another link to an article about the PCjr webserver in the third paragraph :-)…https://hackaday.com/2023/07/20/pcjr-webserver-hits-2500-hours-uptime/",
"parent_id": null,
"depth": 1,
"repl... | 1,760,372,224.748388 | ||
https://hackaday.com/2023/07/23/vanmoof-e-bike-bankruptcy-the-risks-of-cloud-connected-transport/ | VanMoof E-Bike Bankruptcy: The Risks Of Cloud-Connected Transport | Maya Posch | [
"News",
"Transportation Hacks"
] | [
"e-bike",
"VanMoof"
] | When the bankruptcy of VanMoof, the company behind a series of e-bikes, was announced recently, many probably shrugged at this news. After all, what is an e-bike but a regular bicycle that has some electronics and a battery strapped to it to assist with cycling? Unfortunately for owners of a VanMoof e-bike, their fancy wheels come with a Bluetooth-connected smartphone app that somehow involves storing a special encryption key on the VanMoof servers, as
detailed by [Gergely Orosz]
at the
Pragmatic Engineer
. Without this key that is connected to your
VanMoof
account, your VanMoof app cannot communicate with your VanMoof e-bike.
Although basic functionality of the e-bike will be retained, features such as setting the gear modes, changing assistance mode, locking the bicycle and other features not exposed on the bicycle itself will be lost. Essentially this is the equivalent of losing the remote control to a modern-day TV and getting locked out of 90% of the device’s features.
Fortunately, as [Gergely] and others are (urgently) pointing out to VanMoof e-bike owners, this special key can be downloaded with a
Key Exporter project on GitHub
, as well as obtained and used with an alternative app by Cowboy Bikes, which is a competitor of VanMoof. The unfortunate reality remains, however, that should you lose this special key, you are going to be in a world of pain as your expensive e-bike now is mostly an e-brick.
(Thanks to [Jan Praegert] for the tip) | 66 | 19 | [
{
"comment_id": "6665293",
"author": "Rog Fanther",
"timestamp": "2023-07-23T20:05:11",
"content": "Alternative firmware, anyone ?Also, needing an app to change gears ?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665296",
"author": "The Gambler",... | 1,760,372,224.854407 | ||
https://hackaday.com/2023/07/23/amateur-estimates-of-venusian-day-using-arecibo-data/ | Amateur Estimates Of Venusian Day Using Arecibo Data | Chris Lott | [
"Science"
] | [
"amateur",
"amateur astronomy",
"Arecibo Observatory",
"venus"
] | [Nathaniel Fairfield] aka [thandal] was curious about the actual rotation and axis tilt of Venus. He decided to spin up at
GitHub Python repository
to study the issue further, as one does. The scientific literature shows a wide range of estimates and variations for the planet’s rotation and axis tilt. He wondered if the real answer might be found in a
publicly available set
of uncalibrated delay-doppler images of Venus. These data were collected by the former Arecibo Observatory in Puerto Rico from 1988 through 2020. [Thanda] observed that the planet’s rotation appears to be speeding up slightly, and furthermore, his estimates of the orbital axis were within 0.01 degrees of the International Astronomical Union’s (IAU) values. [Note: Venus is a bit confusing — one planetary rotation, 243 Earth days, is longer than its year, 225 Earth days].
Estimations of Venusian Orbital Period, [Thandal] Estimates in Green
Aligning and calibrating the raw data was no trivial task. You have to consider the radar’s (Earth’s) position and time, as well as Venus. Complicating the math even more, some times the radar was operated in a bistatic mode, with the Green Bank Telescope in West Virginia being the receiver.
There’s a lot of interesting signal processing going on here. The Doppler-delay data consists of images that are 8091×8092 array of complex values, has to be mapped onto the Venus geoid. Then by using various surface features, one can compare their positions vs time and obtain an estimate of rotational speed and tilt. If these kinds of calculations interest you, be sure to check out [Thandal]’s
summary report
, and also take note of
the
poliastro
Python astrodynamics library
. Why is this important? One reason to better plan future missions. | 7 | 4 | [
{
"comment_id": "6665291",
"author": "Hirudinea",
"timestamp": "2023-07-23T19:54:06",
"content": "Something you’ll never hear on Venus, “Hey boss, can I have tomorrow off?”",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6665302",
"author": "wibble",
"t... | 1,760,372,224.903387 | ||
https://hackaday.com/2023/07/23/google-nest-mini-gutted-and-rebuilt-to-run-custom-agents/ | Google Nest Mini Gutted And Rebuilt To Run Custom Agents | Lewin Day | [
"google hacks"
] | [
"google",
"Google Nest",
"voice assistant"
] | The Google Nest Mini is a popular smart speaker, but it’s very much a cloud-based Big Tech solution. For those that want to roll their own voice assistant, or just get avoid the corporate surveillance of it all,
[Justin Alvey’s] work may appeal
. (
Nitter
)
[Justin] pulled apart a Nest Mini, ripped out the original PCB, and kitted it out with his own internals. He uses the ESP32 as the basis of his design, since it provides plenty of processing power and WiFi connectivity. His replacement PCB also interfaces with the LEDs, mute switch, and capacitive touch features of the Nest Mini, for ease of interaction.
As a demo, he set up the system to work with a custom
“Maubot” assistant
using the
Matrix framework
. He hooked it up with Beeper, a messaging client that collates all your other messaging platforms into one easily-accessible place. The assistant employs GPT3.5, prompted with a list of his family, friends, and other details, to enable him to make calls, send messages, and handle natural language queries.
The demo itself
is very impressive, and we’d love to try setting up a similar assistant ourselves. Seeing two of [Justin’s] builds talking to each other is amusing, too.
If you’re more comfortable working with Google Assistant rather than dropping it entirely,
we’ve looked at that kind of thing, too
. Video after the break.
I “jailbroke” a Google Nest Mini so that you can run your own LLM’s, agents and voice models.
Here’s a demo using it to manage all my messages (with help from
@onbeeper
)
🔊 on, and wait for surprise guest!
I thought hard about how to best tackle this and why, see 🧵
pic.twitter.com/rUBGoM1pO0
— Justin Alvey (@justLV)
July 18, 2023 | 18 | 8 | [
{
"comment_id": "6665239",
"author": "JoldaxPrime",
"timestamp": "2023-07-23T15:49:47",
"content": "If it can work with AnyList, I’ll have to try this.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6665259",
"author": "hmsYA",
"timestamp": "2023-07-23... | 1,760,372,224.955719 | ||
https://hackaday.com/2023/07/23/closing-in-on-a-pc-enabled-psvr2/ | Closing In On A PC Enabled PSVR2 | Donald Papp | [
"Reverse Engineering",
"Virtual Reality"
] | [
"headset",
"playstation",
"PSVR2",
"reverse engineering",
"sony",
"virtual reality",
"vr"
] | When the PlayStation VR2 headset was released, people wondered whether it would be possible to get the headset to work as a PC VR headset. That would mean being able to plug it into a PC and have it work as a VR headset, instead of it only working on a PS5 as Sony intended.
Enthusiasts were initially skeptical and at times despondent about the prospects, but
developer [iVRy]’s efforts
recently had a breakthrough. A PC-compatible VR2 is looking more likely to happen.
So far [iVRy] is claiming they have 6 DOF SLAM (Simultaneous Localisation and Mapping), Prox sensor, and stereo camera data.
Most of the juicy bits are paywalled behind [iVRy]’s Patreon. We’re hoping the jailbreak process will eventually be open-sourced.
The PS VR2 headset is quite unlike a PC VR headset in a number of ways, and it has not been historically easy to work with Sony’s products from a reverse-engineering perspective, whether it’s an attempt to
improve the user experience of an annoying headset
, or an attempt to understand the
not-even-remotely-sanely-designed protocols behind the Sony Memory Stick
. Getting the PS VR2 headset to work in a way it wasn’t intended was expected to be an uphill battle.
It’s not a finished job, but judging by the progress regularly shared on
[iVRy]’s Twitter account
, it might only be a matter of time. | 25 | 5 | [
{
"comment_id": "6665214",
"author": "Petter",
"timestamp": "2023-07-23T13:32:31",
"content": "So… No display input to the VR headset? Seems kind of like the most important bit in my mind, but no mention",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665218... | 1,760,372,225.022273 | ||
https://hackaday.com/2023/07/23/mapping-the-depths-with-an-autonomous-solar-boat/ | Mapping The Depths With An Autonomous Solar Boat | Tom Nardi | [
"gps hacks",
"green hacks",
"Robots Hacks"
] | [
"autonomous boat",
"depth mapping",
"solar",
"sonar"
] | Ever look out at a pond, stream, or river, and wonder how deep it is? For large bodies of water that are considered navigable, it’s easy enough to pull up a chart and find out. But what if there’s no public data for the area you’re interested in?
Well, you
could
spend all day on a little boat taking depth readings and making your own chart, but if you’re anything like [Clay] you could build a
solar-powered autonomous robot to do it for you
. He’s been working on the boat, which he calls
Gumption Trap
, for the better part of a year now. If we had to guess, we’d say the experience of designing and building it has ended up being a bit more interesting to him than the actual depth of the water — but that’s fine by us.
The design of the boat is surprisingly economical, as far as marine designs go. Two capped four-inch PVC pipes are used as pontoons, and 3D printed brackets attach those to an aluminum extrusion frame that holds the electronics and solar panel high above the water. This arrangement provides an exceptionally stable platform that would be all but impossible to flip under normal circumstances.
Around the back of the craft, there’s a pair of massive 3D printed thrusters, complete with some remarkably chunky printed propellers. The lack of rudders keeps things simple, with differential thrust between the two motors enough to keep the
Gumption
pointed in the right direction.
A waterproof container holds the batteries, solar charge controller, radio gear (for manual control), and the main computer. That computer is a custom PCB containing various modules that make up the brains of the operation. That includes a Teensy microcontroller, a GPS, compass, and a Ping echo sounder from Blue Robotics that [Clay] says cost more than the rest of the project put together. But of course you get what you pay for, and it’s hard to argue it wasn’t worth the investment when you look at the impressive 3D depth maps he’s managed to produce with the data it spits out.
For anyone looking to set sail with a similar craft, [Clay] has provided the source code for his boat, the board files for his custom PCB, and even the MATLAB code used to graph the depth data. He’s also put together the trio of videos below, which document the construction of the boat over the last eight months. The videos provide an interesting look at how the design has matured over time.
This isn’t the first PVC pontoon boat to have graced these pages, last year
we covered a similar design from [wesgood]
that’s also worth taking a look at if you’re thinking of building your own robotic watercraft. | 17 | 9 | [
{
"comment_id": "6665177",
"author": "Juan F Thompson",
"timestamp": "2023-07-23T10:27:04",
"content": "Have you considered adding a downward facing camera to create a visual map in addition to the depth map? Marine archaeologists are starting to use this kind of robot to map areas close to shore we... | 1,760,372,225.080784 | ||
https://hackaday.com/2023/07/22/bridging-a-gap-between-llms-and-programming-with-typechat/ | Bridging A Gap Between LLMs And Programming With TypeChat | Bryan Cockfield | [
"Software Hacks"
] | [
"ChatGPT",
"coding",
"interface",
"javascript",
"json",
"large language model",
"LLM",
"openai",
"programming",
"type safe"
] | By now, large language models (LLMs) like OpenAI’s ChatGPT are old news. While not perfect, they can assist with all kinds of tasks like creating efficient Excel spreadsheets, writing cover letters, asking for music references, and putting together functional computer programs in a variety of languages. One thing these LLMs don’t do yet though is integrate well with existing app interfaces. However,
that’s where the TypeChat library comes in
, bridging the gap between LLMs and programming.
TypeChat is an experimental MIT-licensed library from Microsoft which sits in between a user and a LLM and formats responses from the AI that are type-safe so that they can easily be plugged back in to the original interface. It does this by generating JSON responses based on user input, making it easier to take the user input directly, run it through the LLM, and then use the output directly in another piece of code. It can be used for things like prototyping prompts, validating responses, and handling errors. It’s also not limited to a single LLM and can be fairly easily modified to work with many of the existing models.
The software is still in its infancy but does hope to make it somewhat easier to work between user inputs within existing pieces of software and LLMs which have quickly become all the rage in the computer science world. We expect to see plenty more tools like this become available as more people take up using these new tools,
which have plenty of applications beyond just writing code
. | 33 | 3 | [
{
"comment_id": "6665146",
"author": "Mr Name Required",
"timestamp": "2023-07-23T07:39:57",
"content": "Why am I left thinking this is going to lead to a world of pain in times to come. With AI’s just spewing out all sorts of human-unmanageable code we’re going to need more AI’s to patch that code,... | 1,760,372,225.199575 | ||
https://hackaday.com/2023/07/22/rfid-emulator-e-paper-badge-can-be-programmed-with-sound/ | RFID Emulator + E-paper Badge Can Be Programmed With Sound | Donald Papp | [
"Crowd Funding",
"hardware"
] | [
"badge",
"e-paper",
"ggtag",
"ggwave",
"rfid",
"sound"
] | In a way, an e-paper display makes an excellent foundation for a reprogrammable RFID card. The display only needs power during a refresh, and 125 kHz RFID tags are passive in the sense that the power for the RFID transaction comes from the reader itself. [Georgi Gerganov] has put those together in the
GGtag
, an open-source project for a 3.52″ e-paper badge with a trick or two up its sleeve.
One clever function is that it is programmable with sound, a feature built off another project of [Georgi]’s called
ggwave
, a data-to-sound (and vice-versa) framework that has been ported to just about every hardware platform one cares to imagine — including mobile phones — and can reliably send data through the air.
Transmitting data over sound is limited in throughput but has a number of advantages, not least of which is the huge range of compatible devices. There’s a web-based tool for programming the GGtag with sound available at
ggtag.io
that will give you a preview and let you hear how it works. The data encoding method gives transmissions a charming beep-boop quality that’s a bit reminiscent of an analog modem handshake. GGtag can also be programmed over USB serial, a faster (but somewhat less exciting) option.
The project’s
GitHub repository
contains GGtag’s code and technical details, and the
CrowdSupply project
is in the works for anyone who would prefer to buy one once they become available. | 9 | 2 | [
{
"comment_id": "6665108",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-23T02:51:29",
"content": "Data to sound and back to data.I had a modem that did that 30 years ago.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665126",
... | 1,760,372,225.130552 | ||
https://hackaday.com/2023/07/22/2023-cyberdeck-challenge-crosberry-pi-loves-lo-fi-hip-hop/ | 2023 Cyberdeck Challenge: Crosberry Pi Loves Lo-Fi Hip Hop | Kristina Panos | [
"contests",
"Cyberdecks"
] | [
"2023 Cyberdeck Challenge",
"Crosley",
"cyberdeck",
"raspberry pi",
"record player",
"trackball",
"trackball mouse"
] | As far as we can tell, the only real selling point that any portable record player offered was, well, its portability. To be clear, the sound is never that great. But perhaps a selling point for this crowd is that they usually come in hinged cases with handles, and you know what that means —
cyberdeck that thing
!
[
Mx. Jack Nelson
] started gutting this Crosley CR40 record player to make a Raspberry Pi housing, but it quickly turned into a cyberdeck project with the addition of a 10.1″ portable monitor, a Planck ortholinear keyboard, and a gutted trackball mouse.
We love that [
Mx. Jack Nelson
] made use of the Crosley’s original speakers — this was the wife’s idea! — as well as the volume and tone knobs. But our favorite part has to be the clear acrylic top that both protects the electronics and provides a platform for the keyboard and mouse buttons. Be sure to check out the demo video after the break. | 1 | 1 | [
{
"comment_id": "6665230",
"author": "Piotrsko",
"timestamp": "2023-07-23T14:44:33",
"content": "Back in the day you didn’t get your music to travel with you so anything that played music remotely was like totally awesome crappy sound or not.",
"parent_id": null,
"depth": 1,
"replies": ... | 1,760,372,225.234337 | ||
https://hackaday.com/2023/07/22/root-on-an-amazon-echo-dot/ | Root, On An Amazon Echo Dot | Jenny List | [
"Reverse Engineering"
] | [
"Amazon Echo",
"android",
"echo dot",
"jailbreak",
"root"
] | The Amazon Echo has become an indispensable device for many people unconcerned by its privacy implications. It’s easy to forget that it’s not quite a new product anymore, with the oldest examples now long in the tooth enough to no longer receive security updates. A surprise is that far from being mere clients to Amazon cloud services, they in fact run a version of Android. This makes old dots interesting to experimenters, but first is it possible to gain root access? [Daniel B] has managed it,
on a second-generation Echo Dot
.
In a sense, this is nothing new, as root has previously been achieved on an Echo Dot through means of a patched kernel. Echo devices use a chain of trust boot process in which each successive step must verify the Amazon signing of the previous one. The kernel patch method breaks the ability to reboot the device with root access. [Daniel’s] method bypasses that chain of trust by using a custom pre-loader injected over USB through an exploit.
As an example, [Daniel] created a web server on his Dot, which can serve audio captured by the device. Don’t panic just yet — an analysis of the other security features suggests that this is not the dangerous exploit it might seem. It does however open up these powerful but now pretty cheap devices as potentially usable for other purposes, which can only be a good thing.
We’ve previously brought you
[Daniel]’s work freeing the WiFi details from a Dot
. | 41 | 10 | [
{
"comment_id": "6665055",
"author": "ono",
"timestamp": "2023-07-22T21:37:00",
"content": "So, what would it be possible to do with a freed echo dot gen. 2 ?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665079",
"author": "Jack",
"timesta... | 1,760,372,225.446025 | ||
https://hackaday.com/2023/07/22/the-moment-a-bullet-turns-into-a-flashlight-caught-on-film/ | The Moment A Bullet Turns Into A Flashlight, Caught On Film | Donald Papp | [
"chemistry hacks",
"Weapons Hacks"
] | [
"ballistic gel",
"diesel effect",
"firearms",
"flash",
"gunpowder",
"slow motion"
] | [The Slo Mo Guys] caught something fascinating while
filming some firearms at 82,000 frames per second
: a visible emission of light immediately preceding a bullet impact. The moment it occurs is pictured above, but if you’d like to jump directly to the point in the video where this occurs,
it all starts at [8:18]
.
The ability to capture ultra-slow motion allows us to see things that would otherwise happen far too quickly to perceive, and there are quite a few visual spectacles in the whole video. We’ll talk a bit about what is involved, and what could be happening.
Spotting
something unusual
on video replay is what exteme slo-mo filming is all about.
First of all, the clear blocks being shot are ballistic gel. These dense blocks are tough, elastic, and a common sight in firearms testing because they reliably and consistently measure things like bullet deformation, fragmentation, and impact. It’s possible to make homemade ballistic gel with sufficient quantities of gelatin and water, but the clear ones like you see here are oil-based, visually clear, and more stable (they do not shrink due to evaporation).
We’ve seen
the diesel effect occur in ballistic gelatin
, which is most likely the result of the bullet impact vaporizing small amounts of the (oil-based) gel when the channel forms, and that vaporized material ignites due to a sudden increase in pressure as it contracts.
In the video linked above (and embedded below), there is probably a bit more in the mix. The rifles being tested are large-bore rifles, firing big cartridges with a large amount of gunpowder igniting behind each bullet. The burning powder causes a rapid expansion of hot, pressurized gasses that push the bullet down the barrel at tremendous speed. As the bullet exits, so does a jet of hot gasses. Sometimes, the last bits of burning powder are visible as a brief muzzle flash that accompanies the bullet leaving the barrel.
A large projectile traveling at supersonic velocities results in a large channel and expansion when it hits ballistic gel, but when fired at close range there are hot gasses from the muzzle and any remaining burning gunpowder in the mix, as well. All of which help generate the kind of visual spectacles we see here.
We suspect that the single frame of a flashlight-like emission of light as the flat-nosed bullet strikes the face of the gel is also the result of the diesel effect, but it’s an absolutely remarkable visual and a fascinating thing to capture on film. You can watch the whole thing just below the page break. | 14 | 6 | [
{
"comment_id": "6665010",
"author": "Brian",
"timestamp": "2023-07-22T18:22:38",
"content": "My guess would be sonoluminescence due to dissolved gas, but could be the “Argon Bomb” type flash seen when explosives compress air or argon gas.",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,227.367792 | ||
https://hackaday.com/2023/07/22/whos-afraid-of-assembly-language/ | Who’s Afraid Of Assembly Language? | Elliot Williams | [
"Hackaday Columns",
"Rants",
"Slider",
"Software Hacks"
] | [
"assembly language",
"newsletter"
] | This week, [Al Williams] wrote
a great thought piece about whether or not it was worth learning an assembly language
at all anymore, and when. The comments overflowed, and we’re surprised that so many people basically agree with us: yes. Of course, it’s a Hackaday crowd, but I still didn’t expect the outpouring of love for the most primitive of languages.
Assembly language isn’t really one language, though. Every chip speaks its own dialect. Of course there are similarities: every CPU has an add function, right? But almost no CPU has just one add – there are variants with and without carry, storing and reading from working registers or RAM. And once you start talking about memory access, direct or indirect, the individual architectures of the chips demand different assembly languages.
But still, although the particular ways that CPUs do what they do can be incompatible from a strictly language perspective, they are a lot more similar in terms of the programming idioms that you’ll pick up along the way. Just as learning a set of solid algorithms will help you no matter which higher-level language you use, learning the concepts behind crafting loops and simple memory structures out of raw assembly language will serve you no matter which CPU you choose.
I have only written assembly language for a handful of CPUs, and not much of it at that, but I’ve found the microcontrollers to be the friendliest. So if you want to dip your toes in that water, pick up an AVR or an MSP430. Or maybe even the new hotness – a RISC-V. You’ll find the instruction sets small enough that you have to do most of the work yourself. And that is, after all, the point of learning an assembly language: learning to think like the silicon. If you treat it like a fun puzzle to solve, you’ll probably even enjoy the experience.
[Al]’s original question was when you should learn an assembly language: before or after a higher-level language. For 99% of our readers, I’d say the answer is
right now
.
This article is part of the Hackaday.com newsletter, delivered every seven days for each of the last 200+ weeks. It also includes our favorite articles from the last seven days that you can see on
the web version of the newsletter
.
Want this type of article to hit your inbox every Friday morning?
You should sign up
! | 109 | 39 | [
{
"comment_id": "6664964",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-22T14:11:03",
"content": "I am!That’s why I haven’t touched it in decades!B^)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664966",
"author": "Ken",
"t... | 1,760,372,227.649038 | ||
https://hackaday.com/2023/07/22/that-ultra-white-paint-that-helps-cool-surfaces-make-your-own/ | That Ultra-White Paint That Helps Cool Surfaces? Make Your Own! | Donald Papp | [
"chemistry hacks",
"Science"
] | [
"acrylic paint",
"ambient",
"barium sulfate",
"paint",
"passive cooling",
"radiative cooling"
] | It started with [KB9ENS] looking into paints or coatings for passive or radiative cooling, and
in the process he decided to DIY his own
. Not only is it perfectly accessible to a home experimenter, his initial results look like they have some promise, as well.
[KB9ENS] read about a type of
ultra-white paint formulation
that not only reflects heat, but is able to radiate it into space, cooling the painted surface to below ambient temperature. This is intriguing because while commercial paints can insulate and reflect heat, they cannot make a surface cooler than its surroundings.
Anecdotally speaking, this painted battery section of a solar recharger gets too hot to touch in full sunlight. But when painted over, it was merely warm.
What really got [KB9ENS] thinking was that at its core, the passively-cooling paint in the research is essentially a whole lot of different particle sizes of barium sulfate (BaSO₄) mixed into an acrylic binder. These two ingredients are remarkably accessible. A half-pound of BaSO₄ from a pottery supply shop was only a few dollars, and a plain acrylic base is easily obtained from almost any paint or art supplier.
[KB9ENS] decided to mix up a crude batch of BaSO₄ paint, apply it to some things, and see how well it compared to other paints and coatings. He wetted the BaSO₄ with some isopropyl alcohol to help it mix into the base, and made a few different concentrations. A 60% concentration by volume seemed to give the best overall results.
There’s no indication of whether any lower-than-ambient cooling is happening, but according to a non-contact thermometer even this homemade mixture does a better job of keeping sunlight from heating things up compared to similarly-applied commercial paints (although it fared only slightly better than
titanium dioxide
-based white paint in the initial test.)
[KB9ENS] also painted the battery section of a solar recharger with his homemade paint and noted that while under normal circumstances — that is to say, in full sunlight — that section becomes too hot to touch, with the paint coating it was merely warm.
Actual passive cooling can do more than just keep something less warm than it would be otherwise. We’ve seen it recently used to
passively and continuously generate power
thanks to its ability to create a constant temperature differential, day and night. | 53 | 17 | [
{
"comment_id": "6664925",
"author": "alialiali",
"timestamp": "2023-07-22T11:02:58",
"content": "Night hawk in light did something similarhttps://www.youtube.com/watch?v=KDRnEm-B3AI",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6665029",
"author": ... | 1,760,372,227.507492 | ||
https://hackaday.com/2023/07/22/behold-a-gallery-of-sonys-ps-vr2-prototypes/ | Behold A Gallery Of Sony’s PS VR2 Prototypes | Donald Papp | [
"Virtual Reality"
] | [
"headset",
"Prototypes",
"virtual reality",
"vr"
] | Every finished product stands at the end of a long line of prototypes, and Sony have recently shared an
interview and images of their PlayStation VR2 prototypes
.
Many of the prototypes focus on a specific functionality, and readers who are not familiar with building things might find it a bit wild to see just how big and ungainly un-optimized hardware can be.
Finished product (bottom) contrasted with functionally-identical prototype (top).
The images are definitely the best part of that link, but the interview has a few interesting bits. For example, one prototype was optimized for evaluating and testing camera placement with a high degree of accuracy, and it hardly looks like a VR headset at all.
The controllers on the other hand seem to have gone though more iterations based on the ergonomics and physical layout of controls. The VR2 controllers integrate the adaptive triggers from the PlayStation 5,
which are of a genuinely clever design
capable of variable resistance as well as an active force feedback effect that’s not quite like anything that’s come before.
There’s a lot of work that goes into developing something like a VR headset, as we see here and we’ve seen with
Facebook’s (now Meta) VR research prototypes
. But even when one can leverage pre-made modules as much as possible and doesn’t need to start
entirely
from scratch,
making a VR headset remains a whole heap of work
. | 3 | 3 | [
{
"comment_id": "6664916",
"author": "Gérald",
"timestamp": "2023-07-22T09:04:59",
"content": "Looking at the close-up picture of the tracking system prototype, it seems they used an Arduino Due with a probably custom hat.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comm... | 1,760,372,227.061432 | ||
https://hackaday.com/2023/07/21/restored-amiga-500-is-blue-and-glows-in-the-dark/ | Restored Amiga 500 Is Blue – And Glows In The Dark | Robin Kearey | [
"Retrocomputing"
] | [
"Amiga 500",
"case modding",
"floppy emulator",
"gotek",
"spray paint"
] | Few things are as satisfying to watch as a good retrocomputer restoration project – we’re always happy to see someone bring a rusty old Commodore, Apple or Atari back to life. The goal is typically to get the machine as close to its original state as possible, except for perhaps a few non-intrusive mods like memory upgrades. [Drygol] however, had already done this so many times that he thought it was time to take a different route for once, and apply some creativity to an old Amiga 500 case. Originalists may shudder, but we quite like
his funky blue-and-yellow A500 mod
.
Missing keys, random stickers and an ugly paint job: the A500 wasn’t looking great at the beginning
To be fair, [Drygol] wasn’t the first one to modify this specific Amiga’s case: one of its previous owners had already applied a rather shoddy blue paint job and defaced it with some stickers. [Drygol] decided to stick with the basic idea, but do it right this time. First he removed the old paint using concentrated lye, then gave it a fresh coat of blue. He also applied glow-in-the-dark paint to the Amiga logo embossed in the case and added a fluorescent yellow laser-cut circuit board ornament. It took a bit of experimenting to get all these elements just right, but the end result definitely looks the part.
The insides of the Amiga also needed some TLC: [Drygol] competely cleaned and lubricated the floppy drive, gave the motherboard a good ultrasonic scrub, and replaced dodgy capacitors all over. He expanded the RAM from 512 kB to 1 MB and added a Gotek floppy emulator, which can work in parallel with the original disk drive. To make the Gotek easy to operate, [Drygol] placed its OLED screen and a pair of touch-sensitive buttons in a cutout on the front of the case.
A matching blue mouse and gamepad, both connected through
the MouSTer adapter,
complete the setup. The result is a good-looking A500 with some modern conveniences that’s perfect for exploring the Amiga’s extensive software library. If custom colors aren’t your thing, you’ll be happy to know that the
original shade of grey or beige
might be available for your retro console, too. | 5 | 2 | [
{
"comment_id": "6664893",
"author": "Sjaak",
"timestamp": "2023-07-22T05:51:32",
"content": "The link to the paint article isn’t usable anymore. The shop couldn’t get worldwideshipping to work for spraycans and seized to sell them.Unfortunately as i have a couple of Amiga 2000’s which need some pai... | 1,760,372,227.011837 | ||
https://hackaday.com/2023/07/21/when-is-open-source-ai-not-open-source-ai/ | When Is Open Source AI Not Open Source AI? | Jenny List | [
"Artificial Intelligence"
] | [
"ChatGPT",
"llama",
"meta",
"open source"
] | The world of AI is abuzz, or at least parts of it are,
at the news of Meta’s release of Llama 2
. This is an AI text model which is thought to surpass ChatGPT in capabilities, and which the social media turned VR turned own all your things company wants you to know is open to all. That’s right, the code is open source and you can download the model, and Meta want you to feel warm and fuzzy about it. Unfortunately all is not as it seems, because of course the model isn’t open-source and is subject to a licensing restriction which makes it definitely not free of charge for larger users. This is of course disappointing to anyone hoping for an AI chatbot without restrictions, but we’re guessing Meta would prefer not to inadvertently enable a competitor.
Happily for the open source user large or small who isn’t afraid of a little work there’s an alternative in the form of
OpenLLaMA
, but we understand that won’t be for all users. Whichever LLM you use though, please don’t make the mistake
of imagining that it possesses actual intelligence
.
Thanks to the CoupledAI team for the tip! | 18 | 3 | [
{
"comment_id": "6664881",
"author": "Jonathan Bennett",
"timestamp": "2023-07-22T04:24:53",
"content": "And there’s still the outstanding question of how the licensing of the training data affects the license of the LLM output.",
"parent_id": null,
"depth": 1,
"replies": [
{
... | 1,760,372,227.214017 | ||
https://hackaday.com/2023/07/21/robopianist-is-a-simulation-for-advancing-robotic-control/ | RoboPianist Is A Simulation For Advancing Robotic Control | Lewin Day | [
"Musical Hacks"
] | [
"piano",
"simulation"
] | Researchers at Google have posed themselves an interesting problem to solve: mastering the piano. However, they’re not trying to teach themselves, but a pair of simulated anthropomorphic robotic hands instead.
Enter RoboPianist.
The hope is that the RoboPianist platform can help benchmark “high-dimensional control, targeted at testing high spatial and temporal precision, coordination, and planning, all with an underactuated system frequently making-and-breaking contacts.”
If that all sounds like a bit much to follow, the basic gist is that playing the piano takes a ton of coordination and control. Doing it in a musical way requires both high speed and perfect timing, further upping the challenge. The team hopes that by developing control strategies that can master the piano, they will more broadly learn about techniques useful for two-handed, multi-fingered control. To that end, RoboPianist models a pair of robot hands with 22 actuators each, or 44 in total. Much like human hands, the robot hands are underactuated by design, meaning they have less actuators than their total degrees of freedom.
If you’ve ever seen
a human-like robot hand
pick something up, you’ve probably noticed how slow and ungainly they are. With so many joints to control, making a hand work is a tough task. Learning to play the piano is thus an excellent benchmarking test to develop these techniques.
The project paper
highlights a variety of methods the researchers have used to train RoboPianist to play the instrument. It’s not great yet; you’d certainly make excuses if RoboPianist asked you to come to a gig. But it can definitely play the piano to a basic degree, that’s for sure.
The work is available
on Github
for those that wish to dive deeper, while there’s also
a live demo
you can play with in a browser. In the meantime, you might like to explore
other roboticized efforts to play the piano
. Video after the break. | 10 | 6 | [
{
"comment_id": "6664848",
"author": "MartyK",
"timestamp": "2023-07-21T23:18:29",
"content": "The hands are floating with no support; this is just an animation.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664851",
"author": "The Commenter Former... | 1,760,372,227.410256 | ||
https://hackaday.com/2023/07/21/ai-learns-to-walk-in-3d-training-grounds/ | AI Learns To Walk In 3D Training Grounds | Lewin Day | [
"Machine Learning"
] | [
"ai",
"artificial intelligence",
"learn to walk",
"machine learning",
"unity",
"unity engine",
"walk",
"walk cycle",
"walking"
] | AI agents are learning to do all kinds of interesting jobs, even the creative ones that we quite prefer handling ourselves. Nevertheless, technology marches on. Working in this area is YouTuber [AI Warehouse],
who has been teaching an AI to walk in a simulated environment.
Albert needed some specific guidance to learn how to walk upright, something that humans tend to figure out innately.
The AI controls a vaguely humanoid-like creature, albeit with a heavily-simplified body and limbs. It “lives” in a 3D environment created in the Unity engine, which provides the necessary physics engine for the work. Meanwhile, the ML-Agents package is used to provide the brain for Albert, the AI charged with learning to walk.
The video steps through a variety of “deep reinforcement learning” tasks. In these, the AI is rewarded for completing goals which are designed to teach it how to walk. Albert is given control of his limbs, and simply charged with reaching a button some distance away on the floor. After many trials, he learns to do the worm, and achieves his goal.
Getting Albert to walk upright took altogether more training. Lumpy ground and walls in between him and his goal were used to up the challenge, as well as encouragements to alternate his use of each foot and to maintain an upright attitude. Over time, he was able to progress through skipping and to something approximating a proper walk cycle.
One may argue that the teaching method required a lot of specific guidance, but it’s still a neat feat to achieve nonetheless. It’s altogether more complex than
learning to play Trackmania
, we’d say, and that was impressive enough in itself. Video after the break. | 13 | 6 | [
{
"comment_id": "6664816",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-21T20:06:41",
"content": "Now, teach Albert how to launch nuclear missiles.Skynet is waiting…",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664823",
"author... | 1,760,372,227.155572 | ||
https://hackaday.com/2023/07/21/sand-drawing-plotter-runs-on-esp32/ | Sand Drawing Plotter Runs On ESP32 | Lewin Day | [
"Art"
] | [
"plotter",
"polar coordinates",
"polar plotter",
"sand plotter"
] | Humans have always drawn lines in the sand, whether it’s to communicate a plan of attack or to indicate metaphorically a very real boundary. It’s also something we do just for the aesthetic pleasure,
and this plotter from [aidenvigue]
is great at performing in just that role.
The plotter traces patterns in the circular sand tray by dragging a small marble with a magnet. This is achieved with a pair of NEMA 17 stepper motors, set up in a polar coordinate fashion. One stepper motor controls the angle, while another motor controls the marble’s distance from the center point of the circle. It’s a simple way to build a circular plotter, and works far better than a Cartesian setup would for this geometry. The build uses an ESP32 as the brains of the operation. It hosts a web interface that allows various patterns to be selected and run on the device. It also runs a set of addressable SK6812 LEDs that light the sand rather nicely.
We’ve seen some great sand plotters before, and have always been particular fans
of the larger variety
. Video after the break. | 3 | 2 | [
{
"comment_id": "6664796",
"author": "Olivier",
"timestamp": "2023-07-21T18:49:54",
"content": "Really nice idea and looking great",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664923",
"author": "RoganDawes",
"timestamp": "2023-07-22T10:11:41",
... | 1,760,372,227.098787 | ||
https://hackaday.com/2023/07/21/ask-hackaday-whats-linux-anyway/ | Ask Hackaday: What’s Linux Anyway? | Al Williams | [
"Ask Hackaday",
"Featured",
"Interest",
"Linux Hacks",
"Rants",
"Slider"
] | [
"linux"
] | Any time we mention Linux, it is a fair bet we will get a few comments from people unhappy that we didn’t refer to it as GNU/Linux or with some other appellation. To be fair, they aren’t wrong. Linux is a kernel. Much of what we think of as a Linux desktop OS is really from other sources, including, but not limited to, GNU. We thought about this after reading a report from [The Register] that
Linux has nearly half of the desktop OS Linux market
. Wait, what?
If you are like us, you probably think that’s a typo. It isn’t. But the more you think about it, the less sense it makes. You
know
that half of the world’s desktops don’t run Linux. But maybe they mean Unix? Nope. So how can Linux have almost half of the Linux market? That’s like saying nearly half of Hackaday readers read Hackaday, right?
Here’s the thing. The data came from statistics aggregator Statcounter. They report that desktop Linux use is about 3% of all desktop operating systems, which sounds about right. But an additional 4% are using ChromeOS, and ChromeOS is using Linux — in fact, based on Gentoo Linux and, before that, Ubuntu.
World’s Most Popular Linux?
But, as [The Register] points out, Linux sources don’t like to talk much about ChromeOS. You can make the case that it is like Android, which also leverages parts of Linux, but it really isn’t. Where do you draw the line?
As the post points out, Android isn’t really a full Linux system, at least, not without a lot of hacking, whereas a ChromeOS system uses the same system infrastructure that most Linux boxes use: the kernel, a proper libc, and so on. There are also other Unix splinters like FreeBSD, HURD, OpenBSD, and the like.
So what do you think? What defines a Linux system? Is it simply the kernel? Is it a set of “one true” utilities? What counts and what doesn’t? Will the year of the Linux desktop come, and no one will notice because of fragmentation? If you count Android, has it happened already? Is it a good thing or a bad thing that we don’t have more unification in the Linux/Unix world? Let us know what you think in the comments.
If you want to know more about ChromeOS, we
broke a Chromebook open earlier
. If you want to try FreeBSD, installing it
isn’t as hard as it used to be
. | 55 | 22 | [
{
"comment_id": "6664776",
"author": "me",
"timestamp": "2023-07-21T17:14:11",
"content": "> That’s like saying nearly half of Hackaday readers read Hackaday, right?Have spent time in the comments of various sites, I’d say at least half of hackaday readers actually read hackaday, and that’s **very g... | 1,760,372,227.312525 | ||
https://hackaday.com/2023/07/21/hackaday-podcast-228-bats-eggs-lasers-duck-tape-and-assembly-language/ | Hackaday Podcast 228: Bats, Eggs, Lasers, Duck Tape, And Assembly Language | Dan Maloney | [
"Hackaday Columns",
"Podcasts",
"Slider"
] | [
"Hackaday Podcast"
] | Summer’s in full swing, and this week both Elliot and Dan had to sweat things out to get the podcast recorded. But the hacks were cool — see what I did there? — and provided much-needed relief. Join us as we listen in on the world of bats, look at a laser fit for a hackerspace, and learn how to make an array of magnets greater than — or less than — the sum of its parts. There’ll be flying eggs, keyboards connected to cell phones, and everything good about 80s and 90s cable TV, as well as some of the bad stuff. And you won’t want to miss Elliot putting Dan to shame with the super-size Quick Hacks, either, nor should you skip the Can’t Miss sweep with a pair of great articles by Al Williams.
Check out the links below if you want to follow along, and as always, tell us what you think about this episode in the comments!
Download
a long series of ones and zeroes that, when appropriately interpreted, sound like two people talking about nerdy stuff
!
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 228 Show Notes:
News:
Hackaday Prize 2023: Meet The Assistive Tech Finalists
Supercon 2023 Is On, We Want You!
What’s that Sound?
Congratulations to [Jaxx] for guessing the sound. It was
OtamatoneDX “Brazil (Aquarela do Brasil)”
played by its inventor, the man behind the incomparable Maywa Denki.
Interesting Hacks of the Week:
Listening To Bats As They Search For Food
Worried About Bats In Your Belfry? A Tale Of Two Bat Detectors
Build A Simple Bat Detector
What Does The Bat Say? Tune In With This Heterodyne Detector
Recreating The Golden Era Of Cable TV
Relive The Glory Days Of Cable TV With This Retro Weather Feed
Trebuchet Sends Eggs Flying
FEng Challenge – 009 – Egg-a-pult – Live Stream – YouTube
Brute Forcing A Mobile’s PIN Over USB With A $3 Board
DIY Rubber Ducky Is As Cheap As Its Namesake
DIY Laser For Ablating Metal
Q-switching – Wikipedia
Growing Simple Crystals For Non-Linear Optics Experiments
Halbach Array Makes Magnets Strong, Weak
Powerful, Professional Brushless Motor From 3D-Printed Parts
Shop-Built Fixtures Reveal The Magic Of Switchable Permanent Magnets
Quick Hacks:
Elliot’s (ambitiously long list of) Picks:
Sloth Door Greeter Uses Neat Fold-Up Electronics Enclosures
Welcome To Ziptie City
Hackaday Prize 2023: OMOTE Universal Remote
Improving Ocean Power With Static Electricity
Hackaday Prize 2023: Tilting Mechanical Panels Make A Beautiful Display
Remote Code Execution On An Oscilloscope
Adapter Board Expands The Pi Zero
Sniffing Passwords, Rickrolling Toothbrushes
Dan’s (shamefully short list of) Picks:
Awning Motorized And Automated To Avoid Wind Damage
Taking Mechanical Keyboard Sounds To The Next Level
Leroy Anderson: Ritvélin (The Typewriter) – YouTube
Solenoid Keyboard Sounds Very Much Like a Typewriter
Reverse Engineering Reveals Hidden API In Abandonware Trail Camera
Can’t-Miss Articles:
How Duck Tape Became Famous
Ask Hackaday: Learn Assembly First, Last, Or Never?
Riding The Nostalgia Train With A 6502 From The Ground Up | 1 | 1 | [
{
"comment_id": "6664840",
"author": "Jon",
"timestamp": "2023-07-21T22:14:29",
"content": "Dan, did you find duct tape?",
"parent_id": null,
"depth": 1,
"replies": []
}
] | 1,760,372,227.693811 | ||
https://hackaday.com/2023/07/21/2600-breaks-free-from-drm-with-pdf-epub-subscription/ | 2600 Breaks Free From DRM With PDF/EPUB Subscription | Tom Nardi | [
"internet hacks",
"News"
] | [
"2600",
"amazon",
"drm",
"ebook",
"kindle"
] | Hackaday has been online in some form or another since 2004, which for the Internet, makes us pretty damn old. But while that makes us one of the oldest surviving web resources for hacker types, we’ve got nothing on
2600 —
they’ve been publishing their quarterly zine since 1984.
Summer 2023 Issue of 2600
While the physical magazine can still be found on store shelves, the iconic publication expanded into digital distribution some time ago, thanks largely to the Kindle’s Newsstand service. Unfortunately, that meant Amazon’s recent decision to shutter Newsstand threatened to deprive
2600
of a sizable chunk of their income. So what would any group of hackers do? They took matters into their own hands and
spun-up their own digital distribution system
.
As of today you’re able to subscribe to the digital version of
2600
in DRM-free PDF or EPUB formats, directly from the magazine’s official website. Which one you pick largely depends on how you want to read it: those looking for the highest fidelity experience should go with PDF, as it features an identical layout to the physical magazine, while those who are more concerned with how the content looks on their reader of choice would perhaps be better served by the flexibility of EPUB. After signing up you can download the current Summer issue immediately, with future issues hitting your inbox automatically. Load it onto your
home-built Open Book
, and you can really stick it to the establishment.
While the ending of this story seems to be a happy one, we can’t help but see it as a cautionary tale. How many other magazines would have the means and experience to offer up their own digital subscriptions? Or for that matter, how many could boast readers savvy enough to utilize it? The reality is many publications will be injured by
Amazon’s decision
, some mortally so. That’s a lot of power to be put into the hands of just one company, no matter
how
quick the shipping is. | 13 | 7 | [
{
"comment_id": "6664758",
"author": "Ragnarok700",
"timestamp": "2023-07-21T15:23:20",
"content": "I see this as an opportunity for 2600 to offer those capabilities as a (paid) service to those less technically savvy publications so they can stay available online, too (and DRM-free)!",
"parent_... | 1,760,372,227.749255 | ||
https://hackaday.com/2023/07/21/this-week-in-security-dating-app-woocommerce-and-openssh/ | This Week In Security: Dating App, WooCommerce, And OpenSSH | Jonathan Bennett | [
"computer hacks",
"Hackaday Columns",
"News",
"Security Hacks",
"Slider"
] | [
"openssh",
"This Week in Security",
"WooCommerce"
] | Up first this week is
a report from vpnMentor
, covering the unsecured database backing a set of dating apps, including 419 Dating. The report is a bit light on the technical details, like what sort of database this was, or how exactly it was accessed. But the result is 2.3 million exposed records, containing email address, photos — sometimes explicit, and more. Apparently also exposed were server backups and logs.
The good news here is that once [Jeremiah Fowler] discovered the database door unlocked and hanging open, he made a disclosure, and the database was secured. We can only hope that it wasn’t discovered by any bad actors in the meantime. The app has now disappeared from the Google Play store, and had just a bit of a sketchy air about it.
WooCommerce Under Siege
Back in March,
CVE-2023-28121
was fixed in the WooCommerce plugin for WordPress. The issue here is an authentication bypass that allows an unauthenticated user to commandeer other user accounts.
Within a few months, working exploits had been derived from the details of the patch plugging the hole.
It wasn’t hard
. A function for determining the current user was explicitly trusting the contents of the
X-WCPAY-PLATFORM-CHECKOUT-USER
request header. Set that value in a request sent to the server, and ding, you’re administrator.
And now
the cows are coming home to roost
. Active exploitation started in earnest on July 14, and the folks at Wordfence clocked a staggering 1.3 million exploitation attempts on the 16th. What’s particularly interesting is that the Wordfence data gathering system saw a huge increase in requests for the
readme.txt
file that indicates the presence of the WooCommerce plugin on a WordPress site. These requests were observed before the attacks got started, making for an interesting early warning system.
OpenSSH Has an RCE
But don’t panic. Yes,
there’s an RCE
. And yes it bypasses Address Space Layour Randomization, Position Independent Executables, and the No eXecute bit. The good news is that it’s only reachable by going back down an SSH connection that has ssh-agent forwarding enabled.
This calls for a bit of background. SSH is the Secure SHell program, which allows remote command line connection across the internet. Ssh-agent is a helper program than runs automatically and manages SSH keys — those keys that let you log in to another machine without a password. One of the tricks that a sysadmin has is agent forwarding, enabled with the
-A
flag on the ssh command. This allows the SSH binary on the remote machine to pull keys from the local machine’s ssh-agent process, in order to authenticate an SSH session initiated off to yet another endpoint. It’s always had a warning that it shouldn’t be done with an untrusted machine, to avoid abuse of those keys.
Well now we have yet another reason not to do ssh-agent forwarding. The core observation made by researchers at Qualsys was that the remote machine can trigger a load and unload of all the shared libraries in the
/usr/lib*
folders. And notably, those libraries load in the context of the ssh-agent application, which is not the intended behavior of many of those libraries. The question then becomes, what mischief can be had with just those two primitives?
To find some interesting misbehavior, a fuzzing approach was used, where all of the available libraries in the Ubuntu repositories were run in this condition and an strace captured. There were some interesting findings, like several libraries setting the stack to executable, and some having the nodelete flag set. Then a handful of libraries set up a segfault handler, and fail to properly deregister it when unloaded. And some libraries just crash right away with a segfault.
This does suggest an attack that might work, using library loads and unloads: Make the ssh-agent stack executable, register a SIGSEGV handler and then unmap the code from under the handler. Then load a nodelete library, which puts useful code under the handler pointer, and finally load a library that crashes, jumping execution to the segfault handler. The right code gadget being executed then jumps to the stack, where shellcode can be waiting in a buffer.
It’s brilliant, and thankfully a very narrow windows of exposure for most of us. The flaw was fixed in
an update of OpenSSH this Wednesday
. The broader suggestion is to avoid using ssh-agent forwarding, and instead use ssh jump hosts. Or there’s always
ssh port forwarding
.
Forager
Truffle Security has announced
Forager
, a search engine for leaked secrets. The idea is that individuals and companies routinely publish things to GitHub that they really didn’t intend to make public. Across all of GitHub, Truffle sees something like 1,800 new secrets leaked a day.
What Forager intends to do is automate the confirmation that those secrets are legitimate, make an attempt at informing the organization of the leak, and then categorize those results in a sane way. If you go to Forager now, you can search through the results, but unless you log in with an organization email address, all the results are redacted.
Bits and Bytes
If you ever wanted to know more about MacOS pen testing, and despaired because nearly every resource is aimed at Windows and Linux, then
Cyberark has you covered
. In the first installment of what will hopefully be a long series, we’re introduced to the basics of applications in MacOS, covering details like sandboxing, GUI and network testing, and more. This is one to bookmark, for future reference and further articles.
Gigabyte has gotten some free security analysis of its Baseboard Management Controller firmware, since
it was all dumped in a ransomware attack a couple years ago
. Turns out, that firmware had some really dire vulnerabilities, which
Eclypsium found in a code review
. Two separate CVEs chain together to make a worst-case CVSS 10 attack scenario. Eclypsium has a bit of grim fun at the expense of lights-out management, calling this finding “Lights Out Forever”. | 4 | 4 | [
{
"comment_id": "6664746",
"author": "Gravis",
"timestamp": "2023-07-21T14:23:25",
"content": "Yeah, saw OpenSSH and was filled with dread at first sight. Glad to see it’s a minor issue.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664750",
"author": "F... | 1,760,372,227.92966 | ||
https://hackaday.com/2023/07/21/turning-a-quartz-clock-module-into-a-time-reference/ | Turning A Quartz Clock Module Into A Time Reference | Lewin Day | [
"clock hacks",
"Parts"
] | [
"1 pps reference",
"1pps",
"1pps reference",
"clock",
"Quartz",
"time reference"
] | If you’re looking for a 1-second time reference, you’d probably just grab a GPS module off the shelf and use the 1PPS output. As demonstrated by [InazumaDenki], though,
an old quartz clock module can also do the job with just a little work.
The module was harvested from an old Seiko wall clock, and features the familiar 32.768 KHz crystal you’d expect. This frequency readily divides down by 2 multiple times until you get a useful 1 Hz output. The module, originally designed to run a clock movement, can be repurposed with some basic analog electronics to output a useful time reference. [InazumaDenki] explains various ways this can be done, before demonstrating his favored method by building the device and demonstrating it with a decade counter.
It has some benefits over
a GPS time reference
, such as running at a much lower voltage and needing no external signal inputs. However, it’s also not going to be quite as accurate. Whether that matters to you or not depends on your specific application. Video after the break. | 11 | 6 | [
{
"comment_id": "6664732",
"author": "Paul",
"timestamp": "2023-07-21T13:18:30",
"content": "Funny. I did exactly the same thing a few years ago, to get a stable 1 PPS independent of GPS.Issues:– The even and odd pulses are each not exactly 1s. They are about 50 us different on mine. Not a huge i... | 1,760,372,227.79533 | ||
https://hackaday.com/2023/07/21/old-style-1802-computer-has-mmu/ | Old Style 1802 Computer Has MMU | Al Williams | [
"Microcontrollers",
"Retrocomputing"
] | [
"1802",
"CDP1802",
"cosmac elf"
] | When you think of an MMU — a memory management unit — you probably think of a modern 32-bit computer. But [Jeff Truck] has a surprise. His
new RCA 1802 computer
has bank switching, allowing the plucky little processor to address 256K of RAM. This isn’t just the usual bank-switching design, either.
The machine has several unique features. For example, an Arduino onboard can control the CPU so that you can remotely control the bus. It does not, apparently, stand in for any of the microprocessor support chips. It also doesn’t add additional memory or control its access.
The 256K of memory is under the control of the MMU board. This board generates two extra address bits by snooping the executing instruction and figures out what register is involved in any memory access. Memory in the MMU stores a table that lets you set different memory pages for each register. This works even if the register is not explicit and also for the machine’s DMA and instruction fetch cycles. If you know about the RCA “standard call and return technique,” which also needed a little patching for the MMU. [Jeff] covers that at the end of the video below.
This is a very simple version of a modern MMU and is an impressive trick for a 50-something-year-old CPU. We were surprised to hear — no offense to [Jeff] — that the design worked the first time. Impressive! There’s also some 3D printing and other tips to pick up along the way. But we were super impressed with the MMU. You might never have to do this yourself (although
you could
), but you can still marvel that it can be done at all.
We have a soft spot for the 1802s, real
or emulated
. The
original ELF
was great, but 256K is a lot better than the original 256 bytes! | 8 | 5 | [
{
"comment_id": "6664705",
"author": "Michael Mirsky",
"timestamp": "2023-07-21T08:31:22",
"content": "Wow! I wire wrapped two 8k RAM boards to be able to use Quest Basic on my 1802 back in 1980. But this amount would have been amazing! My Life program could have followed so many more generations be... | 1,760,372,228.199317 | ||
https://hackaday.com/2023/07/20/an-easy-z80-and-vga-upgrade-for-the-apple-ii/ | An Easy Z80 And VGA Upgrade For The Apple II | Lewin Day | [
"Retrocomputing"
] | [
"apple II",
"CP/M",
"vga",
"z80"
] | The Apple II was at the forefront of the home computer revolution when it came out in 1977. In its era, nobody really cared about hooking up the Apple II to a VGA monitor, but these days, it’s far easier than sourcing an original monitor. The
V2 Analog
is a useful tool that will let you do just that, plus some other neat tricks, besides.
As demonstrated on Youtube
by [Adrian’s Digital Basement], The V2 Analog is basically a slot-in video card for the Apple II, II+, and IIe. It’s based upon the
AppleII-VGA,
which uses a
Raspberry Pi Pico
to snoop the 6502 CPU bus and copy the video memory. It then outputs a high-quality VGA signal that is far nicer than the usual composite output options.
As a bonus, the V2 Analog can be reconfigured to run as an emulated AppliCard Z80 expansion card instead. This card was originally intended to allow Apple II users to run CP/M applications. The V2 Analog does a great job in this role, though it bears noting it can’t handle VGA output and Z80 emulation at the same time.
Project files are available
on Github
for the curious. The Apple II may be long out of production,
but it’s certainly not forgotten.
Video after the break. | 15 | 4 | [
{
"comment_id": "6664679",
"author": "David Kuder",
"timestamp": "2023-07-21T06:15:18",
"content": "I didn’t come up with it all on my own, my project is a fork of Mark’shttps://github.com/markadev/AppleII-VGAand is a constantly moving target. I both welcome and encourage others to revise the hardwa... | 1,760,372,228.388051 | ||
https://hackaday.com/2023/07/20/giant-3d-printer-can-print-life-sized-human-statues/ | Giant 3D Printer Can Print Life-Sized Human Statues | Lewin Day | [
"3d Printer hacks"
] | [
"3d printer",
"3d printing",
"statue"
] | We’ve seen a few makers 3D scan themselves, and use those to print their own action figures or statuettes. Some have gone so far as building life-sized statues composed of many 3D printed parts. [Ivan Miranda] is no regular maker though, and his custom 3D printer is big enough that
he can print himself a life-sized statue in one go.
The printer is a gargantuan thing, using an aluminium frame and a familiar Cartesian layout. It boasts a build volume of 1110 mm x 1110 mm x 2005 mm, making it more than big enough to print human-sized statues. Dogs, cats, and some great apes may be possible, too.
Many of the components are 3D printed, including the various braces and adapters that hold the frame together. The build uses NEMA 23 stepper motors, with Duet3D hardware running the show. Notably, it uses V-wheels for the Z-axis, as linear rails would be prohibitively expensive at the sizes required.
[Ivan] shows off the printer by having it produce a statue of his body at 1:1 scale. It’s not a perfect print, with some layer shifts and an awkward moments where the filament supply was interrupted. It took 108 hours in total, with 76 hours of that being actual print time, and is made up of 4375 layers. Despite its flaws, its an incredibly impressive way to demonstrate the capabilities of the machine.
Eager to build such a printer for yourself?
[Ivan] will sell you the design files for a reasonable fee.
[Ivan]’s giant printer was once
a large tabletop affair
; just look how far it’s come. He’s even come up with a system for using smaller printers to create
large-scale construction kits
, too. We can’t wait to see what mad project he comes up with next. Video after the break. | 30 | 9 | [
{
"comment_id": "6664655",
"author": "Vinny",
"timestamp": "2023-07-21T03:36:01",
"content": "Cartesian? Ivan used a CoreXY kinematics for this printer.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664692",
"author": "Hendrik",
"timestamp"... | 1,760,372,228.460741 | ||
https://hackaday.com/2023/07/20/diy-all-flash-nas-vs-commercial-hardware/ | DIY All-Flash NAS Vs. Commercial Hardware | Lewin Day | [
"Network Hacks"
] | [
"asustor",
"nas",
"raid",
"raspberry pi",
"rock 5",
"storage"
] | [Jeff Geerling] has tried building his own network-attached storage before, but found that the Raspberry Pi just wasn’t able to keep pace with his demands. He’s back with a new all-flash NAS build,
and put his new design to the test against proper store-bought gear.
His build is based around the ROCK 5 Model B, which is able to truck data around far faster than most other single-board computers. Internally, it can top 1 GB/sec without too much hassle. He decided to build a NAS rig using the board, putting it up against the turn-key ASUSTOR AS-T10G3.
Using OpenMediaVault to run the ROCK 5 as a NAS, [Jeff] was able to get decent performance out of the setup. With a 3-drive RAID 5 configuration, he recorded write and read speeds of 100 MB/sec and 200 MB/sec respectively, over a 2.5 Gbps network connection. There were also some spikes and curious performance wobbles. While speed was better than [Jeff]’s previous Raspberry Pi experiments, it wasn’t capable of double or triple the performance like he’d hoped. In comparison, the ASUSTOR solution was capable of much greater speeds. It topped out at 600 MB/sec write speeds, and 1.2 GB/sec on reads.
If you’re looking to build
a high-performance DIY NAS
, the ROCK 5 may be a better solution than most Raspberry Pi boards. However, if you want speed over all else, existing commercial NAS solutions really have the edge. Video after the break. | 37 | 10 | [
{
"comment_id": "6664439",
"author": "Raiden",
"timestamp": "2023-07-20T08:41:49",
"content": "“3-drive RAID 5 configuration” Haha lol lmao wtf. This entire post/video is pure nerd sniping.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664588",
"au... | 1,760,372,228.27391 | ||
https://hackaday.com/2023/07/19/vintage-digital-frequency-meter-teardown/ | Vintage Digital Frequency Meter Teardown | Al Williams | [
"Teardown"
] | [
"digital display",
"frequency counter",
"racal"
] | You think of digital displays as modern, but the idea isn’t that new. We had clocks, for example, with wheels and flip digits for years. The
Racal frequency counter
that [Thomas Scherrer] is playing with in the video below has columns of digits with lamps behind them. You just need the right plastic and ten lightbulbs per digit, and you are in business. Easy enough to accomplish in 1962.
Inside the box was surprising. The stack of PC boards looks more like a minicomputer than a piece of test gear. There were a few novel items inside, too, ranging from a glass-encapsulated crystal to an interesting method of selecting the line voltage.
The design seemed thoughtful. There was even a spot for spare bulbs for use when they inevitably blew out. The device has seen a few previous repairs, it seems. But with a little coaxing, it still does its job.
As high-tech as this might have been in 1962, the top range was supposed to be 300 kHz. Turns out, it was able to do quite a bit more than that. Overall, a great piece of engineering for its day and a seemingly rare instrument.
Of course, this
wasn’t the only frequency counter to use this kind of display
. The lights are
a bit more elegant than using meters
. | 4 | 4 | [
{
"comment_id": "6664425",
"author": "BrightBlueJim",
"timestamp": "2023-07-20T05:48:31",
"content": "Now I know what Don Lancaster was copying here:https://deramp.com/swtpc.com/PopularElectronics/Mar1969/PE_Mar_1969_pg33.jpg",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"c... | 1,760,372,228.149178 | ||
https://hackaday.com/2023/07/19/solenoid-keyboard-sounds-very-much-like-a-typewriter/ | Solenoid Keyboard Sounds Very Much Like A Typewriter | Lewin Day | [
"Peripherals Hacks"
] | [
"keyboard",
"mechanical keyboard",
"solenoid"
] | Mechanical keyboards are muchly adored things. For many of us, they take us back to that loud clickity-clack that was so common before consumer keyboards went to membrane switches. For others, it’s just for the pure joy of the finger-powered symphony.
The solenoid edition of the Red Herring keyboard from [Ming-Gih Lam] understands the beauty of this sound intimately.
It can be nearly silent if you so desire, or it can clack away with the best of them
(via Hackster.io).
It all comes down to the switches used in the design. [Lam] selected the Silent Alpacas from Durock, noted for their quiet operation, particularly when lubricated. You get just a faint slide-and-click noise from the keyboard under regular use.
The joy of the solenoid edition is in, you guessed it, the solenoid. It fires away with every keypress when enabled, creating a sound more akin to a real typewriter than any mechanical keyboard we’ve ever heard. Click-clack fans will love it, while those with sensitive ears will scream at any cube neighbours that dare to buy one and switch it on.
Files are available on Github
for the curious. We’ve seen some other great keyboards over the years, like this nifty split-board design. Video after the break. | 29 | 12 | [
{
"comment_id": "6664400",
"author": "mrhss",
"timestamp": "2023-07-20T02:28:24",
"content": "I’ve used Łucznik typewriter and it sounds nothing like that.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664403",
"author": "Timo",
"timestamp": "2023-07... | 1,760,372,228.338064 | ||
https://hackaday.com/2023/07/19/3d-printer-recognizes-third-party-build-plates-just-make-your-own-id-codes/ | 3D Printer Recognizes Third-Party Build Plates, Just Make Your Own ID Codes | Donald Papp | [
"3d Printer hacks"
] | [
"3d printing",
"AprilTag",
"Build platform",
"qr code",
"third party"
] | The Bambu X1C 3D printer is a machine known for its speed, and it has a number of useful features like automatic build platform recognition. Factory build platforms are marked with an identifier code, and thanks to [elumspe] it’s now possible to
make your own identifiers to stick onto third-party platforms
and have the printer recognize them as though they were factory offerings. There’s even a super handy 3D-printable alignment tool that ensures the identifier goes in the correct spot, which is a nice touch.
These codes aren’t DRM so much as they are used by the printer to automatically verify that the installed build plate matches the slicer settings before a job begins. Printing one and sticking it in the right place is an easy way to get third-party plates recognized the same as factory offerings.
The identifier codes aren’t DRM so much as they are a way for the printer to verify that the installed build platform matches the slicer settings before a print begins, and throw up a warning if it doesn’t. The printer is perfectly happy to use third-party build surfaces, but since they lack an identifier, the printer will throw a warning each time. One solution is to simply disable checking the build platform before a print, but for those who would prefer to have the printer see what it expects to see, printing a small 2D barcode to stick on is an easy way to do it.
We see these sometimes called
QR codes
, but they look more like
AprilTags
. Both are types of 2D barcode, but while QR codes can encode a variety of information types, AprilTags are simpler and usually represent identifiers. In this case, they’re an appropriate way to let a camera-enabled printer know what kind of build plate is installed.
AprilTags are common in computer vision applications, and even relatively modest hardware can detect and decode them almost in real time. AprilTags are convenient and easy to use,
as this gate access system
demonstrates. | 14 | 9 | [
{
"comment_id": "6664398",
"author": "Leandro Heck",
"timestamp": "2023-07-20T01:35:24",
"content": "Why would we need that? This is silly for me, I prefere to control the machine from the computer, remotely.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "66... | 1,760,372,228.515477 | ||
https://hackaday.com/2023/07/19/breaking-land-speed-records-with-an-rc-car/ | Breaking Land Speed Records With An RC Car | Lewin Day | [
"Misc Hacks",
"Transportation Hacks"
] | [
"jet car",
"R/C car",
"speed record"
] | Building and running a land speed record car is an expensive business that requires incredibly wealthy benefactors. Doing it on a smaller scale with a radio control car is still pricy, but more within the reach of the individual. [ProjectAir] has been working on just that,
and recently set out to break records with a car of his own design.
The car runs a Jetcat 220 engine capable of delivering 220 newtons of thrust, built into a custom aluminium chassis with streamlined bodywork. Early runs saw it reach 112 km/h, but the goal was to push it beyond 150 km/h to break the standing Guinness World Record.
With an RC event running on a local runway, [ProjectAir] had the venue and opportunity to make an attempt. It was tough going, with the car throwing off its nosecose in one run, while rough weather brought further struggles. Strong crosswinds played a role in a violent crash on the car’s fastest pass, which ripped the car apart and destroyed the engine. However, in the end, it had done enough to secure a record at over 152 km/h, even if its later faster efforts didn’t officially count.
It’s clear that the car has come a long way since [ProjectAir’s]
initial efforts in 2022
, and we can’t wait to see where the project goes next. Video after the break. | 23 | 6 | [
{
"comment_id": "6664357",
"author": "TG",
"timestamp": "2023-07-19T20:12:25",
"content": "Wait the speed record for RC cars is that low? Shucks give me a model rocket engine, smoke that easily. That design is just going to roll in a straight line anyway.",
"parent_id": null,
"depth": 1,
... | 1,760,372,228.573664 | ||
https://hackaday.com/2023/07/19/building-the-cheapest-midi-home-studio-from-1988/ | Building The Cheapest MIDI Home Studio From 1988 | Lewin Day | [
"Musical Hacks"
] | [
"1980's",
"atari st",
"ctrix",
"midi",
"music"
] | These days, there is a plethora of cheap hardware and software which you can use to make digital music. Back in the 1980s, though, this was still a nascent field, with new gear changing the game for musicians. In his latest video, [cTrix] puts together a guide to
building a budget MIDI home studio like it’s 1988.
The original Atari ST is the star of the show, which sold for around £300 back then. Unlike most contemporary computers, it came with MIDI ports built-in, and it quickly became a popular platform for music sequencing and controlling external synth hardware. It was often spotted in posh studios being used by big-time musicians, but [cTrix] wanted to look at how it was used by more humble users.
While the Atari ST could output some passable chiptunes, it was most powerful when paired with off-board gear. Industry magazines would readily talk up “DIY” setups worth thousands, but [cTrix] aimed for a budget in the low hundreds. In 1988, that might get you something like the 16-channel Yamaha PSS-580, which rocked full MIDI support and a ton of sounds and drumkits built in. It ran an OPL soundchip, and could play multiple instruments at once under MIDI control from software like Dr. T’s MIDI Recording Studio.
Of course, if you’ve ever played a keyboard like the PSS-580, you’ll have noted that the sound output can be more than a little chintzy. A cheap way to level up was to get yourself something like the Roland MT-32, which rocked a far higher-quality sound module. Everything from slap bass to solid electric pianos could be blasted out from the Roland, which also included a decent reverb unit, too. [cTrix] also dives into other budget heroes, like the rich and expansive Kawai K1 and the Yamaha EMT-10.
If you want to make music like it’s 1988 and you’re hunting for your first gold record, you’ll learn a lot here. We can’t wait for Part 2, that explores the next level of sophistication in this era. His previous lessons on
how to make 90s dance bangers on the Amiga
are a treat, too. | 7 | 7 | [
{
"comment_id": "6664352",
"author": "cbarn",
"timestamp": "2023-07-19T19:05:03",
"content": "I came a little later to computer-driven MIDI in 1991 … I’d already picked up a Yamaha V50 synth which supported MIDI and had a built-in sequencer, but lacked the resources to connect it to my frankenstein ... | 1,760,372,228.615354 | ||
https://hackaday.com/2023/07/19/hackaday-prize-2023-meet-the-assistive-tech-finalists/ | Hackaday Prize 2023: Meet The Assistive Tech Finalists | Tom Nardi | [
"contests",
"Hackaday Columns",
"Slider",
"The Hackaday Prize"
] | [
"2023 Hackaday Prize",
"assistive technology"
] | If you’re still toiling away at your entry for the Gearing Up Challenge of the
2023 Hackaday Prize
, don’t panic! No, you haven’t lost track of time — due to some technical difficulties we had to delay the final judging for the Assistive Tech Challenge that ended May 30th.
Today we’re pleased to announce that all the votes are in, and we’re ready to unveil the ten projects that our panel of judges felt best captured the spirit of this very important challenge. Each of these projects will take home $500 and move on to the final round of judging. There are few more noble pursuits than using your talents to help improve the lives of others, so although we could only pick ten finalists, we’d like to say a special thanks to everyone who entered this round.
Better Living Through Technology
For the Assistive Tech Challenge, we asked hackers to come up with ideas that could help those with disabilities live fuller and more independent lives. For those of us fortunate enough not to need any assistive technology in our day-to-day lives, it’s easy to imagine this means developing improved prosthetic limbs — but the reality is often considerably more mundane.
Consider the
PionEar project from Jan Říha.
Built around a low-power machine learning accelerator, this small battery powered device lights up to provide a visual indicator when it has identified the sound of a nearby siren. Placed on the dashboard of a car, it can help make sure deaf or hearing-impaired drivers are aware that an emergency vehicle is approaching so they can take appropriate action. Jan says he developed this device after talking to those in the hearing-impaired community and identifying this scenario as a problem that people were struggling with.
In a similar vein, the
“Portable Sound Visualization AR Device” from AIRPOCKET
uses an array of seven MEMS microphones on the front of the device to determine the direction that sounds are coming from. This data, when combined with a live video feed, can help the user identify the source of a sound that they might not otherwise be able to hear.
This augmented reality (AR) device can visually indicate the source of sounds in the user’s environment.
On the other hand, assistive tech doesn’t have to be limited to helping people with their daily activities. Indeed, it could be about enabling rare or even once-in-a-lifetime opportunities that might otherwise be impossible. Consider
Mercator Origins from Mark B Jones
, a dive computer designed from the ground up with inclusion in mind. This aquatic navigation system is intended to let blind or vision impaired individuals enjoy the freedom of movement and sense of weightlessness one experiences while diving underwater. Vibratory and audio alerts are used to help guide the diver between predetermined waypoints, while position and telemetry data is uploaded to a live dashboard so their process can be monitored from a distance — providing a feeling of independence while still maintaining safety.
Affordable Assistance
Instead of developing of new assistive technologies, other finalists focused their efforts on reducing the cost of what’s already available.
For example,
BrailleRAP by Stephane
is a DIY-friendly Braille “printer” that’s built from low-cost 3D printer components such as 8 mm rods, GT2 belts, and NEMA 17 stepper motors. The device, released under the CERN Open Hardware Licence v1.2, can be assembled for as little as $250 USD and is capable of embossing Braille text on standard paper, as well as thin sheets of metal or plastic. The desktop machine can therefore not only run off affordable educational or reading material wherever and whenever it might be needed, but can even be used to produce signage.
Similarly, the
“Electromechanical Refreshable Braille Display” developed by Vijay
seeks to smash the cost barrier that has kept Braille computer interfaces from becoming more widespread. By using an array of tiny electromagnets, each pin of the display can be raised and lowered independently with a minmum number of components.
On the Hackaday.io page for this project, Vijay explains these displays can now be produced affordably by the hobbyist thanks to the increased commercial availability of 0.5 mm NdFeB magnets as well as high-resolution 3D printers.
In both cases, a technique which has been around since the 1800s has been made more accessible and affordable thanks to the ingenuity of passionate individuals using commodity off-the-shelf hardware. They serve as important reminders that the evolutionary progress of modern technology means even the most time-honored of concepts can benefit from the occasional rethinking.
Assistive Tech Finalists
Powered Chair Smart Controller
BrailleRAP: DIY Braille Embosser
Helping H.A.N.D.S.
Electromechanical Braille Display
Speak To Me: A Button Box
Mercator Origins: Sat Nav for Divers
Portable Sound Visualization AR Device
PionEar: Safer Roads for Deaf Drivers
OHMni-Stick
Pill Dispenser Robot
Going Green
The Assistive Tech Challenge might be over, but the 2023 Hackaday Prize continues on. An announcement about the finalists of the Green Hacks Challenge is right around the corner, and of course we’ve still got a couple weeks before the Gearing Up Challenge ends on August 8th. After that, it’s time for the Save the World Wildcard, where things can get
really
interesting.
Of course, none of this would be possible without our incredible sponsors. Special thanks to Supplyframe and DigiKey for making the Hackaday Prize a reality, and giving these incredible ideas a chance to flourish.
The
Hackaday
Prize 2023
is Sponsored by: | 8 | 5 | [
{
"comment_id": "6664339",
"author": "TURFPTAx",
"timestamp": "2023-07-19T18:28:42",
"content": "Congrats to everyone!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664382",
"author": "the_3d6",
"timestamp": "2023-07-19T23:03:51",
"content": "It’... | 1,760,372,228.668085 | ||
https://hackaday.com/2023/07/20/physical-neural-network-can-be-trained-like-a-digital-one/ | Physical Neural Network Can Be Trained Like A Digital One | Donald Papp | [
"Science"
] | [
"compliant mechanism",
"flexure",
"lattice",
"mechanical",
"neural network"
] | Here’s an unusual concept:
a computer-guided mechanical neural network
(video, embedded below.) Why would one want a mechanical neural network? It’s essentially a tool to explore what it would take to make physical materials work in nonstandard ways. The main part is a lattice of interlinked mechanical components. When one applies a certain force in a certain direction on one end, it causes the lattice to deform in a non-intuitive way on the other end.
To make this happen, individual mechanical elements in the lattice need to have their compliance carefully tuned under the guidance of a computer system. The mechanisms shown can be adjusted on demand while force is applied and cameras monitor the results.
This feedback loop allows researchers to use the same techniques for training neural networks that are used in machine learning applications. Ultimately, a lattice can be configured in such a way that when side A is pressed like
this
, side B moves like
that
.
We’ve seen compliant structures that move in unexpected ways before, and they are always fascinating. One example is
this 3D-printed door latch
that translates a twisting motion into a linear one. Research into physical neural networks seems like it might open the door to more complex systems, or provide insights into metamaterial design.
You can watch the video below just under the page break, or if you prefer, skip the intro and
jump straight into How It Works at [2:32]
. | 11 | 6 | [
{
"comment_id": "6664615",
"author": "LordNothing",
"timestamp": "2023-07-20T23:14:08",
"content": "sometimes i feel like hack a day is just reading my youtube history.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664632",
"author": "scott_tx",
... | 1,760,372,228.719123 | ||
https://hackaday.com/2023/07/20/smart-powermeter-uses-e-paper-display/ | Smart Powermeter Uses E-Paper Display | Lewin Day | [
"home hacks"
] | [
"home",
"power meter",
"smart meter"
] | In most places around the world, electricity is getting ever more expensive. Cutting back on your usage is one of the easier ways to escape this pain. This
smart powermeter from [JGAguagdo]
may prove a useful tool to achieve that goal.
The project uses an ESP32-S2 as the brains of the operation. It’s capable of reading up to six current-transformer clamps for measuring current draw in AC devices. It also features an embedded BMP280 temperature and air pressure sensor. Live data is displayed on a 2.9-inch e-Paper display, making it clear and easy to read under normal lighting conditions. By default, it’s set up to display graphs of power usage both over the last 24 hours, and the last ten days. It can even be set up with the prevailing energy rates in your area to display a realistic figure for what you’ll pay for your daily usage.
It can even be set up to work with Home Assistant for more logging and control options. We can imagine that, with a little work, you could even do some fancy plotting of energy use versus temperature to determine the performance and cost of your home HVAC setup.
If you want one with a minimum of fuss, you can score one
on Tindie.
Alternatively, design files are available
on GitHub, too.
We’ve featured
some other great power meters
over the years, and if you’re cooking up your own smart designs, don’t hesitate to
let us know! | 17 | 8 | [
{
"comment_id": "6664590",
"author": "Chris Muncy",
"timestamp": "2023-07-20T20:44:18",
"content": "Waiting on Hash to comment to determine the validity of this project….",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664610",
"author": "ian 42",
"tim... | 1,760,372,228.985711 | ||
https://hackaday.com/2023/07/20/game-boy-style-camera-for-playdate/ | Game Boy-Style Camera For Playdate | Bryan Cockfield | [
"handhelds hacks"
] | [
"1-bit",
"camera",
"game boy camera",
"grayscale",
"monochrome",
"ov7670",
"Playdate",
"Teensy 4.1"
] | The Game Boy Camera, while perhaps not the most technologically advanced piece of equipment, left a huge mark on video game and electronics culture. The grayscale photographs are still highly prized, and there are an untold number of projects which interface with original hardware to download authentic Game Boy Camera pictures to modern computers. There are others that look to recreate the feel and style of these images,
and the latest comes to us on a Game Boy-like platform as well
, the Playdate.
[t0mg] is the creator of this project, utilizing a OV7670 camera module sending data to a Teensy 4.1 which interfaces with the Playdate via USB. The images recorded on the Playdate are 1-bit, slightly different than the 2-bit images the Game Boy Camera was capable of. The case of the camera also physically matches up well with the small console, using magnets to secure it to the device either in normal camera mode, in reverse for selfie mode, and can also support the console in “cover” mode as a way of storing the console to protect the screen. A companion application needs to run on the Playdate to get this all up and running, but with that and a battery plenty of retro-style images are ready to be captured.
All of the source for this project is available on the project’s GitHub page for anyone ready to experience some nostalgia or just experiment with a small camera like this. It’s a clean build that takes advantage of the Playdate’s open-source nature, through which we’ve seen the console
turned into a typewriter
and inspire other builds like
this one-off handheld with a crank-style controller
. | 0 | 0 | [] | 1,760,372,229.02341 | ||
https://hackaday.com/2023/07/20/tv-typewriter-remembered/ | TV Typewriter Remembered | Al Williams | [
"Hackaday Columns",
"History",
"Retrocomputing"
] | [
"Don Lancaster",
"TV Typewriter"
] | With the
recent passing of Don Lancaster
, I took a minute to reflect on how far things have come in a pretty short period of time. If you somehow acquired a computer in the early 1970s, it was probably some discarded DEC, HP, or Data General machine. A few people built their own, but that was a stout project with no microprocessor chips readily available. When machines like the
Mark-8
and, more famously, the
Altair
appeared, the number of people with a “home computer” swelled — relatively speaking — and it left a major problem: What kind of input/output device could you use?
An ad from Kilobaud offered you a ready-to-go, surely refurbished, ASR33 for $840
At work, you might have TeleType. Most of those were leased, and the price tag of a new one was somewhere around $1,000. Remember, too, that $1,000 in 1975 was a small fortune. Really lucky people had video terminals, but those were often well over $1,500, although Lear Siegler introduced one at the $1,000 price, and it became wildly successful. Snagging a used terminal was not very likely, and surplus TeleType equipment was likely of the 5-bit Baudot variety — not unusable, but not the terminal you really wanted.
A lot of the cost of a video terminal was the screen. Yet nearly everyone had a TV, and used TVs have always been fairly cheap, too. That’s where Don Lancaster came in. His TV Typewriter Cookbook was the bible for homebrew video displays. The design influenced the Apple 1 computer and spawned a successful kit for a company known as Southwest Technical Products. For around $300 or so, you could have a terminal that uses your TV for output.
The Good and The Bad
A 1975 ad for the SWTP “terminal system”
Of course, the biggest selling point was the cost. If you were a thrifty shopper or had a well-stocked junk box, you could probably spend less. It used your TV, which also helped keep the cost down.
But there were bad things, too. The TV Typewriter 2 showed 16 lines of 32 uppercase-only characters. Old TVs aren’t made to show digital data, and several things — notably the 4.5 MHz sound trap and the rejection of the color subcarrier at 3.58 MHz — limit how fast you can push dots into the TV. A premium TV might have a bandwidth of 3 MHz to 3.5 MHz, but practically, even that is a stretch. That’s why the resolution was so poor. Later versions offered different formats, including 32 lines by 64 characters, but good luck getting that into a normal TV set. There were ways to modify your TV for dedicated service as a monitor, but that required figuring out your specific brand of TV. Or, if you had the cash, you could get a dedicated monitor.
There were other minor issues. Southwest Technical Products turned the design into a kit and paid Don royalties. It wasn’t very capable by today’s standards. Still, it was the best thing in town at the time. Once people started building them, they also started hacking on them. The TV Typewriter matured into a usable terminal.
The Books
Don wrote several books and many magazine articles based on the TV typewriter design. Most people knew about it from a
comprehensive Radio Electronics article
. (The PDF download is actually the “guide” you had to send away for, but it includes the article and errata, too.) No need to download the schematics or the printed circuit artwork — there was nowhere to download them from in those days! Everything had to be printed.
The
TV Typewriter Cookbook
was a very popular book. (PDF) My copy is co-branded with Radio Shack and cost all of $3.95. The book covered the TVT-1, which used shift register memory, the TVT-2, which was essentially what you got from Southwest Technical Products as a kit, and the TVT-3, which was CMOS and could be wired to a microcontroller via DMA.
One of the output stages you could pick out of the cookbook
Back then, you couldn’t go “Google” for more information, so books had a bit more of a standard to live up to. Also, back then, the typical hacker didn’t know as much about computers as a school kid does today. So there’s a lot of information upfront about ASCII codes and what a UART is. In those days, a book like this had to explain flip flops and other things you’d pretty much assume people know today.
By Chapter 3, though, the discussion moves to memory. A TV typewriter that doesn’t use a microprocessor needs both RAM to store characters and ROM to map characters into dot patterns. Of course, you also need to know how an analog TV signal works. Even things like how to draw the cursor in hardware bear discussion.
The original typewriter was mostly made to put text on a TV screen and nothing more. Using it for input or controlling it via a computer requires a keyboard and a serial interface. That’s all in the book, too. The tail end of the book gives some notes on how you could do color display — a big deal back then.
Looking Back
Looking back, it seems pretty easy. Generate sync pulses and keep time for each line, pushing the signal one way or the other for each dot. Trivial with a microcontroller or an FPGA. But when Don showed us how to do this, those technologies were essentially unobtainable. The book is an amazing mix of analog, digital, and practical computing. Don’s name was synonymous with TV Typewriter for a generation.
Don wrote plenty of other things. Plenty. But none of them had the tremendous impact of the TV Typewriter Cookbook. The [Tech Time Traveller] has a good video that shows some of the vintage hardware and even provides a little context of a $1,000 TeleType when you probably made less than $8,000 a year. If you make it to the 20 minute mark, you can see the insides of a replica unit and dig those old-style PCBs.
You hear a lot of names when the conversation turns to the early days of personal computing. By our reckoning, you should hear Don Lancaster’s more often. We occasionally see things that were clearly influenced by
the TV Typewriter
. Especially for
retrocomputer projects
.
Banner image:
TV Typewriter
by Marcin Wichary, of Don’s own prototype from the
Computer History Museum | 23 | 12 | [
{
"comment_id": "6664549",
"author": "Tom Brusehaver",
"timestamp": "2023-07-20T17:09:50",
"content": "I’m bought school, 3 of us built one.We etched the double sided board, but didn’t have a way to plate through the holes. I soldered sockets on both sides.After we put in chips, many of the sockets ... | 1,760,372,229.104078 | ||
https://hackaday.com/2023/07/20/open-source-oled-nametag-is-full-of-features/ | Open Source OLED Nametag Is Full Of Features | Donald Papp | [
"Wearable Hacks"
] | [
"nametag",
"oled",
"open source",
"wireless"
] | Ever wanted a sweet OLED nametag with fancy features like daylight readability, automatic brightness adjustment, GIF animation support, all-day runtime, easy web interface, and more? [TobleMiner]’s
OLED Nametag
is the project you want to keep an eye on in that case.
It’s still an early prototype, but the feature list looks great and works with a variety of OLED modules that are easily available. The enclosure can be 3D printed, and while there is very little spare room inside the housing, [TobleMiner] has clearly made the most of all available space. Some PCB fab houses offer component placement these days, and the board is designed with exactly that in mind.
We’ve seen a
batteryless E-paper display make a serviceable nametag
in the past, and while those offer high contrast and wide viewing angles, they lack the sort of features this project is bursting at the seams with. Affordable access to good components and the ability to have high-quality PCBs made on demand has really raised the bar in terms of what a hacker project can work with in recent years, and we love to see it expressed in projects like this one. | 5 | 4 | [
{
"comment_id": "6664570",
"author": "rtyr5y45y45eyhe3h beyha",
"timestamp": "2023-07-20T19:00:11",
"content": "similar esp S3 screen but more key (I alvays wrote about more than 4 buttons on board) and power (I was alvays wrote about power on motherboard ;) )oled need more power therefore power mus... | 1,760,372,229.14653 | ||
https://hackaday.com/2023/07/20/pcie-for-hackers-an-m-2-card-journey/ | PCIe For Hackers: An M.2 Card Journey | Arya Voronova | [
"Engineering",
"Featured",
"Interest",
"Slider"
] | [
"adapters",
"engineering",
"PCIe"
] | I’ve designed a few M.2 adapters for my own and my friends’ use, and having found those designs online, people have asked me for custom-made adapters. One of these requests is quite specific – an adapter that adds one more PCIe link to an E-key M.2 slot, the kind of slot you will see used in laptops for WiFi cards.
See, the M.2 specification allows two separate PCIe links connected to the E-key slot; however, no WiFi cards use this apart from some really old WiGig-capable ones, and manufacturers have long given up on connecting a second link. Nevertheless, there are some cards like the
Google Coral M.2 E-key dual AI accelerator
and the recently announced
uSDR
, that do indeed require the second link – otherwise, only half of their capacity is available.
It’s not clear why both Google and WaveletSDR designed for a dual-link E-key socket, since those are a rare occurrence; for the Google card, there are
plenty of people complaining
that the board they bought just doesn’t fully work. In theory, all you need to do to help such a situation, is getting a second PCIe link from somewhere, then wiring it up to the socket – and a perfect way to do it is to get a PCIe switch chip. You will lose out on some bandwidth because the uplink PCIe connection of the switch can only go so fast; for things like this AI accelerator, it’s not much of a problem since the main point is to get the second device accessible. For the aforementioned SDR, it might turn out useless, or you might win some but lose some – can’t know until you try!
Building Our Own Card
That’s a hacker-friendly problem we can solve for fun and learning opportunities! With a small enough PCIe switch chip, we could make an M.2 card PCB that also has an M.2 socket, putting a PCIe switch in between to split the incoming PCIe 1x link into two outgoing 1x links.
What’s more, this problem has even been solved before. This exact adapter already has been made by someone online – however, it’s decidedly not open-source, and its creator has never started selling it, claiming lack of interest. The adapter we’re designing today, will be fully and properly open – anyone will be able to get their own adapter like this manufactured if they need one, learn from it, or remix it into something else.
On the PCIe switch side, I did mention a small, cheap and underexplored PCIe switch chip
last time
– the ASM1182e, which is able to create two PCIe x1 links out of one. It’s easily available on Aliexpress, used on many PCIe-splitting cards from China, it’s $6 after shipping, and it seems to be low-maintenance – small number of external components, standalone operation, simple wireup. Sadly, we just don’t have a datasheet for it that I could find – however, there’s
quite a bit of information
we can use to create our own boards, and I’ll show you how you might be able to design around chips even if you don’t have their datasheets.
Today, we’re solving a long-standing problem for a hardware niche, creating a M.2 adapter with three PCIe links in total, and reverse-engineering a PCIe switch chip with no datasheets available. I’d also like to make this board densely packed as a challenge, and show you what it takes, from a schematic page, to an assembled card.
Schematics More Open Than Expected
I’ll use one of my M.2 adapter designs as a base for this design – specifically, an A+E key to M-key adapter, letting you insert an SSD into a laptop’s WiFi card slot. That one’s a two-layer board because it could be, but today, two layers won’t do – this design will need four layers, as routing PCIe links properly and getting ground to everywhere would get way too intense otherwise! If you can reuse someone else’s design for your goals, absolutely do so – this one has tested symbols and footprints, meaning that there’s less variables for me to recheck! As a result, we don’t have to design an M.2 card from scratch.
The same goes for the reference schematic we can reverse-engineer the ASM1182 from – specifically, it’s from a mass-produced laptop. Today, we’re in luck – Clevo is one of the rare companies that has (or had) a tradition of publishing schematics for their laptops, likely helped by the fact that, unlike every other laptop manufacturer, they actually design their own mainboards. The only other laptop company I’ve seen publish schematics is Framework, whose mainboard is subcontracted (the norm in laptop space), and theirs is a partial one with all possibly-NDAed stuff removed. There’s no confidentiality markings of any kind on the schematic we’re looking for today – nevertheless, I’m not providing a link, but it’s undoubtedly the first result in your favourite search engine, especially if you look for
P75xZM_ESM.pdf
.
For the purposes of writing this article, it’s fortunate that this particular schematic does not appear to be problematic in any way. It’s apparently, quite uncommon for companies to issue takedown requests at schematic hosting sites, but these information-filled PDFs tend to be in a legal grey zone at best when it comes to distribution – you will see it argued that they fall under some form of intellectual property, and you might remember a “showing schematics on stream” dispute with Apple that thrust Louis Rossmann into the limelight. That said, if you personally ever use a schematic found online for reverse-engineering and design purposes, even if it has CONFIDENTIAL all over it, there’s no indication that you’re in any risk whatsoever – people have been doing that for ages with ThinkPads, Apple tech, and certainly random laptops here and there.
A Pinch Of Reverse-Engineering
What do we get out of this schematic? Well, the entire page 93 of the datasheet is dedicated to the ASM1182, with a complete, tested and working circuit that actually was shipped inside a laptop. It’s not a datasheet, sure, but it has a symbol with pin names and it’s fully wired up, so it’s more than enough for us to copy the circuit; it even lists descriptions for strap pins, which is rare to find in schematics. Also, it’s basically the only information about it that I could find online, and I sure did search!
There’s one more source of reference –
an open-source KiCad board
with an ASM1184, a
wonderful project by [will127534]
that lets you connect four NVMe SSDs to a Raspberry Pi CM4, and our hacker has reverse-engineered the ASM1184 just enough to make a fully functioning board. There’s a bit of extra info on power requirements, too – for instance, we see that all the same-voltage power pins are joined together and it doesn’t seem like we actually need multiple 3.3 V or 1.2 V power rails, even if the pin names are different. Connecting all pins together is something that the laptop schematic also does, but in a roundabout way, so it’s good to have reassurance.
One thing the schematic doesn’t list is the ASM1182’s QFN package type – i.e. pad pitch. However, our ASM1184 shows that it has pitch of 0.5 mm, which I’d expect to stay the same within the IC family, and KiCad has 48-pin QFN footprints with 0.5 mm pitch that seem to fit the bill perfectly. Just like the Pi Pico, there’s 3.3 V and 1.2 V pins all around the package – for 1.2 V, I initially decided to designate an inner plane, but 3.3 V could go around behind the pins, between them and the ground pad. I’ve opted to decrease the ground pad’s size – you can do that reasonably safely on a QFN, and my aim is to be able to both put 1.2 V vias there but also be able to pull an extra track. 4 mm ground pad size works perfectly for this, going down from the original 5.3 mm.
In the end, even though we don’t have a datasheet and the chip is reasonably complicated, we seem to have everything we could need to design a board! You won’t always get this lucky – that said, now you know that inaccessible datasheets aren’t the end.
The Crucial Choices
I got the ASM1182 symbol recreated in KiCad, and routing the schematic has been super simple – starting from the M.2 socket-to-socket adapter design I’ve had, I’ve added the ASM1182, wired up the signals of the three PCIe links, one to the card edge and two to the onboard socket, copied basically everything that the laptop schematic had, then started going through component footprint choices, estimating board component placement, and thinking through how the design could look.
As usual, 80% of a successfully routed PCB is proper component placement, 80% is good routing choices, and the remaining 80% are mostly clairvoyance – if you aren’t good at the last one, don’t worry, just be prepared to redesign parts of the board once or twice.
Here, component placement has been deceptively simple – I’ve taken an existing M.2 adapter as a base for outline, and assigned PCIe switch output links to M.2 socket’s link pins in a way that PCIe diffpair routing will mostly be short and sweet. After that, I’ve placed the PCIe switch on the bottom in a way that there’s plenty of space for PCIe diffpair routing on two more intense looking sides, and a bit of space on the other side for all of the PCIe switch configuration resistors. That said, it helps that I’ve been designing boards for a while and I have an eye for good component placement – if you’re starting out, you might not get it right the first time, so cut yourself some slack, ask people for a design review, and take note on what other people do when they design their own boards.
Such a board would more-or-less require a stencil for assembly – having a 0.5 mm pitch ASM1182 and an M.2 socket means that soldering iron assembly will be pretty effortful, and stenciling is fast in comparison. I’m going with 0402 components on this board – since I’m stenciling it anyway, there’s no good reason not to, and larger components would take way more space on the board. It’ll have to be dual-sided assembly, too – I’m not making a bet on having vertical space for any components under the inserted card, and having half of the space on the top layer occupied by the card edge and the socket puts us at a great disadvantage for single-sided placement. Usually, it isn’t as comfortable to stencil a board with components on both sides, but here I’d like to try and do it dual-sided anyway, and it should still be possible to stencil it despite any problems.
All in all, this is going to be a reasonably simple board to design and build, as long as we lay things out well! When routing such a board, you can start with the sensitive high-speed signals first while keeping the power rails and ground in mind, then route the power rails and ground while keeping low-importance signals in mind, and then, route the low-importance signals. Here, rotating the IC in one of the four directions solved most of the routing issues – putting both of the output PCIe links next to where they’re expected to be, and rotating the upstream link so that it can easily be routed from the card edge connector.
Capping The Power Consumption
Proper power is necessary for an IC, and doubly so for a fast PCIe switch. I have no datasheet to refer to when it comes to peak and idle consumption numbers, but in the laptop schematic diagram I have, it’s got its own 2 A linear regulator for the 1.2 V rail. I’ll personally go with a switching regulator, SY8089, a tried and true part from a well-known Chinese manufacturer. Since some of the pins are labelled as AVDD, I suspect some de-noising might be desired, but so far, both of the schematics we’ve seen, just join all power pins together with the non-analog-prefixed pins.
As a rule, you’ll want one capacitor per IC power pin – my usual tactic is copypasting a ton of capacitors in the schematic, placing them around the chip according to the power pins I see, and deleting the extra ones afterwards. I’ve seen people use both 1 uF and 100 nF caps for decoupling, but it’s not clear there’s much of a benefit to 1 uF over 100 nF here – I’m going to use 100 nF caps in most places because they’re slightly cheaper, and add an 1 uF or two in places where current might have a harder time flowing, further away from the power source trace-wise. Of course, these are not exact values – it’s more of a range, and a capacitor’s presence at a power input is often way more important than its very specific value as far as IC decoupling is concerned, plus, the resulting capacitance varies wildly anyway, dependent on voltage applied, temperature, and the capacitor’s manufacturing tolerances. These are the kind of decoupling capacitor rules that I and many other people follow for own designs – if you’d like to learn more about rules of thumb and actual reasoning for decoupling capacitor choice and placement,
there’s plenty
of
information out there
to
get you started
.
Still, these are important capacitors, meant to keep a digital chip at a stable brownout-free voltage with its highly spikey current consumption pattern, supplementing the current that flows through the path from the power supply – a path which tends to be long-winded and electrically thorny, high inductance and all. In the end, I’ve made extra sure that all power pins have capacitors somewhere nearby, and added two 1uF capacitors at further-away 3.3 V and 1.2 V areas. This is, again, more of a vibes-based placement, but it tends to work well. Every decoupling capacitor has to have a great path to both its power rail and GND – vias will work wonders for GND as we have two GND layers throughout the board, and for 3.3 V with 1.2 V, traces under the IC or even on internal layers should work alright too.
Layout Done, Diffpairs To Go
Now, we have at least 80% of this board completed – it’s time to route it. Remember the routing order? High-speed first, then power and ground, then low-importance signals. If the high-speed signals don’t work, the board might as well be toast, and it’s pretty hard to bodge after the fact. If the power distribution doesn’t work, the board won’t work well, but it’s easier to bodge that. And, if low-importance signals are mixed up, you can generally bodge them easily!
As such, we start our routing with diffpairs – next week, we will plug board parameters into a calculator to get trace width and spacing, draw the pairs as properly as the board space allows us, and tune their length a bit – with a video demonstration, too! | 22 | 7 | [
{
"comment_id": "6664510",
"author": "David Kuder",
"timestamp": "2023-07-20T14:14:56",
"content": "Missed the perfect opportunity to mention the flexibility in PCIe links for polarity and count-up / count-down lane ordering. (Hosts and devices are expected to negotiate the polarity and the lane ord... | 1,760,372,229.410209 | ||
https://hackaday.com/2023/07/20/pcjr-webserver-hits-2500-hours-uptime/ | PCjr WebServer Hits 2500 Hours Uptime | Adam Fabio | [
"Network Hacks",
"Retrocomputing"
] | [
"IBM PCjr",
"mTCP",
"peanut",
"retrocomputing",
"web server"
] | When [Mike] fired up his
PCjr webserver
back in March, he probably wasn’t expecting it to go viral. 2640 hours later, here we are! Not only has his machine run continuously for over 110 days, it also is surviving a global hug of death. All of this is thanks to some very special software.
We see lots of old machines here on Hackaday. We also see lots of minimal web servers. But we don’t see many that can run for thousands of hours, offering up to 8 simultaneous connections. Curious if jr is still up? Check
brutmanlabs.org
. The whole website is hosted on the 40-year-old machine. If you want to be a bit more kind, here’s a direct link to the text-only
status page
. While many of those hours were idle, currently lots of folks are hitting that little V20 CPU, so please give it a few seconds to respond.
The PCjr has a few upgrades — the aforementioned V20 CPU upgrade, a jrIDE sidecar, and a memory upgrade to 736 kB to name a few. Ethernet connectivity is via a Xircom parallel port adapter – which is circa 1993. The operating system is IBM PC DOS 5.02. One thing to note is that all these upgrades were possible back in the mid-1980’s when the PCjr was still current. [Mike] could run the system with an MFM hard drive, an ISA ethernet card (via an adapter), and use the original CRT monitor. Older DOS versions would work too — though partition sizes would be limited. The “modern” conveniences are just to keep from wearing out vintage hardware which is quickly becoming rare.
The real glue that holds this all together is [Mike’s] own software:
mTCP
. mTCP is a full set of tools for running internet applications on systems running MS-DOS or a compatible OS. We’ve seen
quite
a
few
mTCP
projects
over the
years
. [Mike] has worked tirelessly testing the software, ensuring that it is stable and reliable.
Software is never perfect though – one thing [Mike] didn’t implement is a log roller. Since he has logging turned on, the PCjr was slowly filling up its hard drive. Once the drive was full, mTCP would perform an orderly shutdown — but the uptime will be reset. [Mike] was able to go in and switch off logging with DOS’s DEBUG command. A live patch is not the way one would normally update software – but the fact that he was able to do it shows how deep [Mike’s] knowledge of the software goes.
[Mike] has even provided a live stream recording of the little PCjr handling requests from all over the globe. | 23 | 7 | [
{
"comment_id": "6664460",
"author": "Andrew",
"timestamp": "2023-07-20T11:18:14",
"content": "736 KB ought to be enough for anybody.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664480",
"author": "Jace",
"timestamp": "2023-07-20T12:29:03... | 1,760,372,229.340543 | ||
https://hackaday.com/2023/07/19/shake-rattle-roll-with-your-own-seismograph/ | Shake, Rattle, Roll, With Your Own Seismograph | Al Williams | [
"Arduino Hacks"
] | [
"mpu6050",
"seismograph"
] | We always love to see projects where you can build your own lab equipment so [CompactDIY’s] homemade
seismograph
caught our eye. The design uses an Arduino with an accelerometer and builds on one of their earlier projects. You can see a video of the device below.
The principle is simple. A hobby servo controls a pen and a stepper motor rolls paper, creating a makeshift strip recorder. Its software uses the Visuino system, which is a flowchart-like system, but it outputs Arduino code. Honestly, we would probably have just plotted the data on a PC, but there’s a certain charm to the strip recorder and the idea would work for other types of data recording projects, too. We thought if you rearranged the stepper motor and cut a paper disk out, you could also have a circular chart recorder easily, which wouldn’t need to friction transport the paper. A clock motor would make it even less dependent on software, too.
If this project interests you, try
a Raspberry shake
, which isn’t as delicious as it sounds. Or, keep an eye on
the entire globe
, if you prefer. | 5 | 3 | [
{
"comment_id": "6664334",
"author": "Dude",
"timestamp": "2023-07-19T18:14:58",
"content": "That “visuino” IDE looks terribly confusing for such a simple program.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664355",
"author": "Carl",
"ti... | 1,760,372,229.188747 | ||
https://hackaday.com/2023/07/19/smart-assistants-need-to-get-smarter/ | Smart Assistants Need To Get Smarter | Lewin Day | [
"Featured",
"Interest",
"Machine Learning",
"Original Art",
"Slider"
] | [
"alexa",
"bixby",
"google assistant",
"siri",
"voice assistant"
] | Science fiction has regularly portrayed smart computer assistants in a fanciful way. HAL from 2001: A Space Odyssey and J.A.R.V.I.S. from the contemporary
Iron Man
films are both great examples. They’re erudite, wise, and capable of doing just about any reasonable task that is asked of them, short of opening the pod bay doors.
Cut back to reality, and you’ll only be disappointed at how useless most voice assistants are. It’s been twelve long years since Siri burst onto the scene, with Alexa and Google Assistant following years later. Despite years on the market, their capabilities remain limited and uninspiring. It’s time for voice assistants to level up.
Is There Anything You
Can
Do?
Alexa allows users to easily purchase common household items via voice queries. It can readily search prior orders to help nail down the correct item. It’s a useful feature many rely on every day.
Amazon
The modern crop of voice assistants were, in many ways, a gamechanger when they first hit the market. They gave us our first real taste of interacting with computers in natural language. No more did we have to carefully craft exact commands for a simplistic voice recognition system. Instead, the idea was that we could speak almost normally, and the assistant would respond.
These days, voice assistants can handle a broad spectrum of tasks. You can use them to send a message, if you trust the voice recognition not to misrepresent your words, or you can add events to your calendar. You can do basic maths, play songs, and even switch your lights on and off – assuming you’ve knitted your smarthome together properly. Google and Amazon will let you make purchases, too, within certain parameters.
Fundamentally, though, these are all pretty basic party tricks. In all of these cases, the voice assistant is basically just saving the user a few mouseclicks, or saving them from pulling out their smartphone. The problem is a lack of higher intelligence and thinking that would make them truly useful, like a proper human assistant.
Ask Google Assistant to recommend you a good local restaurant, and you’ll be disappointed. Nine times out of ten, it will just type “restaurants near me” into Google and show you a list. A human assistant would know that you prefer steak and pub food to tapas, do the research, and come back to you accordingly. Big tech companies have all this data on most of us, or are certainly able to collect it, but they’re not employing it in this useful way.
The Flight Booking Test
Picture another scenario. You’re road tripping down the highway towards the airport, and you need to book a flight on the way. Our movie protagonists would surely bark a simple request at their AI assistant, who would respond with a series of convenient flights and prices. The appropriate bookings would then be handled with pre-stored payment information.
Try that with Google Assistant or Bixby today, and you’ll get nowhere. The former will simply dump you into a web search. The latter has a dedicated add-on for looking at flights, but it’s virtually unusable, failing to properly understand the right departing and arriving airports. Siri is similarly weak-minded, faltering when asked to look into available hotels online.
Yes, it’s that bad. You have a powerful smartphone sitting next to you in the car. It can understand what you say perfectly well, but it’s entirely powerless to execute even a simple request.
Contrast that to having a friend in the passenger seat, who could simply read you out a couple of flights and ask which you want to buy. It’s not that hard, but your voice assistant can’t do it.
A user asks Siri to book a hotel in Melbourne, Australia. When that fails, they decide to try Hong Kong instead, with the assistant faring little better. According to the user, at best, Siri would allow the user to make a phone call to the hotel in question. It took over ten attempts just to get that far. Booking directly was impossible.
It’s true that some innovation in this area has been made; Amazon integrated bookings with various airlines with Alexa years ago,
for example
. The problem is that piecemeal efforts don’t cut it. For such a feature to be useful, it has to work properly almost all of the time. Voice recognition technology has been the subject of mockery since the 1990s for its poor reliability. It’s a lesson that today’s voice assistants could learn from. It’s all well and good if a user can book flights with a certain airline in the continental US using their voice assistant. If it fails every time they’re in a different country, or wanting to fly a different airline, then the users will give up because the feature is functionally useless most of the time.
It bears noting that many of these situations are regionally variable, too. For example, if you’re in the US, you might find that flight and hotel bookings are more readily available to your smart assistant. Or, in Australia, you might note that the Google Assistant has a good handle on movie session times. But the regional variability and the inconsistency are the big problem that really spoils these features.
What’s The Fix?
Smart speakers are selling en masse, as are smartphones with voice assistants baked in. Building one with a real edge in capability could be a competitive advantage.
Amazon
These are just a few examples; you can probably think of thousands more. These fundamentally aren’t even technically difficult queries for an assistant to respond to. Not only that, but the required information is already available online. The problem comes down to two factors: integration, and authority.
Solving the integration problem requires a certain level of work on the back end. Companies would need to hook into existing databases and ensure their voice assistants can reliably parse and work with the data. This would require agreements and coordination with external companies in many cases, further complicating the issue.
As for authority, that’s something companies have struggled with since the dawn of smart assistants. Amazon, and more recently Google, will allow you to purchase items with your smart assistant. However, that has required protections to be put in place after awkward instances of
TV broadcasts inadvertently triggering home devices.
Similarly, there are risks for families, where young children might ask a helpful voice assistant to make purchases without prior parental authorization. However, in the case of a user speaking directly into their smartphone, it’s hard to imagine that voice fingerprinting or a simple device unlock wouldn’t be enough to authorize purchases.
Given a greater level of integration, and thus utility, is possible, why aren’t big tech companies rushing to unlock this functionality? The real key may be that it doesn’t serve them any real purpose. Tech companies could certainly put in the work to advance voice assistant capabilities, but it would take time and money. Nevermind the greater risks to reputation if the newly granted authority allowed smart assistants to do something truly inconvenient or awful for users. The voice assistants we already have
aren’t exactly money spinners as it is,
so it’s perhaps no surprise the difficult and expensive problems aren’t being solved.
Many will say that the problems listed here are edge cases, and that nobody uses their voice assistants this way. This author would counter that nobody does because it simply doesn’t work right now. The very spawning idea for this article came from a long drive, where it became apparent that I would have to spend half an hour clicking my way through various basic admin tasks because my voice assistant was completely incapable to help. Twelve years after the first one hit the market, it shouldn’t be that way.
If one voice assistant does begin to crest the integration mountain, things could change. If it performs reliably, it will also earn the authority to act that we don’t currently give to humble smart assistants today. At that point, you can expect rival tech companies to improve their own products to match. Until one company makes the first move, though, we’re out of luck. We’ll all be wishing we had a real assistant to help us out, rather than the impotent disembodied voices that currently live in our smartphones. | 81 | 25 | [
{
"comment_id": "6664281",
"author": "The2dcour",
"timestamp": "2023-07-19T14:19:32",
"content": "Voice assistants partnered with cameras should be able to tell me I left my keys, remote etc in the oven. Maybe with a smart oven refusing the oven to turn on because there is a foreign object inside.I’... | 1,760,372,229.635054 | ||
https://hackaday.com/2023/07/19/lighting-up-with-chemistry-1823-style/ | Lighting Up With Chemistry, 1823-Style | Dan Maloney | [
"chemistry hacks",
"History"
] | [
"catalyst",
"fire",
"hydrogen",
"lighter",
"platinum",
"sulfuric acid"
] | With our mass-produced butane lighters and matches made in the billions, fire is never more than a flick of the finger away these days. But starting a fire 200 years ago?
That’s a different story
.
One method we’d never heard of was Döbereiner’s lamp, an 1823 invention by German chemist J
ohann Wolfgang Döbereiner. At first glance, the device seems a little sketchy, what with a tank of sulfuric acid and a piece of zinc to create a stream of hydrogen gas ignited by a platinum catalyst. But as
[Marb’s Lab] shows with the recreation in the video below, while it’s not exactly as pocket-friendly as a Zippo, the device actually has some inherent safety features.
[Marb]’s version is built mainly from laboratory glassware, with a beaker of dilute sulfuric acid — “Add acid to water, like you ought-er!” — bathing a chunk of zinc on a fixed support. An inverted glass funnel acts as a gas collector, which feeds the hydrogen gas to a nozzle through a pinch valve. The hydrogen gas never mixes with oxygen — that would be bad — and the production of gas stops once the gas displaces the sulfuric acid below the level of the zinc pellet. It’s a clever self-limiting feature that probably contributed to the commercial success of the invention back in the day.
To produce a flame, Döbereiner originally used a platinum sponge, which catalyzed the reaction between hydrogen and oxygen in the air; the heat produced by the reaction was enough to ignite the mixture and produce an open flame. [Marb] couldn’t come up with enough of the precious metal, so instead harvested the catalyst from a lighter fluid-fueled hand warmer. The catalyst wasn’t quite enough to generate an open flame, but it glowed pretty brightly, and would be more than enough to start a fire.
Hats off to [Marb] for the great lesson is chemical ingenuity and history. We’ve seen
similar old-school catalytic lighters
before, too.
Thanks to [M. Bindhammer] for the tip. | 9 | 6 | [
{
"comment_id": "6664254",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-19T11:24:59",
"content": "Enlightening!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664286",
"author": "KC",
"timestamp": "2023-07-19T14:42:32",
"... | 1,760,372,229.453449 | ||
https://hackaday.com/2023/07/19/digital-microscope-with-an-on-screen-multimeter/ | Digital Microscope With An On-Screen Multimeter | Al Williams | [
"Tool Hacks"
] | [
"microscope",
"multimeter"
] | Some things go together, like chocolate and peanut butter. Others are more odd pairings, like bananas and bacon. We aren’t sure which category to put [IMSAI Guy]’s latest find in. He has a
microscope with a built-in digital multimeter
. You can see the video of the device in operation below.
The microscope itself is one of those unremarkable ten-inch LCD screens with some lights and a USB camera. But it also has jacks for test probes, and the display shows up in the corner of the screen. It is a normal enough digital meter except for the fact that its display is on the screen.
If you had to document test results, this might be just the ticket. If you are probing tiny little SMD parts under the scope, you may find it useful, too, so you don’t have to look away from what you are working on when you want to take a measurement. Although for that, you could probably just have a normal display in the bezel, and it would be just as useful.
At about $180 USD, it’s not exactly an impulse buy. We wonder if we’ll someday see an oscilloscope microscope. That might be something. These cheap microscopes are often just webcams with additional optics. You can do the same thing
with your phone
. If you don’t need the microscope, but you like the idea, can we interest you in
a heads-up meter
? | 18 | 8 | [
{
"comment_id": "6664223",
"author": "C",
"timestamp": "2023-07-19T08:08:15",
"content": "This opens an entire area of possibilities. I’m thinking you can create some type of AR to detect pin 1 of an IC and project the pin numbers on it. Or go crazy and use OCR to detect the IC type and also add the... | 1,760,372,229.508777 | ||
https://hackaday.com/2023/07/18/reverse-engineering-reveals-hidden-api-in-abandonware-trail-camera/ | Reverse Engineering Reveals Hidden API In Abandonware Trail Camera | Dan Maloney | [
"Reverse Engineering"
] | [
"api",
"ble",
"camera",
"game cam",
"nrf",
"PCAPDroid",
"reverse engineering",
"trail camera",
"wifi",
"wireshark"
] | It sometimes seems like there are two kinds of cheap hardware devices: those dependent on proprietary software that is no longer available and those that are equally dependent but haven’t been abandoned just quite yet. But rest assured, abandonment is always on the table, and until then, you get to deal with poorly written apps that often suffer from a crippling lack of essential functionality.
Such was the case for the wireless game camera that [Chris Jones] scored on the cheap, but rather than suffering with the original software, he decided to
reverse engineer the camera and turn it into something more useful
. The eBay description was promising — Bluetooth LE! WiFi! — but the reality proved less so. To save the batteries, WiFi is off by default and can only be turned on by connecting to the camera via BLE using a janky and crash-prone Android app.
[Chris]’ first step in reverse engineering the camera was to snoop into the BLE by capturing the Bluetooth packets to a file and running them through Wireshark. This revealed a write command with the text “BT_KEY_ON” — very promising. After verifying that this command turned on the camera’s access point, [Chris] got to work capturing WiFi packets using PCAPDroid and analyzing the results, again with Wireshark. Using every function available in the OEM app eventually revealed the full API on the camera, which gives file system control, access to individual images, and even putting the camera into live video mode.
With the keys to the kingdom, [Chris] was able to do a proof-of-concept bridge to the camera using an ESP-32, which wakes up the camera’s WiFi with a BLE tickle and interacts with its API. Future plans include a full-blown bridge based on a single-board computer to unlock the full potential of the camera.
Sure, it might be cheaper, in the long run, to just
build a trail cam from scratch
, but where’s the sport in that? | 12 | 7 | [
{
"comment_id": "6664222",
"author": "Sad",
"timestamp": "2023-07-19T08:06:12",
"content": "Wait a minute, there was no hidden API….Disappointeeeeeeeed!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6664228",
"author": "Gérald",
"timestamp": "2023-07-... | 1,760,372,229.68228 | ||
https://hackaday.com/2023/07/18/modern-software-brings-back-the-timex-datalink/ | Modern Software Brings Back The Timex Datalink | Tom Nardi | [
"Software Hacks",
"Wearable Hacks"
] | [
"smartwatch",
"Timex",
"Timex Datalink"
] | As much as some people on the Internet might like to think — no, Apple did not come up with the idea of the smart watch. Even if you ignore the calculator watches that we imagine a full 60% of Hackaday readers wore at one time or another in their lives, the Timex Datalink was already syncing with computers and pulling down the user’s list of appointments back in 1994 by decoding the pulses of light produced by a CRT monitor. Hey, it sounded like a good idea at the time.
Unfortunately, this idea hasn’t aged well. The technique doesn’t work on more modern displays, and naturally the companion software to generate the flashing patterns was written for Windows 3.1. But thanks to the
reverse engineering efforts of [Synthead]
, you can now sync any version of the Timex Datalink to your computer using nothing more complex than the onboard LED of the Teensy LC or Raspberry Pi Pico.
There’s actually several different projects working together to make this happen. In place of a CRT, there was an official “Timex Datalink Notebook Adapter” back in the day that was designed to be used on laptops and featured a single blinking LED. That’s what
[Synthead] has recreated with timex-datalink-arduino
, allowing a microcontroller to stand in for this gadget and featuring 100% backwards compatibility with the original Datalink software.
Appointment data is loaded from a text file.
But since you’re probably not rocking Windows 3.1 anymore, having access to that software is far from a given. That’s why
[Synthead] also created timex_datalink_client
, which is a Ruby library that lets you generate data fit for upload into the Timex Datalink. At the time of this writing there doesn’t seem to be a friendly user interface (graphical or otherwise) for this software, but it’s easy enough to feed data into it using plain-text configuration files.
Helpfully [Synthead] provides screenshots of information loaded into the original software, followed by a config file example that accomplishes the same thing. It looks like writing some glue code that pulls your schedule from whatever service you fancy and formats it for the Datalink client should be relatively simple.
We’ve previously seen projects that
got the Timex Datalink synced without the need for a CRT
, but they still required the original software. To our knowledge, this is the first complete implementation of the Datalink protocol that doesn’t rely on any original hardware or software. Expect eBay prices to go up accordingly. | 27 | 11 | [
{
"comment_id": "6664194",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-19T02:38:12",
"content": "My wife bought me a Datalink around the year 2000.Each time I changed the battery the rubber o-ring that sealed the back stretched a little.The watch died one sweaty summer day... | 1,760,372,229.760496 | ||
https://hackaday.com/2023/07/18/sniffing-passwords-rickrolling-toothbrushes/ | Sniffing Passwords, Rickrolling Toothbrushes | Elliot Williams | [
"classic hacks",
"Reverse Engineering"
] | [
"crc",
"passwords",
"reverse engineering",
"security",
"sniffing",
"toothbrush"
] | If you could
dump the flash from your smart toothbrush and reverse engineer it
, enabling you to play whatever you wanted on the vibrating motor, what would you do? Of course there’s no question:
you’d never give up, or let down
. Or at least that’s what [Aaron Christophel] did. (Videos, embedded below.)
But that’s just the victory lap. The race began
with previous work
by [Cyrill Künzi], who figured out that the NFC chip inside was used for a run-time counter, and managed to reset it by sniffing the password with an SDR as it was being transmitted. A great hack to be sure, but it only works for people with their own SDR setup.
With the goal of popularizing toothbrush-head-NFC-hacking, [Aaron] busted open the toothbrush itself, found the debug pins, dumped the flash, and got to reverse engineering. A pass through Ghidra got him to where the toothbrush reads the NFC tag ID from the toothbrush head. But how does it get from the ID to the password? It turns out that it runs a CRC on a device UID from the NFC tag itself and also a manufacturer’s string found in the NFC memory, and scramble-combines the two CRC values.
Sounds complicated, but the NFC UID can be read with a cellphone app, and the manufacturer’s string is also printed right on the toothbrush head itself for your convenience. Armed with these two numbers, you can calculate the password, and convince your toothbrush head that it’s brand new, all from the comfort of your smartphone! Isn’t technology grand?
We’re left guessing a little bit about the Rickroll hack, but we’d guess that once [Aaron] had the debug pins on the toothbrush’s microcontroller, he just couldn’t resist writing and flashing in a custom firmware. Talk about dedication.
[Aaron] has been doing extensive work on e-paper displays, but his
recent work on the Sumup payment terminal
is a sweet look at hacking into higher security devices with acupuncture needles. | 14 | 6 | [
{
"comment_id": "6664130",
"author": "Jan",
"timestamp": "2023-07-18T20:29:12",
"content": "Being employed by P&G i would say that is not a toothbrush I would put in my mouth.And the ion brushes have ips led displays among other thing and way more fun to hack and play around with.",
"parent_id":... | 1,760,372,229.813612 | ||
https://hackaday.com/2023/07/18/conductive-gel-has-potential/ | Conductive Gel Has Potential | Bryan Cockfield | [
"chemistry hacks"
] | [
"conductive",
"gel",
"mineral oil",
"nixie tube",
"solution",
"xanthan gum"
] | There are some technologies first imagined in the
Star Trek
universe have already come to exist in the modern day. Communicators, tablet computers, and computer voice recognition are nearly as good as seen in the future, and other things like replicators and universal translators are well on their way.
Star Trek: Voyager
introduced a somewhat ignored piece of futuristic technology, the bio-neural gel pack. Supposedly, the use of an organic gel improved the computer processing power on the starship. This wasn’t explored too much on the series, but [Tom] is nonetheless taking the first steps to recreating this futuristic technology
by building circuitry using conductive gel
.
[Tom]’s circuitry relies on the fact that salts in a solution can conduct electricity, so in theory filling a pipe or tube with a saline solution should function similarly to a wire. He’s also using xanthan gum to increase viscosity. While the gel mixture doesn’t have quite the conductivity of copper, with a slight increase in the supplied voltage to the circuit it’s easily able to be used to light LEDs. Unlike copper, however, these conductive gel-filled tubes have some unique properties. For example, filling a portion of the tube with conductive gel and the rest with non-conductive mineral oil and pushing and pulling the mixture through the tube allows the gel to move around and engage various parts of a circuit in a way that a simple copper wire wouldn’t be able to do.
In this build specifically, [Tom] is using a long tube with a number of leads inserted into it, each of which correspond to a number on a nixie tube. By moving the conductive gel, surrounded by mineral oil, back and forth through the tube at precise intervals each of the numbers on the nixie tube can be selected for. It’s not yet quite as good as the computer imagined in
Voyager
but it’s an interesting concept nonetheless, not unlike
this working replica of a communicator badge
. | 24 | 7 | [
{
"comment_id": "6664084",
"author": "hartl",
"timestamp": "2023-07-18T18:39:18",
"content": "One question remains: How many switching cycles at room temperature will it endure before gel and oil emulsify?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "66640... | 1,760,372,229.874884 | ||
https://hackaday.com/2023/07/18/pcmcia-flash-card-gives-up-its-secrets-thanks-to-retro-gear/ | PCMCIA Flash Card Gives Up Its Secrets Thanks To Retro Gear | Dan Maloney | [
"Retrocomputing"
] | [
"ftp",
"gis",
"gps",
"libretto",
"PCMCIA",
"retrocomputer",
"Toshiba",
"Windows 98"
] | There are two ways to recover data from an obsolete storage medium. One way is to pull out all the tools in the hacker’s kit — with logic analyzers, oscilloscopes, and bit-banged software in a desperate attempt to reverse engineer the original protocol. The other way is to have a really, really deep junk bin that just happens to contain exactly the right pieces that would have been used decades ago.
For
recovering data from a 25-year-old PCMCIA memory card
, [Dave] from
Vintage Apparatus
chose the latter method. But to be fair, characterizing the stash of gear he had to select from as a “junk bin” is pretty insulting. It’s more like a museum of retro technology, which just so happened to hold
Toshiba Libretto
, a subnotebook computer hailing from the late 1990s. The machine sports a pair of PCMCIA slots and was just the thing to read the data from the old 32 MB SanDisk flash card, which once lived in a backpack-mounted GPS system for surveyors.
If this hack sounds as easy as plugging things into an old computer, you’d be right — if you just happen to have a stack of floppies containing the Windows 98 drivers for said things. So [Dave]’s task became a game of finding the right combination of cards that already had the drivers installed and would provide the connectivity needed to get the data off the flash card. Between a suspiciously crunchy-sounding floppy drive and an Ethernet card dongle badly in need of some contact cleaner, cobbling together the right hardware was a bit of a chore. After that, a lot of the hack was [Dave] just remembering how we used to do things back in the day, with the eventual solution being transferring over the files to an FTP server on a Raspberry Pi.
The video below tells the whole saga, but the real treat might just be the
Vintage Apparatus
collection of gear. Incidentally, we really like [Dave]’s idea for storing associated bits and bobs. | 27 | 16 | [
{
"comment_id": "6664054",
"author": "zoobab",
"timestamp": "2023-07-18T17:03:24",
"content": "I have one of those pcmcia SRAM card 2mb that i used to flash usr2450 routers with linuxap back in 2000, in the pre-openwrt days. One of the few distro to support it for the Demolinux livecd.",
"parent... | 1,760,372,230.016974 | ||
https://hackaday.com/2023/07/18/crab-shells-massively-improve-zinc-ion-batteries/ | Crab Shells Massively Improve Zinc-Ion Batteries | Lewin Day | [
"Current Events",
"Engineering",
"Original Art",
"Science",
"Slider"
] | [
"battery",
"battery tech",
"battery technology",
"research",
"zinc battery",
"zinc-ion battery"
] | In the fast-moving world of battery research, scientists are constantly on the lookout for innovative materials with the right properties to help improve energy storage. Meanwhile, batteries are in greater demand than ever as production of EVs and renewable energy projects ramp up to new heights.
In the hunt for new and better battery materials, scientists found an unexpected hero: crab shells.
Researchers at the University of Maryland have uncovered a remarkable breakthrough by exploring their use in battery production.
Rock Lobster
Crab shells contain chitosan, a carbohydrate material that is proving useful as a component in battery electrolyte. Credit:
John Gibbons
The quest for advanced energy storage materials has been a driving force behind numerous research endeavors worldwide. Traditional lithium-ion batteries have come to dominate in many fields. They power the vast majority of our personal electronic devices, as well as
electric vehicles
and
large grid storage projects
. While effective, face limitations in terms of cost, finite resource availability, and
safety concerns
. As a result, scientists have been exploring alternative battery technologies that offer improved performance, longevity, and scalability.
One such alternative gaining traction is zinc-ion batteries, which have shown promise due to their lower cost and abundance of raw materials. They have comparable performance in some respects, though do have lower power output which makes them suited for less-demanding storage roles. Thus far, their practicality has been hindered by a limited lifespan, hampering their viability. However, the innovative use of material from crab shells could change all that.
The material in question is chitosan—a substance found in abundance within crab and lobster shells. Scientists believe it could be used as a key ingredient in zinc-ion batteries. It’s an unconventional approach that showcases the versatility of natural resources, and could hold the potential to revolutionize the energy storage landscape.
The researchers at the University of Maryland sought to harness the properties of chitosan—a carbohydrate found abundantly in the hard outer skeletons of shellfish—for energy storage applications. By incorporating chitosan into the gel membrane of zinc-ion batteries, they achieved unprecedented results, according to
the research paper
. The batteries exhibited an impressive year-long lifespan in cycle testing, retaining 70% of their initial capacity—an astonishing improvement compared to existing zinc-ion battery technology.
The chitosan-based electrolyte causes the deposition of neat zinc platelets on the anode of a zinc-ion battery, rather than harmful spiked dendrites. Credit:
research paper
Usually, zinc-ion batteries suffer from zinc metal dendrites, which disable the battery after a relatively low number of cycles. This is largely down to the aqueous electrolytes typically used, which allows zinc to form dendritic spikes due to inhomogenous deposition of the metal on the anode over time.
When chitosan is used as part of the electrolyte of the battery, it brings several benefits to the table. It offers strong conductivity and good mechanical strength, and massively improves the cycle stability of zinc-ion batteries. It achieves this by changing the way zinc is deposited on the anode surface. When using the chitosan-based electrolyte, the zinc forms hexagonal platelets that sit neatly in parallel on the anode, instead of forming large dendrites that pierce the battery separator. As a further benefit, the chitosan electrolyte is able to achieve this without unduly compromising the conductivity of the battery. In testing, the batteries were shown to still be stable after over 400 cycles at a 2C discharge rate, while also demonstrating the ability to charge at up to 20C.
Furthermore, the inclusion of chitosan mitigates safety concerns often associated with lithium-ion batteries. The use of this non-flammable electrolyte reduces the risk of explosions and fire hazards, paving the way for safer and more sustainable energy storage solutions. A further bonus is that zinc-ion batteries could be fabricated in a sustainable and biodegradable manner using chitosan-based electrolyte.
The Glory of Byproducts
Historically, crab shells are discarded from the crab meat production process, and have found limited utility in applications such as fertilizer and animal feed. However, the emergence of chitosan-based batteries presents an exciting opportunity to transform these shells into a valuable resource for renewable energy storage. Mass chitosan production could yet become a serious side-hustle for big players in the seafood industry.
However, while the research has attracted considerable attention, several challenges remain on the path to commercialization. The process of refining and scaling up the production of chitosan-based batteries requires further development, investment, and collaboration with industry partners.
The unexpected alliance between battery research and crab shells exemplifies the remarkable potential of natural materials. By leveraging chitosan from discarded crab shells, scientists have achieved breakthroughs in energy storage that could transform the renewable energy landscape. As the world continues to hunt for new battery solutions, the humble crab could be our latest ally in this area. | 32 | 10 | [
{
"comment_id": "6664035",
"author": "BW",
"timestamp": "2023-07-18T15:36:45",
"content": "A non-vegan battery is a bizarre concept (yes, I know early galvanic experiments were done with frogs’ legs)",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664039",
... | 1,760,372,229.957027 | ||
https://hackaday.com/2023/07/18/tesla-door-phone-decoded-not-that-tesla/ | Tesla Door Phone Decoded (Not That Tesla) | Al Williams | [
"Reverse Engineering"
] | [
"pwm",
"reverse engineering"
] | [Danman] has digital door phones manufactured by Tesla — or at least,
a
Tesla, as they’re not to be confused with the carmaker, though. The problem is if someone comes to the door when no one’s home, there’s no remote indicator. The answer?
Reverse engineer the protocol
and fix it.
A quick dump on a storage scope showed the data clearly, but it wasn’t obvious what protocol it was using. After a little analysis, it proved the datastream used 4 PWM pulses as symbols with three symbols: one, zero, and stuffing sequence.
Once you can read the bits, it is easy to determine that each frame consists of a 16-bit destination and source address, along with a command byte and a checksum byte. Each station can have an ID from 000 to 999 although you can only dial up to number 323. Some nodes are special, and there are ways to address particular units.
Connecting to the hardware took a transformer for isolation. Honestly, unless you have this exact hardware, this isn’t likely to be something you can directly use. However, it is a great example of how you can figure out a specialized device and bend it to your will.
We love
reverse engineering projects
. In some cases, it is easier if you have
a CT scan
. | 6 | 2 | [
{
"comment_id": "6664145",
"author": "IIVQ",
"timestamp": "2023-07-18T21:47:49",
"content": "I have read many articles about intercom systems. They always seem to have very weird protocols, with leads to ultimate vendor lock-in. My 90-apt building’s entire intercom system including cabling had to be... | 1,760,372,230.190724 | ||
https://hackaday.com/2023/07/18/do-you-have-an-old-hitachi-computer-you-might-just-have-beos-without-realizing-it/ | Do You Have An Old Hitachi Computer? You Might Just Have BeOS Without Realizing It | Jenny List | [
"Retrocomputing"
] | [
"1990s",
"BeOS",
"hitachi"
] | There was a moment in the years spanning the move from 16-bit platforms to 32-bit, during which it looked for a moment as though there might be a few new operating system contenders making a mark on the desktop.
Does this PC look familiar to you?
This was the period that gave rise to the “Year of Linux on the desktop” meme as the open source contender just wasn’t ready for the general public, but we all know what happened. The various commercial contenders slipped by the wayside or survived by the skin of their teeth as enthusiast or niche platforms, while Microsoft Windows steamrollered all before it except for the walled garden of Apple users.
One of the players was BeOS, a powerful multimedia OS that might have had a chance if it could have persuaded OEMs to ship it on some PCs, but in that endeavour it had no luck. Or so everyone thought, but [Thom Holwerda] reports on the fascinating tale of
a PC that shipped with BeOS, but not in a way anyone could easily use
.
It seems that even being seen to talk to the folks from Be was enough to ensure an OEM received a visit from Microsoft
goons
sales representatives so even though the rival OS was offered for free it received no PC takers. This was the received opinion, but it turns out that the one manufacturer which did include BeOS was Hitachi, in Japan. Their Flora Prius PC was a Pentium II equipped white box typical of late-90s multimedia hardware, and though it booted into Windows it also had a BeOS installation on board that probably very few owners would have even realised existed. It seems
Hitachi did the deal with Be
but didn’t install the required bootloader to use the Be partition. A Flora Prius owner could run the software if they were prepared to follow some instructions on the Be website and download a floppy image, but it seems very few did so.
All this leads to a fascinating challenge for today’s BeOS enthusiasts, to locate a surviving Flora Prius PC if any can still be found with an intact BeOS partition, and activate the only factory PC BeOS install. We know we have readers in Japan who almost certainly have an eye for an old computer, can any of you help them in this quest?
We’ve touched on BeOS in the past
on its own BeBox platform and the elusive Sony eVilla internet appliance. | 43 | 11 | [
{
"comment_id": "6663975",
"author": "Mathias",
"timestamp": "2023-07-18T11:20:20",
"content": "I actually tried BeOS at some point. It was amazing – at least for the few things I could do. I remember on Windows (95?) I couldn’t have MP3s playing on Winamp and scroll some files in the explorer windo... | 1,760,372,230.10349 | ||
https://hackaday.com/2023/07/18/practical-inductors-in-ltspice/ | Practical Inductors In LTSpice | Al Williams | [
"Parts",
"Software Hacks"
] | [
"inductor",
"LTSpice",
"SPICE"
] | LTSpice and the underlying Spice engine does a great job of simulating ideal components. But it is also capable — if you know how — of handling models of real-world devices. Inductors, for example, are one of the most imperfect components. Their constituent wire has resistance, and there is parasitic capacitance between the windings. If there is a core, it also will have many imperfections and losses. [Sam Ben-Yaakov] has a lecture about modeling real inductors in LTSpice, and he
covers how you can capture some of these imperfections in the video below.
There is a bit of math in the presentation, but we liked that it relates back to datasheets for actual components. Being able to understand what the parameters on a datasheet mean is crucial, and if you ever wondered what some of these entries mean, you’ll get a lot from this video.
The main feature of the model is the flux equation. The tanh (hyperbolic tangent) function is similar to the curve you want for the flux equation, so it plays a major part. Of course, there are other parts of the inductor you may have to model, too, but this is one of the most difficult parts.
You can also model
transformers
using LTSpice. You can also create
custom components
. | 8 | 4 | [
{
"comment_id": "6663960",
"author": "IIVQ",
"timestamp": "2023-07-18T08:59:26",
"content": "So an inductor has flux and has capacitance. What happens at 88MPH?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6663971",
"author": "Alan",
"times... | 1,760,372,230.149275 | ||
https://hackaday.com/2023/07/17/building-a-minipet-is-better-with-friends/ | Building A MiniPET Is Better With Friends | Adam Fabio | [
"Retrocomputing"
] | [
"6502 processor",
"Chuck Peddle",
"MOS",
"pet",
"retrocomputing",
"Taylor and Amy",
"vintage"
] | [Taylor and Amy] love taking on retro computer projects. This week they’re
building a MiniPET
from Tynemouth and The Future is 8 Bit. It’s a pretty awesome kit which sadly isn’t available anymore. Taylor bought one of the last ones as part of a charity sale at the 2023
Vintage Computer Festival Southwest
.
If you haven’t seen
their YouTube channel yet
, check it out! The two have been best friends since 1984. Their channel has just the right mix of education and comedy, with pacing fast enough to keep things interesting. It’s really refreshing to see two people enjoying a project together.
The MiniPET is of course a reproduction of the hardware in the
Commodore PET
, the machine which predated the VIC-20 and of course the Commodore 64. The kit starts with installing a few discrete parts — resistors, capacitors, and diodes. Then come the IC sockets. [Taylor and Amy] ran into a bit of trouble when it came time to install the chips. While installing the 40-pin 65C21
Peripheral Interface Adapter (PIA)
, one pin bent under the socket. [Taylor] popped the chip back out, and replaced it — which resulted in 3 bent pins!
Anyone who’s installed new DIP parts has been through this. The pins are always bent out a bit from the factory. The old “Bend it in using a table” method usually works — but if you want perfect pins, try a pin straightener. These versatile tools
can even be 3D printed
.
Once the pin problems are solved, it’s time to power up the kit and see if it will work. That’s when we get to see that magic moment when a project first comes to life. Check out the video – you’ll see what we mean. | 4 | 3 | [
{
"comment_id": "6663943",
"author": "elwing",
"timestamp": "2023-07-18T06:06:41",
"content": "Assuming you used a pin straightener (ours had a metal rails and ball bearing on the sides and you just slid chip through it), the major risk during insertion is that you tend to insert one row before the ... | 1,760,372,230.319848 | ||
https://hackaday.com/2023/07/17/this-risc-v-cpu-games-in-rust-from-inside-the-game/ | This RISC-V CPU Games In Rust From Inside The Game | Jonathan Bennett | [
"computer hacks",
"Games",
"News"
] | [
"nand2tetris",
"RISC-V",
"Terraria"
] | [Xander Naumenko] has created something truly impressive — a
working RISC-V CPU completely contained in a Terraria world
. And then for added fun, he wrote the game of pong, playable in real time, from within the game of Terraria. It’s all based on the in-game wiring system, combined with a bit of a hack that uses the faulty lamp mechanic to create a very odd AND gate. In Terraria, the existing logic gates have timing issues that make them a no-go for complicated projects like this one. The faulty lamp is intended to do randomized outputs, by stacking multiple inputs to get a weighted output when a clock signal is applied. The hack is to simply give this device a single input, turning it into a clocked IF gate. Two of them together in series makes a clocked AND gate, and two in parallel make a clocked OR gate.
Why would [Xander] embark on this legendary endeavor? Apparently after over eight thousand hours clocked in game, one gets a bored of killing slimes and building NPC houses. And playing with the game’s wiring system turned on a metaphorical lightbulb, that the system could be used to build interesting systems. A prototype CPU, with a completely custom instruction set came next, and was powerful enough to compute Fibonacci. But that obviously wasn’t enough. Come back after the break for the rest of the story and the impressive video demonstration.
Surprisingly, playing three months playing Terraria has
improved my career prospects
.
After this prototype worked, the obvious next step was to use the RISC-V specification to build a rv32i processor. And a display. Because the CPU must be able to game. The full version has a problem, though. It’s huge, and Terraria really, really isn’t designed for wiring projects this complicated. So naturally, [Xander] just rolled up his sleeves and re-wrote the Terraria wiring system, in the form of the WireHead mod. By a series of tricks, like looking at wires as a whole, instead of each individual tile, he managed to make the cpu run at a blistering 5 MHz. Fast enough for pong, but slow enough that Conway’s Game of Life has to be watched in fast forward.
The whole thing is very reminiscent of
the Nand2Tetris course
, as well as the equally impressive
Minecraft computers we’ve covered before
. And there’s even more fun to come for Computerraria, as a low-res Doom clone is being worked on, as well as video playback for the well known Bad Apple. It’s all
open source
, and ridiculously well put together, so go take a look! | 14 | 7 | [
{
"comment_id": "6663921",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-07-18T03:36:05",
"content": "I fear that if one iterates further in this operation, a spontaneous recursion will result in taking us either forward or backward to The Singularity.",
"parent_id": null,
... | 1,760,372,230.413574 | ||
https://hackaday.com/2023/07/17/glasnost-is-a-computer-that-makes-transparency-a-priority/ | GLASNOST Is A Computer That Makes Transparency A Priority | Bryan Cockfield | [
"computer hacks"
] | [
"computer",
"core memory",
"gate",
"glasnost",
"logic",
"soviet",
"vacuum tube"
] | We live in a world where most of us take the transistor for granted. Within arm’s length of most people reading this, there are likely over ten billion of them sending electrons in every direction. But the transistor was not the first technology to come around to make the computer a possibility, but if you go to the lengths of building something with an alternative,
like this vacuum tube computer
, you may appreciate them just a tiny bit more.
This vacuum tube computer is called GLASNOST, which according to its creator [Paul] means “glass, no semiconductors” with the idea that the working parts of the computer (besides the passive components) are transparent glass tubes, unlike their opaque silicon-based alternatives. It boasts a graphical display on an oscilloscope, 4096 words of memory, and a custom four-bit architecture based only on NOT, NOR, and OR gates which are simpler to create with the bulky tubes.
The project is still a work in progress but already [Paul] has the core memory figured out and the computer modeled in a logic simulator. The next steps are currently being worked through which includes getting the logic gates to function in the real world. We eagerly await the next steps of this novel computer and, if you want to see one that was built recently and not in the distant past of the 1950s, take a look at
the Electron Tube New Automatic Computer
that was completed just a few years ago. | 7 | 3 | [
{
"comment_id": "6663888",
"author": "YGDES",
"timestamp": "2023-07-17T23:20:03",
"content": "Ah, Paul Kocyla, of course ! :-D",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6664175",
"author": "BDR",
"timestamp": "2023-07-18T23:58:51",
... | 1,760,372,230.361096 | ||
https://hackaday.com/2023/07/17/hackaday-prize-2023-tilting-mechanical-panels-make-a-beautiful-display/ | Hackaday Prize 2023: Tilting Mechanical Panels Make A Beautiful Display | Donald Papp | [
"Art",
"The Hackaday Prize"
] | [
"3d printed",
"art",
"display",
"mechanical display",
"servo",
"sg90"
] | Mechanical displays use a variety of different methods to represent data with physical objects, and [AIRPOCKET]’s
Mechanical Display
aims to be a platform anyone can use. Each “pixel” in this display is a panel of some kind, and different effects can be had by moving individual panels to different angles. Not only can images be represented, but the patterns of the movements themselves can be beautiful as well.
The panels are an important part of how the display presents, so the design makes them easy to change out.
These sorts of displays are fertile ground for artistic expression (one memorable implementation of this basic idea was the
wooden mirror
, which used varnished tiles of wood) but anyone looking to use the concept has usually been on their own when it comes to implementation.
The idea [AIRPOCKET] has is to make this kind of installation easier to implement. This method uses economical mini RC servos and 3D-printed pieces to create modular segments that can be assembled into whatever configuration one may need.
The material of the panels matters, too. Just below the page break, you can see a large unit with each “pixel” consisting of a mirrored square that reflects daylight. There’s also a video of an earlier prototype that uses some ridged two-color pieces to create a simple 4×4 three-level greyscale display.
There are a lot of possibilities if [AIRPOCKET] can make this sort of display more easily accessible, and that makes it a contender in the
2023 Hackaday Prize
.
The
Hackaday
Prize 2023
is Sponsored by: | 13 | 6 | [
{
"comment_id": "6663860",
"author": "a_do_z",
"timestamp": "2023-07-17T21:41:46",
"content": "Interesting.Maybe the camera angle in the top video isn’t doing it justice. I have a hard time reading the message until I squint or, even more effectively, take off my glasses.How well does it reflect lig... | 1,760,372,230.515057 | ||
https://hackaday.com/2023/07/17/remote-code-execution-on-an-oscilloscope/ | Remote Code Execution On An Oscilloscope | Bryan Cockfield | [
"Security Hacks"
] | [
"arbitrary code execution",
"binary",
"curl",
"exploit",
"firmware",
"network",
"oscilloscope",
"rigol",
"security",
"vulnerability"
] | There are a huge number of products available in the modern world that come with network connectivity now, when perhaps they might be better off with out it. Kitchen appliances like refrigerators are the classic example, but things like lightbulbs, toys, thermostats, and door locks can all be found with some sort of Internet connectivity. Perhaps for the worse, too, if the security of these devices isn’t taken seriously, as they can all be vectors for attacks. Even things like
this Rigol oscilloscope and its companion web app
can be targets.
The vulnerability for this oscilloscope starts with an analysis of the firmware, which includes the web control application. To prevent potentially bricking a real oscilloscope, this firmware was emulated using QEMU. The vulnerability exists in the part of the code which involves changing the password, where an attacker can bypass authentication by injecting commands into the password fields. In the end, the only thing that needs to be done to gain arbitrary code execution on the oscilloscope is to issue a
curl
command directed at the oscilloscope.
In the end, [Maunel] suggests not connecting this oscilloscope to the Internet at all. He has informed the producer about it but as of this writing there has not been a resolution. It does, however, demonstrate the vulnerabilities that can be present in network-connected devices where the developers of the software haven’t gone to the lengths required to properly secure them for use with the modern Internet.
Even things not connected to a traditional Internet connection
can be targets for attacks. | 10 | 4 | [
{
"comment_id": "6663816",
"author": "smellsofbikes",
"timestamp": "2023-07-17T18:46:25",
"content": "I thought this was really impressive when I read it the other day, and am looking around our lab. We have at least 20 different kinds of test instruments that are capable of remote operation by web... | 1,760,372,230.462369 | ||
https://hackaday.com/2023/07/17/discussing-the-finer-points-of-space-worthy-software/ | Discussing The Finer Points Of Space-Worthy Software | Tom Nardi | [
"Hackaday Columns",
"Slider",
"Space"
] | [
"cubesat",
"Hack Chat",
"nasa",
"software development",
"spacecraft"
] | At the dawn of the Space Race, when computers were something that took up whole rooms, satellites and probes had to rely on analog electronics to read from their various sensors and transmit the resulting data to the ground. But it wasn’t long before humanity’s space ambitions outgrew these early systems, which lead to vast advancements in space-bound digital computers in support of NASA’s Gemini and Apollo programs. Today, building a spacecraft without an onboard computer (or even multiple redundant computers) is unheard of. Even the smallest of CubeSats is likely running Linux on a multi-core system.
Jacob Killelea
As such, software development has now become part an integral part of spacecraft design — from low-level code that’s responsible for firing off emergency systems to the 3D graphical touchscreen interfaces used by the crew to navigate the craft. But as you might expect, the stakes here are higher than any normal programming assignment. If your code locks up here on Earth, it’s an annoyance. If it locks up on a lunar lander seconds before it touches down on the surface, it could be the end of the mission.
To get a bit more insight into this fascinating corner of software development, we invited Jacob Killelea to host last week’s
Software for Satellites Hack Chat
. Jacob is an engineer with a background in both aero and thermodynamics, control systems, and life support. He’s written code for spacecraft destined for the Moon, and perhaps most importantly, is an avid reader of Hackaday.
Reliability Above All Else
The conversation started about as you’d expect, with several people wanting to know what kind of languages, frameworks, and even operating systems are used in today’s spacecraft. Jacob says while there’s an incredible amount of variability out there depending on the hardware and what the software needs to do, much of it is familiar to folks like us. He says the language of choice tends to be C, and that while Linux is used, it’s generally only for higher level tasks that don’t need to happen in real-time. If not running on the bare metal, critical code is likely to be running on something like VxWorks. Although even here he cautions that the aerospace community prefers to stick with what works, so you may find the spacecraft you’ve been tasked to write code for is using an OS from the early 2000s.
Reliability is ultimately the name of the game when writing code for space applications, which brought the conversation towards fault tolerance and so-called “safe mode” operation. Given that faults can be triggered by external events outside of your control (such as cosmic rays), even the most carefully crafted and tested code may one day crash. In that event, there needs to be a secondary system that can take over and put the craft into a known-good state. Interestingly, these “safe-mode controllers” are often a dedicated module and not just a different operating mode of the main computer.
This provides true redundancy in the event of a complete computer failure, but isn’t without its own risk — Jacob recalled a mission he’d studied where a controller designed for a previous vehicle had been reused on one with a different physical layout. Everything was fine until the satellite eventually went into safe-mode, at which point the controller’s attempts to stabilize the craft actually caused it to tumble out of control. In the end the “safe-mode” ended up being anything but, and the vehicle was lost.
Test Like You Fly
Others in the chat wanted to know about what kind of simulations or testing can be done with spacecraft software here on the ground. Jacob says one of the most powerful tools is what’s called a FlatSat, which could be considered something akin to the breadboard version of the spacecraft’s final hardware. All of the craft’s electronic components are laid out on a workbench, with ample test-points that allow tapping into the power and communication busses. This gives engineers the necessary access to test different modules and simulate various failures in ways that would be difficult or perhaps even impossible if using a replica of the flight hardware.
Image of a
FlatSat being tested by the ESA
.
But still, this only gets you so far. Jacob points out that it’s all but impossible to accurately simulate the space environment. There’s no way to create microgravity in the lab, so how will you know how it impacts your inertial measurement units (IMUs) in orbit? How can you be sure your optical star tracker won’t be confused as the craft rotates when your test rig is bolted to the table? The answer is, simply, that you can’t. All you can do is test for as many edge cases as you can think of, and make sure the system can fail as gracefully as possible.
That said, you can get an idea of how your electronics will respond to cosmic radiation without hitching a ride to space. Jacob says he was involved with a project where they tested their system against radiation induced faults by putting it in the cyclotron at Texas A&M University and hitting it with proton beams. This produced numerous fault conditions, some of which they were able to devise recovery procedures for. Of course there’s no way of predicting what will actually happen in space, and satellites in lower orbits are partially protected from radiation by the Earth’s magnetic field, but it’s still good to at least have an idea of what you’re up against.
On the Shoulders of Giants
In decades past, each spacecraft or mission was an entirely new venture — a real “to boldly go where no one has gone before” kind of thing. But today’s aerospace engineers have the benefit of shared spacecraft platforms and robust software frameworks that allow them to incorporate the hard-learned lessons of previous missions into their new craft.
Modern craft like the JWST can safely host software payloads.
For example, Jacob strongly recommended anyone interested in spacecraft software take a look at NASA’s Core Flight System (cFS). This Apache-licensed flight software framework can run on Linux and various real-time operating systems (RTOSs), and provides modules for various spaceflight-related tasks such as telemetry, process management, error reporting, command scheduling, etc. Even if your homebrew rover isn’t likely to get much farther than the back garden, it could probably benefit from some of the research and software development that NASA has already done.
Jacob also mentioned that more modern satellites, especially the larger and more capable variants that operate in deep space, have enough computing power that they can offer up virtualized environments for “software payloads” that are uploaded from the ground. So for example if you had some kind of research you wanted to conduct using the sensors on a given spacecraft, you could potentially upload your own code that would run in a protected environment where failures won’t endanger the craft’s vital systems.
This is especially helpful on spacecraft designed for exploration or scientific observations. It turns out the
James Webb Space Telescope (JWST)
uses a system like this so scientists that “visit” the observatory virtually can operate its instruments safely through programs written in, of all things, JavaScript.
Jacob was good enough to end the chat with a rundown of various systems and technologies at play in modern spacecraft, such as standardized data busses or telemetry protocols. Basically he took the time to answer the questions that most of us aren’t well versed enough to even ask, and the results were absolutely fascinating. Like they say, you don’t know what you don’t know.
We’d like to thank Jacob for giving us a taste of what it’s like to develop software for modern spacecraft. While we might not get the chance to run any of our
own
code in orbit, we can all certainly benefit from some of the lessons learned while operating in such a hostile environment.
The Hack Chat is a weekly online chat session hosted by leading experts from all corners of the hardware hacking universe. It’s a great way for hackers connect in a fun and informal way, but if you can’t make it live, these overview posts as well as the
transcripts posted to Hackaday.io
make sure you don’t miss out. | 28 | 9 | [
{
"comment_id": "6663799",
"author": "nonconformingnomad",
"timestamp": "2023-07-17T17:48:38",
"content": "Thank you so much for this article! This is fascinating! Such an interesting shift of perspective from our everyday ‘tech’ software engineering (where I admit to ‘moving fast’ and ‘breaking thi... | 1,760,372,230.608496 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.