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/2023/06/05/increasing-system-memory-with-the-flick-of-a-switch/ | Increasing System Memory With The Flick Of A Switch | Bryan Cockfield | [
"Retrocomputing"
] | [
"apple",
"mac",
"macintosh",
"macintosh 128k",
"macintosh 512k",
"memory",
"retrocomputing",
"switch",
"upgrade"
] | There’s an apocryphal quote floating around the internet that “640K ought to be enough memory for anybody” but it does seem unlikely that this was ever actually said by any famous computer moguls of the 1980s. What is true, however, is that in general more computer memory tends to be better than less. In fact, this was the basis for the Macintosh 512k in the 1980s, whose main feature was that it was essentially the same machine as the Macintosh 128k, but with quadruple the memory as its predecessor. If you have yet to upgrade to the 512k, though,
it might be best to take a look at this memory upgrade instead
.
The Fat Mac Switcher, as it is called by its creator [Kay Koba], can upgrade the memory capability of these retro Apple machines with the simple push of a switch. The switch and controller logic sit on a separate PCB that needs to be installed into the computer’s motherboard in place of some of the existing circuitry. The computer itself needs its 16 memory modules replaced with 41256 DRAM modules for this to work properly though, but once its installed it can switch seamlessly between 512k and 128k modes.
Another interesting quirk of the retro Macintosh scene is that the technically inferior 128k models tend to be valued higher than the more capable 512k versions, despite being nearly identical otherwise. There are also some other interesting discussions on
one of the forum posts about this build
as well. This module can also be used in reverse; by installing it in a Macintosh 512k the computer can be downgraded to the original Macintosh 128k. For this the memory modules won’t need to be upgraded but a different change to the motherboard is required.
A product like this certainly would have been a welcome addition in the mid 80s when these machines were first introduced, since the 512k was released only months after the 128k machines were, but the retrocomputing enthusiasts should still get some use out of this device and be more able to explore the differences between the two computers. If you never were able to experience one of these “original” Macintosh computers in their heyday,
check out this fully-functional one-third scale replica
. | 17 | 8 | [
{
"comment_id": "6650008",
"author": "wert3w4e34",
"timestamp": "2023-06-05T18:58:03",
"content": "I would ethernet and wifi as mac network and normal usb mouse and keyboard",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6650012",
"author": "Dan Julio",
... | 1,760,372,277.435525 | ||
https://hackaday.com/2023/06/05/microsculptures-3d-printed-with-advanced-macromolecular-inks/ | Microsculptures 3D Printed With Advanced Macromolecular “Inks” | Lewin Day | [
"3d Printer hacks",
"Science"
] | [
"3d printing",
"buckyball",
"buckyballs",
"two-photon laser printing"
] | When we think about 3D printing, our mind often jumps to hot nozzles squirting out molten plastic. Other popular techniques include flashing bright light into resin, or using lasers to fuse together metal powders. All these techniques are great at producing parts with complicated geometries at desktop scales.
However, it’s also possible to 3D print at altogether microscopic scales. Researchers in Germany have now developed
advanced macromolecular “inks”
that can be used to create microscopic 3D sculptures with finer control than ever before.
Exacting Requirements
Macromolecular inks were produced with exacting structures, and used to print buckyballs for mechanical and chemical testing. Credit:
Catt, Hackner, Spatz, Blasco, 2023
At the cutting edge of 3D printing, Eva Blasco’s team at the University of Heidelberg has successfully created 3D printed structures with meticulously designed molecular sequences. This technique echoes the precision found in polymers in the natural world – akin to the way DNA can code for precisely specific amino acids of exacting composition.
Researchers first meticulously engineered the molecular sequence of their inks, with an eye to gaining unprecedented control of the printed product’s fundamental properties. In simpler terms, Blasco and her team worked to arrange molecules in a custom sequence to create unique structures with exacting properties.
Blasco’s team created a series of inks, each with unique permutations of eight molecular units, to observe how changing the sequence impacts the properties of the printed structures. These are referred to as sequence-defined or macromolecularly-defined polymers in the scientific literature. They often require complex chemical synthesis in order to produce molecules with the precise desired structure. These precision-built molecules could have wider applications in realms like data storage, cryptography, or pharmaceutical applications, assuming researchers can master their manipulation at the molecular level.
In the case of Blasco’s research, the aim was to determine whether different sequence-defined macromolecules could create materials with varying properties. The goal was to precisely engineer the molecules to be suited for a 3D printing like process called
two-photon laser printing
, or 2PLP. Currently popular as a tool for working with microfluidics and micro-optics, it can be used to create tiny structures at the microscopic level. Focused laser light is used to polymerize a material at a precise spot, over and over again, to build up 3D structures. As it stands, currently available commercial materials for this use are considered imprecise in composition. Thus, the goal was to create molecularly-exact inks for this polymerization process.
The research team created three different sequences of macromolecule using (B) non-functional and photocrosslinkable (C) units. The sequences used were alternating (BCBCBCBC), triblock (CCBBBBCC) and block (BBBBCCCC). The changes in sequence had direct effects on the printability of the inks, due to the distinct structures at the molecular level.
The 3D sculptures produced with the alternating, triblock, and block inks, respectively. Credit:
Catt, Hackner, Spatz, Blasco, 2023
The inks were used to print a variety of microstructures which were then assessed for their mechanical and chemical properties. This was achieved with nanoindentation testing and Raman spectroscopy, respectively. It took some finesse, both in synthesis and control of the laser printing process, but the team was able to produce a variety of structures using the new inks.
Notably, the results showed that the alternating structure had the best printability of the three tested. The block structure had the lowest Young’s Modulus, outperformed by triblock, with the alternating sequence posting the highest result, and thus exhibiting the greatest stiffness. Meanwhile, chemical analysis showed that the block structure required the highest laser power to produce stable structures, while the alternating version produced stable prints with lower laser powers and a lower degree of cross-linking.
The above initial tests were performed on simple buckyball structures printed with the 2PLP method. However, to better showcase the performance of the inks, the research team also 3D printed some more complex structures, akin to the way that the
Benchy benchmark model
is used to get a holistic view of a regular 3D printer’s performance. The researchers printed a toucan model using the alternating structure ink, showing off a large 10 um overhang on the bird’s beak. The triblock ink was used to print a koala, showing off finely detailed fur, while a kangaroo model printed with the block ink again demonstrating successful overhangs and fine details.
The value of this research is that it shows that viable sequence-defined inks can be produced for the 2PLP microprinting process. After all, it only makes sense that you’d want to control your inks on as fine a level as possible when producing features at micrometer scales. While the technology was demonstrated with the production of simple microsculptures, these techniques could prove vital to a variety of tiny fabrication tasks. Whether you’re looking at the production of tiny optical components, microfluidic tooling, or microrobotics, having the ultimate control over material properties at the molecular level is key. | 3 | 3 | [
{
"comment_id": "6649982",
"author": "Frenchgeek",
"timestamp": "2023-06-05T17:58:13",
"content": "So the world smallest violin can now be made even smaller?",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649986",
"author": "scott_tx",
"timestamp": "2... | 1,760,372,277.381022 | ||
https://hackaday.com/2023/06/05/getting-started-in-ham-hack-chat/ | Getting Started In Ham Hack Chat | Dan Maloney | [
"Hackaday Columns",
"Slider"
] | [
"Hack Chat"
] | Join us on Wednesday, June 7 at noon Pacific for the
Getting Started in Ham Hack Chat
with
Mark Hughes
and
Beau Ambur
!
If you were to scratch any random hacker from the last 100 years, chances are pretty good you’d find an amateur radio operator just beneath the surface. Radio is the first and foremost discipline where hacking was not only welcomed, but required. If you wanted to get on the air, you sat down with some coils of wire, a few random parts — as often as not themselves homemade — and a piece of an old breadboard, and you got to work. Build it yourself or do without, and when it broke down or you wanted to change bands or add features, that was all on you too.
Like everything else, amateur radio has changed dramatically over the decades, and rolling your own radio isn’t exactly a prerequisite for entry into the ham radio club anymore. Cheap but capable handheld radios are available for a pittance, better quality radios are well within most people’s budget, and commercially available antennas have reduced the need to dabble in that particular black art. The barrier to entry for amateur radio has never been lower; you don’t even have to learn Morse anymore! So why haven’t you gotten a license?
Whatever your reason for putting off joining the club of licensed amateur radio operators, we’re going to do our best to change your mind. And to help us do that, we’ve asked Mark Hughes (KE6WOB) and Beau Ambur (K6EAU) to swing by the Chat and share their experiences with getting on the air. Both are relatively recent licensees, and they’ll do their best to answer your questions about getting on the air for the first time, to get on your way to building that first radio.
Our Hack Chats are live community events in the
Hackaday.io Hack Chat group messaging
. This week we’ll be sitting down on Wednesday, June 7 at 12:00 PM Pacific time. If time zones have you tied up, we have a
handy time zone converter
.
Click that speech bubble to the right, and you’ll be taken directly to the Hack Chat group on Hackaday.io. You don’t have to wait until Wednesday; join whenever you want and you can see what the community is talking about. | 41 | 16 | [
{
"comment_id": "6649956",
"author": "Michelle Thompson",
"timestamp": "2023-06-05T16:44:00",
"content": "There are other options besides legacy or traditional clubs in the US, the membership of which is almost always white men older than 70 who are primarily interested in socializing with each othe... | 1,760,372,277.787911 | ||
https://hackaday.com/2023/06/05/motion-canvas-helps-get-your-point-across/ | Motion Canvas Helps Get Your Point Across | Matthew Carlson | [
"Software Development"
] | [
"documentation",
"open source software",
"typescript",
"video"
] | Generating videos for projects can be difficult. Not only do you have to create the thing, but you film the process and cut it together in a story that a viewer can follow. Explaining complex topics to the viewer often involves a whiteboard of some sort, but as we all know, it’s not always a perfect solution. [Jacob] was working on a video game and making videos to document the progress and built
a tool called Motion Canvas
to help visualize topics like custom shaders. A few months ago, he decided to
release it as an open source project
.
Since then, it has seen quite a few forks and GitHub forks with a lively showcase on the community Discord. Looking at the docs, it is pretty easy to see why. The interface allows you to write procedural animations using the async semantics of TypeScript while still offering the GUI interface we expect from our video editors. In particular, the signal system allows dependencies to be defined between values. The system runs in Node, and the GUI runs in your browser locally while you edit the files in your terminal/notepad/IDE. CSS and Flexbox are available as the video is rendered to a web canvas and then compiled into a video via FFMPEG. The documentation is quite extensive, and it’s a great example of a tool someone built to fit a need they had going on to become something a little more fantastic.
This isn’t the first time
we’ve discussed how to share your projects with the world
, and we’ll freely admit we have a
bit of bias toward encouraging folks to document their projects
. | 1 | 1 | [
{
"comment_id": "6649966",
"author": "come2",
"timestamp": "2023-06-05T17:11:29",
"content": "Is it similar to the 3blue1brown python library that can be used to generate animations ? The average videast doesn’t need it, but when they do, it’s very powerful.",
"parent_id": null,
"depth": 1,
... | 1,760,372,277.252802 | ||
https://hackaday.com/2023/06/05/why-did-the-home-assistant-future-not-quite-work-the-way-it-was-supposed-to/ | Why Did The Home Assistant Future Not Quite Work The Way It Was Supposed To? | Jenny List | [
"Artificial Intelligence",
"Featured",
"Original Art",
"Rants",
"Slider"
] | [
"ai",
"alexa",
"amazon",
"virtual assistant"
] | The future, as seen in the popular culture of half a century or more ago, was usually depicted as quite rosy. Technology would have rendered every possible convenience at our fingertips, and we’d all live in futuristic automated homes — no doubt while wearing silver clothing and dreaming about our next vacation on Mars.
Of course, it’s not quite worked out this way. A family from 1965 whisked here in a time machine would miss a few things such as a printed newspaper, the landline telephone, or receiving a handwritten letter; they would probably marvel at the possibilities of the Internet, but they’d recognise most of the familiar things around us. We still sit on a sofa in front of a television for relaxation even if the TV is now a large LCD that plays a streaming service, we still drive cars to the supermarket, and we still cook our food much the way they did. George Jetson has not yet even entered the building.
The Future is Here, and it Responds to “Alexa”
“Alexa, why haven’t you been a commercial success?” Gregory Varnum,
CC BY-SA 4.0
There’s one aspect of the
Jetsons
future that has begun to happen though. It’s not the futuristic automation of projects such as Disneyland’s
Monsanto house Of The Future
, but instead it’s our current stuttering home automation efforts. We’re not having domestic robots in pinnies hand us rolled-up newspapers, but we’re installing smart lightbulbs and thermostats, and we’re voice-controlling them through a variety of home hub devices. The future is here, and it responds to “Alexa”.
But for all the success that Alexa and other devices like it have had in conquering the living rooms of gadget fans, they’ve
done a poor job of generating a profit.
It was supposed to be a gateway into Amazon services alongside their Fire devices, a convenient household companion that would help find all those little things for sale on Amazon’s website, and of course, enable you to buy them. Then, Alexa was supposed to move beyond your Echo and into other devices, as your appliances
could come pre-equipped with Alexa-on-a-chip
. Your microwave oven would no longer have a dial on the front, instead you would talk to it, it would recognise the food you’d brought from Amazon, and order more for you.
Instead of all that, Alexa has become an interface for connected home hardware, a way to turn on the light, view your Ring doorbell on models with screens, catch the weather forecast, and listen to music. It’s a novelty timepiece with
that pod bay doors joke
built-in, and worse that that for the retailer it remains by its very nature unseen. Amazon have got their shopping cart into your living room, but you’re not using it and it hardly reminds you that it’s part of the Amazon empire at all.
But it wasn’t supposed to be that way. The idea was that you might look up from your work and say “Alexa, order me a six-pack of beer!”, and while it might not come immediately, your six-pack would duly arrive. It was supposed to be a friendly gateway to commerce on the website that has everything, and now
they can’t even persuade enough people to give it a celebrity voice for a few bucks
.
The Gadget You Love to Hate
In the first few days after the Echo’s UK launch, a member of my hackerspace installed his one in the space. He soon became exasperated as members learned that “Alexa, add butt plug to my wish list” would do just that. But it was in that joke we could see the problem with the whole idea of Alexa as an interface for commerce. He had locked down all purchasing options, but as it turns out,
many people in San Diego hadn’t done the same thing
. As the stories rolled in of kids spending hundreds of their parents’ hard-earned on toys, it would be a foolhardy owner who would leave left purchasing enabled. Worse still, while the public remained largely in ignorance the potential of the device for data gathering and unauthorized access
hadn’t evaded researchers
. It’s fair to say that our community has loved the idea of a device like the Echo, but many of us wouldn’t let one into our own homes under any circumstances.
So Alexa hasn’t been a success, but conversely it’s been a huge sales success in itself. The devices have sold like hot cakes, but since they’ve been sold at close to cost, they haven’t been the commercial bonanza they might have hoped for. But what can be learned from this, other than that the world isn’t ready for a voice activated shopping trolley?
Sadly for most Alexa users it seems that a device piping your actions back to a large company’s data centres is not enough of a concern for them. It’s an easy prediction that Alexa and other services like it will continue to evolve, with inevitable AI pixie dust sprinked on them. A bet could be on the killer app being not a personal assistant but a virtual friend with some connections across a group of people, perhaps a family or a group of friends. In due course we’ll also see locally hosted and open source equivalents appearing on yet-to-be-released hardware that will condense what takes a data centre of today’s GPUs into a single board computer. It’s not often that our community rejoices in being late to a technological party, but I for one want an Alexa equivalent that I control rather than one that invades my privacy for a third party. | 121 | 36 | [
{
"comment_id": "6649852",
"author": "Joe S",
"timestamp": "2023-06-05T14:16:01",
"content": "We went from having Google Homes and Hue bulbs in every room to having zero of either. All it took was moving into a house that had reasonable built in lighting and sensible light switch-controlled outlets.... | 1,760,372,278.034687 | ||
https://hackaday.com/2023/06/05/navy-program-pumps-up-hopes-for-magnetic-propulsion/ | Navy Program PUMPs Up Hopes For Magnetic Propulsion | Navarre Bartz | [
"Transportation Hacks"
] | [
"caterpillar",
"Magnetohydrodynamic",
"marine",
"submarine"
] | The “caterpillar drive” in
The Hunt for Red October
allowed the sub to travel virtually undetected through the ocean, but real examples of magnetohydrodynamic drives (MHDs) are rare. The US Navy’s recently announced
Principles of Undersea Magnetohydrodynamic Pumps
(PUMP) intends to jump-start the technology for a new era.
Dating back to the 1960s, research on
MHDs
has been stymied by lower efficiencies when compared with driving a propeller from the same power source. In 1992 the Japanese Yamato-1 prototype, pictured at the top of the page, was able to hit a blistering 6.6 knots (that’s 12 kph or 7.4 mph for you landlubbers) with a 4 Tesla liquid helium-cooled MHD. Recent advances courtesy of fusion research have resulted in magnets capable of generating fields up to 20 Telsa, which should provide a considerable performance boost.
The new PUMP program will endeavor to find solutions for more robust electrode materials that can survive the high currents, magnetic fields, and seawater in a marine environment. If successful, ships using the technology would be
both sneakier
and
more environmentally friendly
. While you just missed the
Proposers Day
, there is more information about getting involved in the project
here
. | 43 | 12 | [
{
"comment_id": "6649754",
"author": "Garth Bock",
"timestamp": "2023-06-05T11:22:39",
"content": "I remember an article in Popular Science back in the 80s about using MHD as a more efficient way to generate electricity with lower emissions. Finely pulverized coal or natural gas would be ignited and... | 1,760,372,277.578986 | ||
https://hackaday.com/2023/06/05/protect-vintage-gear-with-easy-capacitor-reforming/ | Protect Vintage Gear With Easy Capacitor Reforming | Dave Rowntree | [
"classic hacks",
"Repair Hacks"
] | [
"capacitor",
"electrolytic capacitor",
"reforming",
"voltage rating"
] | Having acquired some piece of old electronic equipment, be it a computer, radio, or some test gear, the temptation is there to plug it in as soon as you’ve lugged it into the ‘shop. Don’t be so hasty. Those power supplies and analog circuits often have a number of old aluminium electrolytic capacitors of unknown condition, and bad things can happen if they suddenly get powered back up again. After a visual inspection, to remove and replace any with obvious signs of leakage and corrosion, those remaining may still not be up to their job, with the oxide layers damaged over time when sat idle, they can exhibit lower than spec capacitance, voltage rating or even be a dead short circuit. [TechTangents] presents for us a
guide to detecting and reforming these suspect capacitors
to hopefully bring them, safely, back to service once more.
Capacitor failure modes are plentiful
When manufactured, the capacitors are slowly brought up to operating voltage, before final encapsulation, which allows the thin oxide layer to form on the anode contact plate, this is an electrically driven chemical process whereby a portion of the electrolyte is decomposed to provide the needed oxygen ions. When operating normally, with a DC bias applied to the plates, this oxidation process — referred to as ‘self-healing’ — continues slowly, maintaining the integrity of the oxide film, and slowly consuming the electrolyte, which will eventually run dry and be unable to sustain the insulating oxide layer.
If left to sit un-powered for too long, the anodic oxide layer will decay, resulting in reduced operating voltage. When powered up, the reforming process will restart, but this will be in an uncontrolled environment, resulting in a lot of excess heat and gases being vented. It all depends on how thin the oxide layer got and if holes have started to form. That is, if there is any electrolyte left to react – it may already be far too late to rescue.
If the oxide layer is sufficiently depleted, the capacitor will start to conduct, with a resultant self-heating and runaway thermal decomposition. They can explode violently, which is why there are score marks at the top of the can to act as a weak point, where the contents can burst through. A bit like that ‘egg’ scene in Aliens!
Yucky leaky capacitor. Replace these! and clean-up that conductive goo too.
The ‘safe’ way to reform old capacitors is to physically remove them from the equipment, and apply a low, controlled voltage below the rated value to keep the bias current at a low value, perhaps just 2 mA. Slowly, the voltage can be increased to push the current back up to the initial forming level, so long as the current doesn’t go too high, and the temperature is within sensible bounds. The process ends when the applied voltage is at the rated value and the current has dropped off to low leakage values.
A word of warning though, as the ESR of the reformed caps could be a little higher than design, which will result in higher operating temperature and potentially increased ripple current in power supply applications.
We’re really glossing over this subject fast here, but [TechTangents] was kind enough to link to some fine capacitor-related reading for those who need a primer.
Here
is a US DoD handbook for reforming capacitors with advice on storage shelf life, some tech notes on
using electrolytic capactors from chemi-con
, and a
general capacitor guide from TDK
. Reforming caps is nothing new, here’s
an previous article about repairs
, and something a
bit more recent
.
Thanks [Jimi] for the tip! | 28 | 10 | [
{
"comment_id": "6649691",
"author": "macsimski",
"timestamp": "2023-06-05T09:10:59",
"content": "well…to save your milliamp meter, i suggest taking it out of the loop altogether and just measure the voltage across the resistor. so in case your capacitor develops a short, it will not hurt your meter... | 1,760,372,277.858515 | ||
https://hackaday.com/2023/06/04/3d-printing-safety-according-to-the-ul/ | 3D Printing Safety (According To The UL) | Al Williams | [
"3d Printer hacks",
"Science"
] | [
"3d printing",
"safety"
] | If you want to start a heated discussion in 3D printing circles, ask people about the requirements to print safely. Is ABS safe to print without ventilation? Can you drink out of a PLA cup? How nasty is that photo resin if you spill it on yourself? If you are at home, it’s more or less up to you. But if you are building a shared hackerspace, a corporate workstation, or a classroom, these questions might come up, and now, the UL has your answer. The
UL200B documen
t is aimed at 3D printers in “institutions of higher education,” but we imagine what’s good for the university is good for us, too.
The 45-page document isn’t an easy read. It does cover both “material extrusion” and “vat photopolymerization” technology. In fact, they identify seven “most common” processes ranging from powder bed fusion, energy deposition, and more. The work results from a UL task force with participants from Harvard, Princeton, and Carnegie-Mellon. We were surprised there didn’t seem to be any industry representation, but maybe that was on purpose.
With extrusion printing — what we’d call FDM — the focus seems to be on ultra-fine particles and volatile organic compounds (VOCs). However, the level of VOCs rose up to six times with resin printers when compared to FDM. Filters helped with ABS, nylon, and ASA, and polycarbonate/ABS. The paper does acknowledge that PLA is probably safer, although it is quick to point out that PLA with additives may not be as safe as plain PLA. If you want a quick summary, check out Table 2, starting on page 23.
The rest of the document is about creating a safety plan for all the printers that might be on a college campus — that might not be as interesting. However, you’ll want to skip forward to the appendix section. It has some data about relevant industrial standards and other data.
This is a great step in analyzing the risks of 3D printing. Of course, laser printers and copiers also spew micro-particles, and we seem to have survived those for a number of decades. Still, more data is good — you should be informed to make decisions about your health and safety. We didn’t see much in the document that covered
food safety
, something we’ve talked about before. If you want to monitor your
VOC exposure
, we got you. | 17 | 6 | [
{
"comment_id": "6649710",
"author": "Daid",
"timestamp": "2023-06-05T09:46:18",
"content": "> although it is quick to point out that PLA with additives may not be as safe as plain PLAThere is no plain PLA. Plain PLA is unprintable as it is as brittle as toasted bread, you cannot get it off a spool ... | 1,760,372,277.317045 | ||
https://hackaday.com/2023/06/04/victorian-train-tunnel-turned-test-track/ | Victorian Train Tunnel Turned Test Track | Danie Conradie | [
"Transportation Hacks"
] | [
"aerodynamics",
"tunnel",
"wind tunnel"
] | Characterizing the aerodynamic performance of a vehicle usually requires a wind tunnel since it’s difficult to control all variables when actually driving. Unless you had some kind of perfectly straight, environmentally controlled, and precision-graded section of road, anyway. Turns out the
Catesby Tunnel
in the UK meets those requirements exactly, and
[Tom Scott] recently got to take a tour of it
.
The 2.7 kilometer (1.7 mile) long tunnel was constructed as a railway tunnel between 1895 and 1897, thanks to the estate owner objecting to the idea of “unsightly trains” crossing his property. The tunnel’s construction was precise even by modern standards, deviating only 3 mm from being perfectly straight along its entire length. It lay abandoned for many years until it was paved and converted into a test facility, opening in 2021.
To measure the speed without the luxury of GPS reception, a high-speed camera mounted inside a vehicle detects reflective tags mounted every 5 m along the tunnel’s wall. This provides accurate speed measurement down to 0.001 km/h. A pair of turntables are installed at the ends of the tunnel to avoid an
Austin Powers
multi-point turn (apparently that’s the technical term) when turning around inside the confined space.
Due to the overhead soil and sealed ends, the temperature in the tunnel only varies by 1 – 2 °C year round. This controlled environment makes the tunnel perfect for coastdown tests, where a vehicle accelerates to a designated speed and then is put into neutral and allowed to coast. By measuring the loss of speed across multiple runs, it’s possible to calculate the aerodynamic drag and friction on the wheels. Thanks to the repeatable nature of the tests, it was even possible to calculate the aerodynamic losses caused by [Tom]’s cameras mounted to the outside of the vehicle.
The Catesby Tunnel is an excellent example of repurposing old infrastructure for modern use. Some other examples we’ve seen include using
coal mines
and
gold mines for geothermal energy
. | 28 | 6 | [
{
"comment_id": "6649435",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-06-05T02:08:51",
"content": "Using a literal tunnel As a wind tunnel, I wouldn’t have thought of that!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649437",
"... | 1,760,372,277.502075 | ||
https://hackaday.com/2023/06/04/hackaday-links-june-4-2023/ | Hackaday Links: June 4, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"amateur radio",
"cryptography",
"Dark Side of the Moon",
"Decode",
"fcc",
"hackaday links",
"HAKUTO-R",
"ham",
"Ingenuity",
"interference",
"Jezero",
"mars",
"optics",
"Perserverance",
"physics",
"pink floyd",
"prism",
"refractive index",
"SETI"
] | A report released this week suggests that 50 flights into its five-flight schedule, the Mars helicopter might be starting to show its age. The report details
a protracted communications outage
Ingenuity’s
flight controllers struggled with for six sols after flight 49 back in April. At first attributed to a “communications shadow” caused by the helicopter’s robotic buddy,
Perseverance
, moving behind a rocky outcrop and denying line of sight, things got a little dicey once the rover repositioned and there was still no joy. Since the helicopter has now graduated from “technology demonstration” to a full-fledged member of the team tasked with scouting locations for the rover while respecting the no-fly zone around it, it was essential to get it flying again. Several attempts to upload a flight plan failed with nothing but an acknowledgment signal from the helicopter, but a final attempt got the program uploaded and
flight 50
was a complete if belated success. So that’s good, but the worrying news is that since Sol 685, the helicopter has been switching in and out of nighttime survival mode. What that portends is unclear, but no matter how
amazing the engineering is
, there’s only so much that can be asked on
Ingenuity
before something finally gives.
Also in Mars news this week, our own Al Williams covered
an interesting project
that really seems to have captured the attention of space geeks, math geeks, and crypto geeks — the signals kind, not the money kind — alike. The project is called
A Sign in Space
, and is aimed at developing the chops needed to decode a message from an extraterrestrial intelligence. Should we ever be so lucky as to actually pick up something, chances are pretty good that what was encoded by lifeforms that evolved under completely different circumstances from us will be essentially incomprehensible. The simulated ET message, which was sent to Earth from a European Space Agency probe in orbit around Mars, is now available to one and all, and has garnered a lot of attention
over on the project’s Discord
. Whatever the message is, we really hope it’s not some variation of “So long, and thanks for all the fish,” or “Shaka, when the walls fell!” Although we’d suggest that the decoders check the polarization of the signal for any hidden messages.
A word to the wise: If your experiments tend toward the RF variety,
do NOT mess with the amateur radio bands
. Unless, of course, you have a spare $24,000 lying around that you want to donate to the Federal Communication Commission. That’s what it’ll cost Philip Beaudet (N6PJB) who allegedly engaged in some very bad behavior in late 2022. Local hams complained that Beaudet regularly interfered with the Western Amateur Radio Friendship Association’s net by playing recorded music while members were trying to check in, while refusing to identify himself. An FCC agent caught him in the act three times, and now he has 30 days to cough up the fine. Strangely, they didn’t revoke his license, which seems like the least they could do to clean up the airwaves.
At the risk of stating the obvious, landing on the Moon is hard. It’s only been done successfully a few dozen times, and while it’s not as complicated as nailing a Mars landing, it still carries plenty of challenges. We got a stark reminder of this fact with the recent failure of ispace’s HAKUTO-R mission, which was to be the first private lunar landing mission but crashed into the surface. We now have
views of the crash site
thanks to a flyover by the Lunar Reconnaissance Orbiter, as well as
an explanation of what went wrong
. Surprise! It was a software error; apparently, the radar altimeter got confused as the lander passed over a deep crater with steep sides, and calculated the lunar surface to be five kilometers higher than it actually is. The good news is that the lander absolutely nailed landing on that virtual lunar surface; the bad news is that as it hovered there waiting for the pads to touch the surface, it ran out of fuel and took a free-fall ride to the real surface.
And finally, we all know someone — or might actually
be
someone — who loves to pick apart movies that depict space travel in ways that violate the laws of physics. Yes, we know that spacecraft don’t need wings and wouldn’t bank and jink like World War II fighters trying to evade an enemy on their six, but there’s something to be said for just getting into the spirit of the proceedings. And so in a similar vein, we present one Tom Tierney, a physics teacher who
absolutely ruins Pink Floyd’s classic 1973 album
The Dark Side of the Moon
with physics. While pointing out that there really is no dark side of the Moon, his main quibble is with the optics depicted by Storm Thorgerson’s iconic design, which aren’t accurate in virtually any way. What’s cool about this is that Tom uses the artwork in his physics lessons, having students make measurements from the cover to determine the refractive index of the depicted prism, which clearly was not made of glass. We shouldn’t complain, because it’s not mean-spirited or petty at all, and if it helps teach physics, we’re all for it. But there’s something slightly sacrilegious about attacking
DSOTM
, at least for some of us. | 9 | 4 | [
{
"comment_id": "6649335",
"author": "Pwalsh",
"timestamp": "2023-06-04T23:39:30",
"content": "I do this a lot for movies. Thinking about the Star Wars universe, after having recently seen the Boba Fett and Mandalorian series:1) The technology is completely uniform and saturated everywhere – you can... | 1,760,372,277.70976 | ||
https://hackaday.com/2023/06/04/it-turns-out-parrots-love-videoconferencing/ | It Turns Out Parrots Love Videoconferencing | Donald Papp | [
"home hacks",
"Tablet Hacks"
] | [
"birds",
"parrot",
"pets",
"video calling",
"videoconferencing",
"wholesome"
] | A recent experiment showed that parrots seem
considerably enriched by the ability to video call other parrots
. It’s important that the activity be done in a healthy and ethical way, so researchers do not recommend bird caretakers immediately slap a spare tablet in front of every bird — but the results are as heartwarming as they are encouraging.
Parrots are intelligent creatures known to require and benefit from intellectual and emotional stimulation, and their eyesight is such that they are able to use a display like a tablet screen much like a human would. They are also social creatures, and that led to researchers designing a pilot study to explore a parrot-to-parrot videoconferencing system.
The three-month study showed that when given the opportunity to initiate and receive video calls, every single parrot in the test group did so and all bird caretakers reported perceived benefits. Birds made friends, seemed highly motivated, and even learned behaviors by watching others.
Curious about the details?
The published results
(a PDF and two brief videos) covers all the bases. Parrot pals may also remember another time that technology enriched a feathered friend with
a motorized buggy complete with beak-compatible joystick for steering
. | 18 | 8 | [
{
"comment_id": "6649293",
"author": "Unochepassa",
"timestamp": "2023-06-04T20:57:19",
"content": "This experiment makes me think of “the planet of the apes” movie (the good one)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649294",
"author": "Dan (No,... | 1,760,372,278.135131 | ||
https://hackaday.com/2023/06/04/make-yourself-a-megamind-with-a-hypercentric-camera/ | Make Yourself A Megamind With A Hypercentric Camera | Dan Maloney | [
"digital cameras hacks"
] | [
"camera",
"fresnel",
"hypercentric",
"lens",
"perspective",
"telecentric"
] | Sometimes, all it takes to learn something new is a fresh perspective on things. But what’s to be learned from
reversing your perspective completely with a hypercentric lens
? For one thing, that you can make humans look really, really weird.
To be fair, there’s a lot to the optical story here, which [volzo] goes over in ample detail. The short version of it is that with the right arrangement of optical elements, it’s possible to manipulate the perspective of a photograph for artistic effect, up to the point of reversing the usual diminishment of the apparent size of objects in the scene that are farther away from the camera. Most lenses do their best to keep the perspective of the scene out of this uncanny valley, although the telecentric lenses used in some machine vision systems manipulate the perspective to make identical objects within the scene appear to be the same size regardless of their distance from the camera. A hypercentric lens, on the other hand, turns perspective on its head, making near objects appear smaller than far objects, and comically distorts things like the human face.
[volzo]’s hypercentric camera uses a 700-mm focal length Fresnel lens mounted on a motorized gantry, which precisely positions a camera relative to the lens to get the right effect. A Raspberry Pi controls the gantry, but it’s not strictly needed for the hypercentric effect to work. Lighting is important, though, with a ring of LEDs around the main lens providing even illumination of the scene. The whole setup as well as the weirdly distorted portraits that result are shown in the video below.
If these bizarrely distorted faces look familiar, you might be recalling
[Curious Marc]’s head-enlarging wearable
. | 4 | 3 | [
{
"comment_id": "6649561",
"author": "P. Duff",
"timestamp": "2023-06-05T05:03:54",
"content": "Aper’ture not a’perture",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6650091",
"author": "Rob",
"timestamp": "2023-06-05T23:55:35",
"con... | 1,760,372,278.173612 | ||
https://hackaday.com/2023/06/04/a-real-world-experience-in-pcb-dye-sub-printing/ | A Real-World Experience In PCB Dye-Sub Printing | Jenny List | [
"Parts"
] | [
"color pcb",
"dye sublimation",
"pcb printing"
] | We all love PCB artwork, but those who create it work under the restriction of having a limited color palette to work with. If it’s not some combination of board, plating, solder mask, and silk screen, then it can’t easily be rendered on a conventional PCB. That’s not the end of the story though, because it’s technically possible to print onto a PCB and have it any color you like. Is it difficult? Read [Spencer]’s experience
creating a rainbow Pride version of his RC2014 modular retrocomputer
.
Dye-sublimation printing uses an ink that vaporizes at atmospheric pressure without a liquid phase, so a solid ink is heated and the vapor condenses back to solid on the surface to be printed. Commercial dye-sub printers are expensive, but there’s a cheaper route in the form of an Epson printer that can be converted. This in turn prints onto a transfer paper, from which the ink is applied to the PCB in a T-shirt printing press.
[Spencer] took the advice of creating boards with all-white silkscreen applied, and has come up with a good process for creating the colored boards. There is still an issue with discoloration from extra heat during soldering, so he advises
in the instructions for the kit
to take extra care. It remains however a fascinating look at the process, and raises the important point that it’s now within the reach of perhaps a hackerspace.
Regular readers will know
we’ve long held an interest in the manufacture of artistic PCBs
. | 8 | 6 | [
{
"comment_id": "6649222",
"author": "Jan",
"timestamp": "2023-06-04T14:18:16",
"content": "Cool! Very informative, must keep this one in mind.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649234",
"author": "arcdoom",
"timestamp": "2023-06-04T15:58... | 1,760,372,278.074933 | ||
https://hackaday.com/2023/06/04/c17s-useful-features-for-embedded-systems/ | C++17’s Useful Features For Embedded Systems | Maya Posch | [
"Microcontrollers",
"Software Development"
] | [
"c++",
"c++17",
"embedded software"
] | Although the world of embedded software development languages seem to span somewhere between ASM and C89 all the way to MicroPython, there is a lot to be said for a happy medium between ease of development and features that makes the software more robust without adding overhead or bloat to the final firmware image.
This is where C++ has objectively many advantages over even C99, and as [Çağlayan Dökme]
argues in a recent blog post
C++17 adds many developer critter comforts to C++98 and the more recent C++11 C++14 standards.
First stepping back a generation (technically two, with C++20 also being a thing already), the addition of binary literals (e.g.
0b1010'1100
) in C++14 and the expanded use of
constexpr
is addressed, with the latter foreshadowing C++17’s increased focus on compile time optimizations. A new attribute in C++17 that is part of this is
[[nodiscard]]
, which when added before to the return type of a function or method requires the return value to be used in some manner, much like with functions in Ada (contrasted with procedures).
As [Çağlayan] notes, the biggest strength of compile-time checks is that it can save a lot of deploy-test-fix round-trips, with the total number of issues caught after deployment that could have been caught during compilation ideally being zero. Here C++17 streamlines the
static_assert()
mechanism and simplifies using
if constexpr
to instantiate code depending on compile-time conditions. Beyond compile-time optimizations there are a few other niceties, such as C++17 guaranteeing copy elision (return value optimization) when an object is returned directly, which is a welcome feature in hard real-time environments.
With today even MCUs having enough grunt to run multi-threaded applications and potentially firmware compiled from a many-thousand LoC codebase, picking a programming language that assists the developer with such an arduous task is very important, with
Ada being the primary choice
for high-reliability embedded platforms, but C++ along with C enjoying the most widespread (free) compiler support. Even if C++ isn’t supported on every single MCU out there (8051-based and most PIC MCUs mostly), whenever it is an option, it’s a pretty solid choice, especially with knowledge of these new language features. | 42 | 10 | [
{
"comment_id": "6649191",
"author": "Jouni",
"timestamp": "2023-06-04T12:51:56",
"content": "Good tips. C++ is great for embedded code.And now, let the C++ and C hate begin. If you don’t know where to start, you can start telling how horrible pointers are for example. Then you can continue to topic... | 1,760,372,278.523242 | ||
https://hackaday.com/2023/06/04/the-most-ornate-birdbath-youve-ever-seen/ | The Most Ornate Birdbath You’ve Ever Seen | Danie Conradie | [
"Art"
] | [
"automaton",
"kinetic art",
"kinetic sculpture"
] | When one thinks of art, a birdbath may not be the first thing that comes to mind. However, there is no denying that the
La Fontaine aux Oiseaux
(The Bird Fountain) is a true work of art. This automaton, created by automaton maker [François Junod] in collaboration with 20 different workshops and craftsmen, represents thousands of hours of work and boasts a complex beauty that is both visible and hidden.
Commissioned by the Van Cleef & Arpels jewelry company, this purely mechanical display piece features a pair of jewel-encrusted birds that perform a little routine around the edge of the bath every hour. All the birds’ appendages move while bird song is added with the help of a whistle and bellows. The “water” is also mechanized, with a series of metal plates moving together to create ripple effects, while a water lily opens and closes and a dragonfly flutters above the surface.
The overall effect of this ridiculously over-the-top mechanical art piece is absolutely mesmerizing. Even if the bejeweled exterior isn’t quite your style, you can still appreciate its intricate workings thanks the video after the break giving us a peek at the development.
We’ve featured some of
[François]’ other work
before, which is equally impressive and displays the mechanics in all it’s glory. If you want to try your hand at making automatons,
3D printing is the perfect way to get started
. | 8 | 5 | [
{
"comment_id": "6649162",
"author": "Andrew",
"timestamp": "2023-06-04T08:41:25",
"content": "Do you have the STL?",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649166",
"author": "Jan",
"timestamp": "2023-06-04T08:51:15",
"content": "Wow! Beaut... | 1,760,372,278.622908 | ||
https://hackaday.com/2023/06/03/a-fresnel-lens-without-the-pain/ | A Fresnel Lens Without The Pain | Jenny List | [
"green hacks"
] | [
"fresnel",
"lens",
"optics",
"Robert Murray-Smith"
] | Making a traditional glass lens requires a lot of experience, skill, and patience grinding a piece of glass to the required shape, and is not for the casual experimenter. Making a glass Fresnel lens with its concentric rings requires even more work, but as the ever-resourceful [Robert Murray-Smith] shows us, a Fresnel lens can be made from far more mundane materials.
He shows us a working lens made from transparent plastic tube
, and even successfully smoulders a piece of paper with it under the anaemic British sun.
His lens, with its circular profile tube filled with water, is not perhaps the most efficient lens in terms of light focused per unit area of lens. From dredging up our highschool physics lessons we are guessing that half the light is diffracted outwards rather than inwards by the cylindrical profile of the coil, but for the cost of the whole device we’re not sure that matters. Next time we’re shipwrecked on a desolate island with a handy supply of clear plastic tube and fresh water, we know we can always raise a fire.
If Fresnel lenses interest you,
we’ve taken a look in the past at their history
. | 21 | 12 | [
{
"comment_id": "6648963",
"author": "Murray",
"timestamp": "2023-06-03T08:16:04",
"content": "Looks more like a diffuser with interference patterns.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648964",
"author": "Joshua Ellis",
"timestamp": "2023-... | 1,760,372,278.680197 | ||
https://hackaday.com/2023/06/02/c64-gets-chatgpt-access-via-bbs/ | C64 Gets ChatGPT Access Via BBS | Lewin Day | [
"Machine Learning"
] | [
"ai",
"ChatGPT",
"large language model"
] | ChatGPT, powered by GPT 3.5 and GPT 4, has become one of the most popular Large Language Models (LLM), due to its ability to hold passable conversations and generate large tracts of text. Now,
that very tool is available on the Commodore 64 via the Internet.
Obviously, a 6502 CPU with just 64 kilobytes of RAM can barely remember a dictionary, let alone the work with something as complicated as a modern large language model. Nor is the world’s best-selling computer well-equipped to connect to modern online APIs. Instead, the C64 can access ChatGPT through the Retrocampus BBS, as demonstrated by [Retro Tech or Die].
Due to security reasons, the ChatGPT area of the BBS is only available to the board’s Patreon members. Once in, though, you’re granted a prompt with ChatGPT displayed in glorious PETSCII on the Commodore 64. It’s all handled via a computer running as a go-between for the BBS clients and OpenAI’s ChatGPT service, set up by board manager [Francesco Sblendorio]. It’s particularly great to see ChatGPT spitting out C64-compatible BASIC.
While this is a fun use of ChatGPT,
be wary of using it for certain tasks in wider society
. Video after the break.
[Thanks to Nick W. for the tip!] | 4 | 3 | [
{
"comment_id": "6649010",
"author": "Steven Goldsmith",
"timestamp": "2023-06-03T16:16:43",
"content": "Why? Try to get it to generate Z80 code. It makes up operands and opcodes.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6649109",
"author": "Jo... | 1,760,372,278.388923 | ||
https://hackaday.com/2023/06/02/perovskite-sensor-array-emulates-human-retina-for-panchromatic-imaging/ | Perovskite Sensor Array Emulates Human Retina For Panchromatic Imaging | Maya Posch | [
"News",
"Science"
] | [
"artificial retina",
"panchromatic imaging",
"perovskite"
] | The mammalian retina is a complex system consisting out of cones (for color) and rods (for peripheral monochrome) that provide the raw image data which is then processed into successive layers of neurons before this preprocessed data is sent via the optical nerve to the brain’s visual cortex. In order to emulate this system as closely as possible, researchers at Penn State University
have created a system
that uses perovskite (methylammonium lead bromide, MAPbX
3
) RGB photodetectors and a neuromorphic processing algorithm that performs similar processing as the biological retina.
Panchromatic imaging is
defined
as being ‘sensitive to light of all colors in the visible spectrum’, which in imaging
means enhancing
the monochromatic (e.g. RGB) channels using panchromatic (intensity, not frequency) data. For the retina this means that the incoming light is not merely used to determine the separate colors, but also the intensity, which is what underlies the wide dynamic range of the Mark I eyeball. In this experiment, layers of these MAPbX
3
(X being Cl, Br, I or combination thereof)
perovskites
formed stacked RGB sensors.
The output of these sensor layers was then processed in a pretrained convolutional neural network, to generate the final, panchromatic image which could then be used for a wide range of purposes. Some applications noted by the researchers include new types of digital cameras, as well as artificial retinas, limited mostly by how well the perovskite layers scale in resolution, and their longevity, which is a long-standing issue with perovskites. Another possibility raised is that of powering at least part of the system using the energy collected by the perovskite layers, akin to proposed perovskite-based solar panels.
(Heading: Overall design of retina-inspired NB perovskite PD for panchromatic imaging. (Credit: Yuchen Hou et al., 2023) ) | 13 | 6 | [
{
"comment_id": "6648922",
"author": "Ostracus",
"timestamp": "2023-06-03T02:08:46",
"content": "Two for one. Power generation and image sensor.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648926",
"author": "Chris",
"timestamp": "2023-06-03T02:32:... | 1,760,372,278.444107 | ||
https://hackaday.com/2023/06/02/sma-connector-footprint-design-for-open-source-rf-projects/ | SMA Connector Footprint Design For Open Source RF Projects | Dave Rowntree | [
"hardware"
] | [
"characteristic impedance",
"design",
"pcb",
"qucs",
"RF",
"S-params",
"simulation",
"sma",
"stack up"
] | When you first start out in the PCB layout game and know just enough to be dangerous, you simply plop down a connector, run a trace or two, and call it a hack. As you learn more about the finer points of inconveniencing electrons, dipping toes into the waters of higher performance, little details like via size, count, ground plane cutouts, and all that jazz start to matter, and it’s very easy to get yourself in quite a pickle trying to decide what is needed to just exceed the specifications (or worse, how to make it ‘the best.’) Connector terminations are one of those things that get overlooked until the MHz become GHz. Luckily for us, [Rob Ruark] is on hand to give us a leg-up on
how to get decent performance from edge-launch SMA connections for RF applications
. These principles should also hold up for high-speed digital connections, so it’s not just an analog game.
Return loss vs frequency for various test coupons
Everything that happens to those unfortunate electrons along their travels will affect performance in a subtle way, but the higher the frequency components of a signal, the worse it gets. An SMA edge connector may be designed to present a characteristic impedance of 50Ω typically, but that is to the end of the connection pins. Once it’s soldered down, there is a discontinuity unless precautions are taken. Even the transition from the pad to the signal trace can push a system out of spec, but what about the stack-up? What about the ground plane under the pad?
Simulation vs measurements
The first part of the job is to lock down your PCB process, via a specific stack-up. Every PCB house and line within it is different from the next, so it is critical to get hold of the layer arrangement, foil and dielectric thicknesses, dielectric constants, and loss tangent figures. [Rob] took a typical route, making a first stab at a footprint design supported by lots of online calculators (like
these
by Chemandy Electronics) and reference material. The basic structure is the usual coplanar waveguide, where the e-field is constrained by the ground plane below and leaks over the top of the trace. This resulted in a set of test coupons (small test PCBs) for two fab processes in parallel, OSHPark and JLCPCB.
The returned PCBs were characterised using a NanoVNA V2 Plus, to get the S
11
(return loss) curve up to about 4.5 GHz, confirming at about -26 dB they were already in a good position for optimisation. [Rob] also goes into some details about how to line up a QUCS simulation of a lumped transmission line model with the measured test coupon performance, which is well worth digging into.
PCB design is about functionality, but it is also about
aesthetics and other factors
that come out of that. Also on the subject of transmission lines, there are
other kinds of transmission lines to read about
. | 10 | 4 | [
{
"comment_id": "6648890",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-06-02T23:34:08",
"content": "I wish there were cheap bandpass filters for the cheap 2 meter handheld transceivers.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6... | 1,760,372,278.572371 | ||
https://hackaday.com/2023/06/02/what-makes-wedge-coils-better-than-round-for-pcb-motors/ | What Makes Wedge Coils Better Than Round For PCB Motors? | Lewin Day | [
"Engine Hacks"
] | [
"motor",
"motor design",
"pcb motor",
"python"
] | PCB motors are useful things. With coils printed right on the board, you don’t need to worry about fussy winding jobs, and it’s possible to make very compact, self contained motors. [atomic14] has been doing some work in this area, and decided to explore
why wedge coils perform better than round coils in PCB motor designs.
[atomic14]’s designs use four-layer PCBs which allow for more magnetic strength out of the coils made with traces. While they’ve tried a variety of designs, like most in this area, they used wedge-shaped coils to get the most torque out of their motors. As the video explains, the wedge layout allows a much greater packing efficiency, allowing the construction of coils with more turns in the same space. However, diving deeper, [atomic14] also uses Python code to simulate the field generated by the different-shaped coils. Most notably, it shows that the wedge design provides a significant increase in field strength in the relevant direction to make torque, which scales positively on motors with higher numbers of coils.
This kind of simulation and optimization is typical in industry. It’s great to see
an explainer on real engineering
methods on YouTube for everyone to enjoy. Video after the break. | 11 | 9 | [
{
"comment_id": "6648856",
"author": "Andy",
"timestamp": "2023-06-02T21:00:26",
"content": "Can these be stacked on a single armature? Diminishing returns on track width?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648945",
"author": "TacticalNi... | 1,760,372,278.867608 | ||
https://hackaday.com/2023/06/02/hackaday-prize-2023-lask4-watches-those-finger-wiggles/ | Hackaday Prize 2023: LASK4 Watches Those Finger Wiggles | Matthew Carlson | [
"Medical Hacks",
"The Hackaday Prize"
] | [
"2023 Hackaday Prize",
"ESP32",
"machine learning",
"muscle sensor"
] | What do you get when you combine an ESP32-S2, a machine-learning model, some Hall effect sensors, and a grip exercise toy? [Turfptax]
did just that and created LASK4
. The four springs push down pistons with tiny magnets on them. Hall effect sensors determine the piston’s position, and since the springs are linear, the ESP32 can also estimate the force being applied on a given finger. This data is then streamed to a nearby computer over TCP. A small OLED screen shows the status, and a tidy 3D printed case creates a comfortable package.
So other than an excellent musical instrument, what is this good for? First, it creates well-labeled training data when combined with what is collected by
the muscle sensor band
we discussed previously. The muscle band measures various pressure sensors radially around the forearm. With just a few minutes of training data, the system can accurately predict finger movement using the random forest regression model.
What would you use it for? It’s considered a somatosensory device, so it can be used for physical therapy when undergoing hand rehabilitation, as it provides feedback during sessions. Or it could be used to train a controller efficiently.
It’s an
exciting project on GitHub
under an OpenCERN hardware license. The code is in MicroPython, and the PCB and STL files are included. We’re looking forward to seeing what else comes from the project. After the break, there’s a progress update video.
The
Hackaday
Prize 2023
is Sponsored by: | 0 | 0 | [] | 1,760,372,278.71603 | ||
https://hackaday.com/2023/06/02/chatting-about-the-state-of-hacker-friendly-ar-gear/ | Chatting About The State Of Hacker-Friendly AR Gear | Tom Nardi | [
"Hackaday Columns",
"Wearable Hacks"
] | [
"augmented reality",
"Hack Chat",
"smart glasses",
"wearable display"
] | There are many in the hacker community who would love to experiment with augmented reality (AR), but the hardware landscape isn’t exactly overflowing with options that align with our goals and priorities. Commercial offerings, from Google’s Glass to the Microsoft HoloLens and Magic Leap 2 are largely targeting medical and aerospace customers, and have price tags to match. On the hobbyist side of the budgetary spectrum we’re left with various headsets that let you slot in a standard smartphone, but like their virtual reality (VR) counterparts, they can hardly compare with purpose-built gear.
But there’s hope — Brilliant Labs are working on AR devices that tick all of our boxes: affordable, easy to interface with, and best of all, developed to be as open as possible from the start. Admittedly their first product, Monocle, it somewhat simplistic compared to what the Big Players are offering. But for our money, we’d much rather have something that’s built to be hacked and experimented with. What good is all the latest features and capabilities when you can’t even get your hands on the official SDK?
This week we invited Brilliant Lab’s Head of Engineering
Raj Nakaraja to the Hack Chat
to talk about AR, Monocle, and the future of open source in this space that’s dominated by proprietary hardware and software.
Raj Nakaraja
Naturally the Chat started off with questions about how the Monocle works, and specifically, what exactly it looks like when you’re wearing it. Compared to other devices which attempt to fill your entire field of view with high resolution graphics, the Monocle uses a tiny Sony ECX336CN 640 x 400 OLED shining down through a beam splitter placed in front of the user’s eye. The end result is an experience that Raj describes looking like a “tablet screen at arm’s length” sitting a few degrees down from the center of your vision. Viewing what’s on the Monocle is fairly natural — it’s a bit like glancing down from a movie to see your phone.
For a commercial product, the
documentation for Monocle
is nothing short of outstanding. We could only dream of a world in which all the hardware we purchased came with this sort of information. Schematics and 3D models are available, and there’s extensive guidance available for the software side of things, going as far as explaining how you can craft your own over-the-air (OTA) upgrades.
That said, you’d be hard pressed to actually build a Monocle yourself. Raj says the manufacturing aspect was a considerable challenge, and it took them awhile to find a partner that could actually produce the optics required. Multiple injection molded optics components need to be bonded to themselves and the OLED itself with a special optical glue. Brilliant Labs has this part of the Monocle patented, but Raj says this was mainly to fend off the patent trolls, and invited those in the Chat to check it out if they wanted to read more about the work that went into it.
Despite its small size, there’s an impressive amount of hardware packed into the Monocle, including an FPGA used to provide graphics acceleration. All those components consume a fair amount of energy, and even with the built-in power management, the device’s internal 70 mAh battery will only get you so far.
Raj says you can get about 45 minutes of runtime out of the Monocle under normal use, and roughly half that if you’re recording using its 5 MP Omnivision OV5640 camera. On the plus side, the Monocle comes with a charging case that has enough capacity to recharge the device six times.
Hardware details aside, several in the Chat asked what kind of things hackers could realistically do with AR. Naturally, this is where some imagination is required. But at least in the case of the Monocle, all of the software is essentially Python, so it’s very easy to plug into whatever you want. Raj points to a few examples, such as one user that
tied their Monocle to ChatGPT
— the device would listen to what was being said to the user, feed it into the language model, and covertly display the appropriate response on the display. Obviously it was a tongue in cheek project, but with a little tweaking, it could be used as a universal translator of sorts.
We’d like to thank Raj Nakaraja for taking the time to talk with the Hackaday community this week. We’ve seen interest in hackable AR and VR hardware for years, but it’s always been frustratingly out of reach. With devices the Monocle, it seems like there’s finally a change in the wind, and we can’t wait to see what hackers come up with as the hardware becomes more widespread.
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. | 13 | 7 | [
{
"comment_id": "6648825",
"author": "David",
"timestamp": "2023-06-02T18:07:48",
"content": "https://www.cnn.com/2023/06/02/tech/apple-mixed-reality-headset-challenges/index.htmlComing soon … WiFi connected players in a real world MMORPG staged in a forest or park. The ultimate cosplay.",
"par... | 1,760,372,278.921256 | ||
https://hackaday.com/2023/06/03/an-almost-invisible-desktop/ | AnAlmostInvisible Desktop | Dave Rowntree | [
"computer hacks"
] | [
"desktop",
"floating display",
"hid",
"laptop",
"machine learning"
] | When you’re putting together a computer workstation, what would you say is the
cleanest
setup? Wireless mouse and keyboard? Super-discrete cable management? How about no visible keeb, no visible mouse, and no obvious display?
That’s what
[Basically Homeless] was going for
. Utilizing a Flexispot E7 electronically raisable standing desk, an ASUS laptop, and some other off-the-shelf parts, this project is taking the idea of decluttering to the extreme, with no visible peripherals and no visible wires.
There was clearly a lot of learning and much painful experimentation involved, and the guy kind of glazed over how a keyboard was embedded in the desk surface. By forming a thin layer of resin in-plane with the desk surface, and mounting the keyboard just below, followed by lots of careful fettling of the openings meant the keys could be depressed. By not standing proud of the surface, the keys were practically invisible when painted. After all, you need that tactile feedback, and a projection keeb just isn’t right.
ChatGPT-inspired machine learning mouse emulator
Moving on, never mind an ultralight gaming mouse, how about a zero-gram mouse? Well, this is a bit of a cheat, as they mounted a depth-sensing camera inside a light fitting above the desk, and built a ChatGPT-designed machine-learning model to act as a hand-tracking HID device. Nice idea, but we don’t see the code.
The laptop chassis had its display removed and was embedded into the bottom of the desk, along with the supporting power supplies, a couple of fans, and a projector. To create a ‘floating’ display, a piece of transparent plastic was treated to a coating of
Lux labs “ClearBright” transparent display film
, which allows the image from the projector to be scattered and observed with sufficient clarity to be usable as a PC display. We have to admit, it looks a bit gimmicky, but playing
Minecraft
on this setup looks a whole lotta fun.
Many of the floating displays we’ve covered tend to be for clocks (after all timepieces are important) like this
sweet HUD hack
. | 28 | 10 | [
{
"comment_id": "6649136",
"author": "BrightBlueJim",
"timestamp": "2023-06-04T05:26:20",
"content": "The keyboard is epic, the nanoparticle projection screen is inSANE, but that mouse was a step too far. There are many, many capacitive touchpads that can operate through 3mm of wood with no trouble... | 1,760,372,278.99276 | ||
https://hackaday.com/2023/06/03/the-glitch-that-brought-down-japans-lunar-lander/ | The Glitch That Brought Down Japan’s Lunar Lander | Matthew Carlson | [
"Software Development",
"Space"
] | [
"lunar lander",
"software bug",
"software bugs"
] | When a computer crashes, it usually doesn’t leave debris. But when a computer happens to be descending towards the lunar surface and glitches out, that’s a very different story. Turns out that’s what happened on April 26th, as the Japanese Hakuto-R Lunar lander made its mark on the Moon…by crashing into it. [Scott Manley] dove in to try and
understand the software bug that caused an otherwise flawless mission to go splat
.
The lander began the descent sequence as expected at 100 km above the surface. However, as it descended, the altitude sensor reported the altitude as much lower than it was. It thought it was at zero altitude once it reached about 5 km above the surface. Confused by the fact it hadn’t yet detected physical contact with the surface, the craft continued to slowly descend until it ran out of fuel and plunged to the surface.
Ultimately it all came down to sensor fusion. The lander merges several noisy sensors, such as accelerometers, gyroscopes, and radar, into one cohesive source of truth. The craft passed over a particularly large cliff that caused the radar altimeter to suddenly spike up 3 km. Like good filtering software, the craft reasons that the sensor must be getting spurious data and filters it out. It was now just estimating its altitude by looking at its acceleration. As anyone who has tried to track an object through space using just gyros and accelerometers alone can attest, errors accumulate, and suddenly you’re not where you think you are.
We know what you’re thinking: surely they would have run landing simulations to catch errors like these? Ironically they did, it’s just that after the simulations were run, the landing site for Hakuto-R was changed. Unfortunately, nobody thought to re-run the simulations, and now the Moon has a new lawn ornament,
We’ve previously
written about why lunar landings are so hard
. While knowing what led to the crash will hopefully prevent a similar fate for future missions, the reality is that remotely landing a robot on a dusty world without the help of GPS is fiendishly difficult and likely will be for some time. | 36 | 13 | [
{
"comment_id": "6649119",
"author": "J",
"timestamp": "2023-06-04T02:21:40",
"content": "Change management is hard",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6649120",
"author": "Andrew",
"timestamp": "2023-06-04T02:28:38",
"content": "“I wond... | 1,760,372,279.065884 | ||
https://hackaday.com/2023/06/03/bike-rides-played-back-via-aircraft-altitude-indicator/ | Bike Rides Played Back Via Aircraft Altitude Indicator | Lewin Day | [
"Microcontrollers",
"Transportation Hacks"
] | [] | Any good bike ride should have a big climb to push your fitness, and a nice descent for the joy of careening down at high speed. [Glen Akins] has been recording his altitude during his mountain biking expeditions, and has now built a way
to play them back on an aircraft altitude indicator.
A Python script is used to parse a recorded GPX file, which stores position and elevation data captured from a GPS device during [Glen]’s rides. The elevation data is then output to a Raspberry Pi Pico, which drives a set of three Microchip MCP4802 DACs and three TI OPA584 op-amps in order to create the necessary 400 Hz AC waveforms to drive the aircraft altitude indicator. One DAC and op-amp are used to generate 400 Hz AC to simply power the device, while the other two are used to generate synchro signals to actually drive the dial as needed. The maths involved is worth checking out, particularly if you’re into old-school instrumentation from the 20th century.
We’ve seen similar tinkering efforts from [Glen] before, too
.
[Thanks to smellsofbikes for the tip!] | 7 | 3 | [
{
"comment_id": "6649092",
"author": "misrhop",
"timestamp": "2023-06-03T23:14:04",
"content": "“a big climb to push your fitness”to rapidly decrease chain life“a nice descent for the joy of careening down at high speed”to rapidly wear out wheel bearings",
"parent_id": null,
"depth": 1,
... | 1,760,372,279.110659 | ||
https://hackaday.com/2023/06/03/the-apple-silicon-that-never-was/ | The Apple Silicon That Never Was | Bryan Cockfield | [
"computer hacks",
"Retrocomputing"
] | [
"80's",
"apple",
"Apple Silicon",
"aquarius",
"arm",
"cray",
"development",
"powerpc",
"risc",
"supercomputer"
] | Over Apple’s decades-long history, they have been quick to adapt to new processor technology when they see an opportunity. Their switch from PowerPC to Intel in the early 2000s made Apple machines more accessible to the wider PC world who was already accustomed to using x86 processors, and a decade earlier they moved from Motorola 68000 processors to take advantage of the scalability, power-per-watt, and performance of the PowerPC platform. They’ve recently made the switch to their own in-house silicon,
but, as reported by [The Chip Letter], this wasn’t the first time they attempted to design their own chips from the ground up
rather than using chips from other companies like Motorola or Intel.
In the mid 1980s, Apple was already looking to move away from the Motorola 68000 for performance reasons, and part of the reason it took so long to make the switch is that in the intervening years they launched Project Aquarius to attempt to design their own silicon. As the article linked above explains, they needed a large amount of computing power to get this done and purchased a Cray X-MP/48 supercomputer to help, as well as assigning a large number of engineers and designers to see the project through to the finish. A critical error was made, though, when they decided to build their design around a stack architecture rather than a RISC. Eventually they switched to a RISC design, though, but the project still had struggled to ever get a prototype working. Eventually the entire project was scrapped and the company eventually moved on to PowerPC, but not without a tremendous loss of time and money.
Interestingly enough, another team were designing their own architecture at about the same time and ended up creating what would eventually become the modern day ARM architecture, which Apple was involved with and currently licenses to build their M1 and M2 chips as well as their mobile processors. It was only by accident that Apple didn’t decide on a RISC design in time for their personal computers. The computing world might look a lot different today if Apple hadn’t languished in the early 00s as the ultimate result of their failure to develop a competitive system in the mid 80s. Apple’s distance from PowerPC now
doesn’t mean that architecture has been completely abandoned, though
.
Thanks to [Stephen] for the tip! | 22 | 12 | [
{
"comment_id": "6649070",
"author": "Alphatek",
"timestamp": "2023-06-03T21:01:50",
"content": "Didn’t realise that Apple went into ARM having failed to develop their own processor. Seems like they’ve a long history of over-rating their own ability.",
"parent_id": null,
"depth": 1,
"rep... | 1,760,372,279.168184 | ||
https://hackaday.com/2023/06/03/adata-ssd-gets-liquid-cooling-but-not-everyones-convinced/ | ADATA SSD Gets Liquid Cooling, But Not Everyone’s Convinced | Lewin Day | [
"computer hacks",
"Parts"
] | [
"liquid cooling",
"ssd",
"ssds",
"storage",
"water cooling"
] | Solid-state drives (SSDs) were a step change in performance when it came to computer storage. They offered incredibly fast seek times by virtue of dispensing with solid rust for silicon instead. Now, some companies have started pushing the limits to the extent that their drives supposedly need liquid cooling,
as reported by
The Register.
The device in question is the ADATA Project NeonStorm, which pairs a PCIe 5.0 SSD with RGB LEDs, a liquid cooling reservoir and radiator, and a cooling fan. The company is light on details, but it’s clearly excited about its storage products becoming the latest piece of high-end gamer jewelry.
Notably though, not everyone’s jumping on the bandwagon. Speaking to
The Register,
Jon Tanguy from Crucial indicated that while the company has noted modern SSDs running hotter, it doesn’t yet see a need for active cooling. In their case, heatsinks have proven enough. He notes that NAND flash used in SSDs actually operates best at 60 to 70 C. However, going beyond 80 C risks damage and most drives will shutdown or throttle access at this point.
Realistically, you probably don’t need to liquid cool your SSDs, even if you’ve got the latest and greatest models. However, if you want the most tricked out gaming machine on Twitch, there’s plenty of
products out there that will happily separate you from your money
. | 19 | 5 | [
{
"comment_id": "6649026",
"author": "fuzzyfuzzyfungus",
"timestamp": "2023-06-03T17:35:04",
"content": "Color me skeptical.The m.2 slot just doesn’t provide all that much bus power(numbers seem to vary slightly; but the highest one I’ve found is in OCP m.2 carrier card specs; which are aimed at lea... | 1,760,372,279.225121 | ||
https://hackaday.com/2023/06/03/software-driving-hardware/ | Software Driving Hardware | Elliot Williams | [
"Hackaday Columns",
"Microcontrollers",
"Rants"
] | [
"microcontrollers",
"micropython",
"newsletter"
] | We were talking about [Christopher Barnatt]’s very insightful analysis of
what the future holds for the Raspberry Pi single board computers
on the
Podcast
. On the one hand, they’re becoming such competent computers that they are beginning to compete with lightweight desktop machines, instead of just being a hacker curiosity.
On the other hand, especially given the shortage and the increase in price that has come with the Pi’s expanding memory endowments, a lot of people who would “just throw in a Raspberry Pi” are starting to think more carefully about their options. Five years ago, this would have meant looking into what you could whip together on an Arduino-based platform, either on actual Arduino hardware or on an ESP8266 or similar, but that’s a very different beast from a programmer’s perspective. Working with microcontrollers used to be very different from working with even the smallest Linux machines.
These days, there is no shortage of microcontrollers that have enough memory – both flash and RAM – to support a higher-level environment like MicroPython. And if you think about it, MicroPython brings to the microcontrollers a lot of what people were using a Raspberry Pi for in projects anyway: a friendly interactive programming environment that was free of the compile-here, flash-there debug cycle. If you’re happy coding Python on a single-board Linux computer, you’ll be more or less happy coding in MicroPython or Circuit Python on a microcontroller.
And what this leaves us with, as hackers, is a fantastic spectrum of choices. Where before there was a hard edge between programming C on an 8-bit PIC or an AVR and working with something that had a full Linux operating system like a Pi, it’s all blurry now. And as the Pis, the Jetson, and all the other Linux SBCs are blurring the boundary with more traditional computers as they all become more competent and gain more computer-like peripherals. Nowadays your choice is much freer, and the hardware landscape more fluid. You don’t have to let software development concerns drive your hardware choices, and we think that’s a great thing.
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
! | 69 | 17 | [
{
"comment_id": "6648997",
"author": "al177",
"timestamp": "2023-06-03T14:19:39",
"content": "I’ve used MicroPython on ESP32 in a 6 hour intro to electronics class. We had them use Thonny as the IDE, which makes connectivity for terminal and file copying seamless. None of them had any embedded exper... | 1,760,372,279.524561 | ||
https://hackaday.com/2023/06/03/zelda-guardian-sculpture-tracks-humans-and-pets-via-camera/ | ZeldaGuardian Sculpture Tracks Humans And Pets Via Camera | Lewin Day | [
"Raspberry Pi"
] | [
"nintendo",
"raspberry pi",
"sentry",
"zelda"
] | In
The Legend of Zelda: Breath of the Wild
Guardians are a primitive form of sentry turret that tracks the player with a watchful eye. Inspired by this,
[npentrel] decided to whip up one of her own in the real world.
The build relies on a Raspberry Pi kitted out with its usual camera for machine vision purposes. It uses the Viam robot toolkit, which runs a machine learning model to detect pets and humans on the camera feed. The guardian then tracks any pets or humans that show up by turning its head, and thus the camera, with a servo controlled by a PWM signal via the Raspberry Pi’s GPIO pins. It’s all wrapped up in a nicely-decorated 3D printed model that really does look like something straight out of
Breath of the Wild.
Sentry projects are a great way to learn about electronics, mechanics, and image processing techniques. It’s funny to see how advanced and complicated these projects were
fifteen years ago
, compared to
how easy they are today
with modern machine learning libraries. How times change! | 3 | 2 | [
{
"comment_id": "6649007",
"author": "Dan",
"timestamp": "2023-06-03T16:10:18",
"content": "Was going to whinge that you’d just put a game screenshot as the image instead of a photo of the model, but eventually realised that is the model… wow…!",
"parent_id": null,
"depth": 1,
"replies":... | 1,760,372,279.263099 | ||
https://hackaday.com/2023/06/02/hackaday-podcast-221-the-future-of-the-raspberry-pi-sniffing-a-toothbrush-your-tactical-tool-threshold/ | Hackaday Podcast 221: The Future Of The Raspberry Pi, Sniffing A Toothbrush, Your Tactical Tool Threshold | Tom Nardi | [
"Hackaday Columns",
"Podcasts"
] | [
"Hackaday Podcast"
] | Editors Elliot Williams and Tom Nardi are back in the (virtual) podcast studio to talk the latest phase of the 2023 Hackaday Prize, the past, present, and future of single-board computers, and a modern reincarnation of the Blackberry designed by hardware hackers. They’ll also cover the current state of toothbrush NFC hacking, the possibilities of electric farm equipment, and a privately funded satellite designed to sniff out methane. Stick around till the end to find out if there really is such a thing as having too many tools.
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!
Or download all the things
!
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 221 Show Notes:
News:
Hackaday Prize 2023: This Challenge Makes It So Easy Being Green
What’s that Sound?
Recognize this week’s sound?
Fill out the form
and give us your best guess.
Interesting Hacks of the Week:
What Next For The SBC That Has Everything?
Can You Really Use The Raspberry Pi 4 As A Desktop Machine?
Beepberry Brings Memory LCD And A Physical Keyboard To Your Pi
Pretty Small Robot Is Capable, Nonetheless
Hacking A “Smart” Electric Toothbrush To Reset Its Usage Counter
Will Electric Tractors Farm Your Food?
DIY 3D Printed Rain Gauge Connects To Home Assistant
Quick Hacks:
Elliot’s Picks:
Hackaday Prize 2023: EyeBREAK Could Be A Breakthrough
Supercon 2022: [Jorvon Moss] Gives His Robots A Soul
Google Nest Hub Teardown
Tom’s Picks:
The CCTV Cameras That Recorded The Chernobyl Disaster And Aftermath
Electronic Connect 4 Console Doesn’t Use LCD
Hackaday Prize 2023: Low Cost Braille Embosser From 3D Printer Parts
Can’t-Miss Articles:
Methane-Tracking Satellites Hunt For Nasty Greenhouse Gas Emissions
Ask Hackaday: What’s Your “Tactical Tool” Threshold? | 2 | 1 | [
{
"comment_id": "6649115",
"author": "Foley Matthews",
"timestamp": "2023-06-04T02:07:48",
"content": "i tried dialling the number which censored the reveal of the answer but i couldn’t get through.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6650174",
... | 1,760,372,279.409091 | ||
https://hackaday.com/2023/06/02/ai-camera-imagines-a-photo-of-what-you-point-it-at/ | AI Camera Imagines A Photo Of What You Point It At | Lewin Day | [
"Artificial Intelligence",
"digital cameras hacks"
] | [
"ai",
"AI image generation",
"ai image generator",
"camera",
"not-a-camera"
] | These days, every phone has a camera, and few of us are ever without one. [Bjørn Karmann] has built an altogether not-camera, though, in the form of
the Paragraphica, powered by artificial intelligence.
The Paragraphica doesn’t actually take photographs at all. Instead, it uses GPS to determine the user’s current position. It then feeds the address, time of day, weather, and temperature into a paragraph which serves as a prompt for an AI image generator. It also uses data gathered from various APIs to determine points of interest in the immediate area, and feeds those into the prompt as well. It then generates an artificial image that is intended to bear some resemblance to the prompt, and ideally, the real-world scene. In place of a lens, it bears a 3D printed structure inspired by the star-nosed mole, which feels its way around in lieu of using its eyes.
Three dials on the Paragraphica control its action. The first dial controls the radius of the area which the prompt will gather data about; it’s akin to setting the focal length of the lens. The second dial provides a noise seed value for the AI image generator, and the third dial controls how closely the AI sticks to the generated textual prompt.
The results are impressive, if completely false and generated from scratch. The Paragraphica generates semi-believable photos of a crowded alley, a public park, and a laneway full of parked cars. It’s akin to telling a friend where you are and what you’re seeing over the phone, and having them paint a picture based on that description.
Through their
unique abilities and stolen data sets
, AI image generators are proving controversial to say the least. As all good art does, Paragraphica explores this and raises new questions of its own. | 20 | 9 | [
{
"comment_id": "6648778",
"author": "Abe",
"timestamp": "2023-06-02T15:42:58",
"content": "Thanks, I hate it.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648794",
"author": "Sean",
"timestamp": "2023-06-02T16:16:31",
"content": "... | 1,760,372,279.585054 | ||
https://hackaday.com/2023/06/02/this-week-in-security-barracuda-zyxel-and-the-backdoor/ | This Week In Security: Barracuda, Zyxel, And The Backdoor | Jonathan Bennett | [
"Featured",
"Hackaday Columns",
"News",
"Security Hacks",
"Slider"
] | [
"Gigabyte",
"libreoffice",
"This Week in Security"
] | Barracuda’s Email Security Gateway (ESG)
has had a vulnerability in it for years
. Tracked as CVE-2023-2868, this one was introduced back in version 5.1.3.001, and only got patched during the 9.2 development cycle. Specific build information on patched firmware has not been made available, but
a firmware build containing the patch was deployed on May 20
.
The flaw was a command injection bug triggered by .tar files attached to incoming emails. The appliance scans attachments automatically, and the file names could trigger the
qx
operator in a Perl script. It’s a nasty one, ranking a 9.4 on the CVSS scale. But the really bad news is that Barracuda found the vulnerability in the wild, and
they have found evidence of exploitation as far back as October 2022
.
There have been three malware modules identified on the compromised appliances. SALTWATER is a backdoor trojan, with the ability to transfer files, execute commands, and host network tunnels. SEASPY is a stealthier module, that looks like a legitimate service, and uses PCAP to monitor traffic and receive commands. And SEASIDE is a Lua module for the Barracuda SMTP monitor, and it exists to host a reverse shell on command. Indicators of Compromise (IOCs) have been published, and Barracuda recommends the unplug-and-remove approach to cleaning up an infection. The saving grace is that this campaign seems to have been targeted, and wasn’t launched against every ESG on the Internet, so maybe you’re OK.
Moxa, Too
And speaking of security software that has problems, the
Moxa MXsecurity appliance has a pair of problems
that could be leveraged together to lead to a complete device takeover. The most serious problem is a hard coded credential, that allows authentication bypass for the web-API. Then the second issue is a command-line escape, where an attacker with access to the device’s Command Line Interface (CLI) can break out and run arbitrary commands.
And Zyxel
And while we’ve talked about this one before, if you have an unpatched Zyxel Firewall on the internet,
you should just assume that it’s been compromised
. It’s a command injection flaw that was patched in late April, and allowed a single malicious UDP packet to compromise the machine. In the month since then, this vulnerability has been added to the Mirai botnet, and it looks like quite a few have fallen. And if you patched the previous problems, don’t rest, as there have been another pair of CVSS 9.8 severity flaws.
Gigabyte’s Backdoor
But who needs malware when you have OEM’s like these? One of the scary scenarios is a machine’s firmware getting compromised, and that firmware dropping files into your system on boot. Far-fetched? Apparently that’s exactly
what the official Gigabyte firmware does to launch the Gigabyte APP Center
.
A multi-step process, starting in the board’s firmware, writes a Windows executable to disk and sets registries values to launch the executable as a service. That service downloads and executes an update from from Gigabyte, potentially loaded over an unencrypted HTTP connection. And the encrypted connection? Accepts a self-signed certificate. It looks like this functionality allows anyone that can pull off a Man-in-the-Middle (MitM) attack to run arbitrary code on the machine. Not to mention the possibility of compromising Gigabyte’s update server, and loading malware on a bunch of machines at once. The only saving grace is that this firmware function is disabled by default on most machines, but Eclypsium did discover the issue by finding it enabled in the wild, so some percentage of machines have it enabled.
This is obviously really bad. Gigabyte is working to get this updated, but a problem like this one will have quite the tail, given how rarely most of us install motherboard updates. The good news is that there haven’t been any attacks found in the wild. The bad news is that the details have all been released, so watch out for someone to try to take advantage of it.
Android App Gone Bad
The iRecorder app on Android was added to the Play Store mid 2021, and pretty much did exactly what it claimed — record the screen. Nearly a year later, the app was updated to 1.3.8,
and added some less-wholesome capabilities
. It suddenly could record audio, and upload it and other files to a Command and Control (C&C) server. The app was reported and yanked from the store, but it’s unclear who is responsible for the campaign. It’s surprising that a malicious app designer would wait that long to weaponize an app, which raises the suggestion that this could have been a supply chain attack. Someone could have hacked the developer, and pushed malicious code surreptitiously.
Bits and Bytes
Wireshark has a new release, and this one actually
fixes some important security problems
. We don’t think about it much since wireshark uses PCAP to capture packets, rather than receive them directly, but this software has a bunch of data parsers built in to it. And just like any other software, it only takes a simple mistake for something malicious to break the code behind a parser.
Nextcloud has
a fun set of fresh vulnerabilities
. A couple of them are relatively high severity, but the most amusing is
a problem with logging out
. Turns out that not all of the user’s local session data was neutralized when hitting the logout button, and so the next user to authenticate would be logged in as the previous account. Whoops.
And Libreoffice has had an update fixing two notable issues. The first is
a floating frame feature
, which displays content from a linked document. That frame was loading content without prompting the user, leading to some potential security mitigation bypasses. And the second, more serious problem, is
an array index underflow
when parsing a malformed spreadsheet formula. There isn’t a Proof of Concept released for this one, but the LibreOffice folks believe that arbitrary code execution is possible as a result. So go forth and update! | 12 | 7 | [
{
"comment_id": "6648781",
"author": "xeon",
"timestamp": "2023-06-02T15:47:53",
"content": "the isp i worked for supplied zyxel, the problems never ended as we constantly got hit with ransomware.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648903",
... | 1,760,372,279.636555 | ||
https://hackaday.com/2023/06/02/is-minix-dead-and-does-it-matter/ | Is MINIX Dead? And Does It Matter? | Jenny List | [
"computer hacks"
] | [
"minix",
"operating system",
"unix"
] | Is MINIX dead?
OSnews is sounding its death-knell
, citing evidence from the operating system’s git log that its last updates happened as long ago as 2018. Given that
the last news story on the MINIX website is from 2016
and the last release version, 3.3, came out in 2014, it appears they they may have a point. But perhaps it’s more appropriate to ask not whether or not MINIX is dead, but whether indeed it matters that the venerable OS appears no longer in development. It started as an example to teach OS theory before becoming popular in an era when there were no other inexpensive UNIX-like operating systems for 16-bit microcomputers, but given that its successors such as Linux-based operating systems have taken its torch and raced ahead, perhaps its day has passed.
No doubt many of you will now be about to point out that MINIX
lives on unexpectedly baked into the management engine core on Intel microprocessors
, and while there’s some debate as to whether that’s still the case, you may have a point. But the more important thing for us isn’t whether MINIX is still with us or even whether it’s a contender, but what it influenced and thus what it was responsible for. This is being written on a GNU/Linux operating system, which has its roots in
[Linus Torvalds]’ desire to improve on… MINIX
.
Read more about the tangled web of UNIX-like operating systems
here
. | 51 | 17 | [
{
"comment_id": "6648705",
"author": "segm2",
"timestamp": "2023-06-02T11:03:38",
"content": "Who cares? But I’ll shed a tear after RTEMS.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648709",
"author": "Andrew",
"timestamp": "2023-06-02T11:09:34",
... | 1,760,372,279.72635 | ||
https://hackaday.com/2023/06/02/wii-xl-is-twice-as-nice/ | Wii XL Is Twice As Nice | Navarre Bartz | [
"Nintendo Wii Hacks"
] | [
"Case mods",
"console hack",
"nintendo",
"nintendo wii"
] | The Wii was a relatively small console when it released, but it packed a big punch when it came to its game library and the impact it had on the industry. [Bringus Studios] wanted a Wii that physically matched the grandeur of one of Nintendo’s greatest successes, and
built the Wii XL
.
Basing the scale of this console around an 80 mm case fan, the final product has twelve times the volume of the original Wii. This leaves plenty of room for an unmodified original Wii, its power brick, and all the various cables and adapters necessary to bring the ports to the exterior of the case. To power the fan, [Bringus Studios] designed his first PCB to leach power off one of the USB connectors while still allowing data to pass through.
Given the size constraints of his 3D printers, he used melamine MDF for the sides and had to print the other panels in multiple pieces, resulting in some gapping in the front panel where the prints peeled off the print bed. We really love the use of a modular design that leaves room for future improvements, since no project is ever truly done.
Power is routed through a figure eight power connector on the outside to a female two prong plug on the inside while USB and HDMI are routed out the back via a combination panel connector intended for RV and boat use. If you don’t remember the Wii having HDMI out, that’s because it didn’t, but HDMI adapters are easy to come by for the machine.
In case you want to see more supersized projects checkout this giant
XBox Series X
or ponder if it would’ve been better with an
enormous 555
. | 17 | 7 | [
{
"comment_id": "6648674",
"author": "ono",
"timestamp": "2023-06-02T08:31:26",
"content": "Cool. I guess you can even store frozenhot-dogs in it. Very useful.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6649478",
"author": "Tyler Hovanec",
... | 1,760,372,280.10987 | ||
https://hackaday.com/2023/06/01/commodore-64-web-server-brings-8-bit-into-the-future/ | Commodore 64 Web Server Brings 8-Bit Into The Future | Lewin Day | [
"Retrocomputing"
] | [
"c64",
"commodore 64",
"retrocomputer",
"retrocomputing",
"web server"
] | These days, most webservers are big hefty rackmount rigs with roaring fans in giant datacenters. [naDDan]’s webserver is altogether more humble,
as it runs on a single Commodore 64.
The C64 is running Contiki OS, an operating system for 6502-based computers. It’s built with an eye to networking, requiring ethernet hardware for full functionality. In [naDDan]’s case, he’s outfitted his C64 with an ETFE network adapter in the cartridge port to get it online. It serves up the HTML file off a 1541C floppy drive, with the drive buzzing away every time someone loads up the page.
The page itself is simple, showing some basic information on a simple blue background. There is some scrolling text though, as is befitting the 8-bit era. It’s also available in four languages.
[naDDan’s] server can be found
here
, according to his video, but at the time of writing, it was down for the count. Whether that’s due to a dynamic DNS issue or the simple fact that
an 8-bit 6502
isn’t up to heavy traffic is up for debate. Regardless, try for yourself and see how you go. Video after the break. | 28 | 16 | [
{
"comment_id": "6648642",
"author": "Derek Tombrello",
"timestamp": "2023-06-02T05:13:36",
"content": "I have several c64s. I would love to use one to run the web server for my shop. It’s a simple small engine shop, so it’s a simple site, currently running on a libre (pi-like) single board computer... | 1,760,372,279.791921 | ||
https://hackaday.com/2023/06/01/watch-out-sic-diamond-power-semiconductors-are-coming-for-you/ | Watch Out SiC, Diamond Power Semiconductors Are Coming For You! | Dave Rowntree | [
"Science"
] | [
"Diamfab",
"diamond",
"GaN",
"power electronics",
"semiconductor",
"SiC"
] | The vast majority of semiconductors products we use every day are primarily constructed on a silicon process, using wafers of pure silicon. But whilst the economics are known, and processes mature, there are still some weaknesses. Especially for power applications. gallium nitride (GaN) and silicon carbide (SiC) are materials that have seen an explosion in uses in the power space, driven especially by an increase in electric vehicle sales and other high-power/high-voltage systems such as solar arrays. But, SiC is expensive and very energy intensive. It looks like diamond substrates could become much more common if the
work by Diamfab takes off
.
Diamond, specifically thin films of synthetic diamond formed on a suitable substrate, exhibits many desirable properties, such as a vastly superior maximum electric field compared with silicon, and a thermal conductivity five times better than copper. Such properties give diamond structures a big power and voltage advantage over SiC, which is in turn a lot better the pure silicon. This also means that diamond-based transistors are more energy efficient, making them smaller and cheaper, as well as better performing. Without the high formation temperatures needed for SiC, diamond could well be their downfall, especially once you factor in the reduced environmental impact. There is even some talk about solid-state, high-voltage diamond insulator capacitors becoming possible. It certainly is an interesting time to be alive!
We do cover news about future semiconductors from time to time, like this
piece about cubic boron arsenide
. We’ve also seen
diamond being used as a battery
, albeit a very weak radiative one.
[via EETimes] | 24 | 6 | [
{
"comment_id": "6648622",
"author": "jenningsthecat",
"timestamp": "2023-06-02T02:25:12",
"content": "You might want to correct the title. It took me a few beats to realize that the substance in question is “SiC”, (silicon carbide), and not “SIC”.",
"parent_id": null,
"depth": 1,
"repli... | 1,760,372,279.848054 | ||
https://hackaday.com/2023/06/01/ir-camera-is-excellent-hacking-platform/ | IR Camera Is Excellent Hacking Platform | Bryan Cockfield | [
"digital cameras hacks"
] | [
"camera",
"doom",
"Imaging",
"lens",
"linux",
"modifications",
"serial port",
"SoC",
"temperature",
"Thermal",
"webcam"
] | While there have been hiccups here and there, the general trend of electronics is to decrease in cost or increase in performance. This can be seen in fairly obvious ways like more powerful and affordable computers but it also often means that more powerful software can be used in other devices without needing expensive hardware to support it. [Manawyrm] and [Toble_Miner] found this was true of a particular inexpensive thermal camera that ships with Linux installed on it, and found that this platform was nearly perfect for tinkering with and
adding plenty of other features to turn it into a much more capable tool
.
The duo have been working on a SC240N variant of the InfiRay C200 infrared camera, which ships with a Hisilicon SoC. The display is capable of displaying 25 frames per second, making this platform an excellent candidate for modifying. A few ports were added to the device, including USB and MicroSD, and which also allows the internal serial port to be accessed easily. From there the device can be equipped with the uboot bootloader in order to run essentially anything that could be found on any other Linux machine such as supporting a webcam interface (and
including a port of DOOM
, of course). The duo doesn’t stop at software modifications though. They also equipped the camera with a lens, attached magnetically, which changes the camera’s focal length to give it improved imaging capabilities at closer ranges.
While the internal machinations of this device are interesting, it actually turns out to be a fairly capable infrared camera on its own as well. The hardware and software requirements for these devices certainly don’t need a full Linux environment to work, and while we have seen thermal cameras that easily fit in a pocket that are based on
nothing any more powerful than an ESP32
, it does tend to simplify the development process dramatically to include Linux and a little more processing power if you can. | 14 | 4 | [
{
"comment_id": "6648587",
"author": "Ostracus",
"timestamp": "2023-06-01T23:34:50",
"content": "Resolution seems to be the issue with most cheap IR cams.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648594",
"author": "Andrew",
"timestamp... | 1,760,372,279.996643 | ||
https://hackaday.com/2023/06/01/flexible-actuator-flaps-for-100000000-cycles-without-failure/ | Flexible Actuator Flaps For 100,000,000 Cycles Without Failure | Lewin Day | [
"hardware"
] | [
"flex PCB",
"flexible actuator",
"flexled"
] | Flexible PCBs are super-useful things, but they can have a limited fatigue life. [Carl Bugeja] has been using them to create flexible actuators, though,
and he’s getting an amazing 100,000,000 cycles out of them after some rigorous development.
[Carl] explores all manner of optimizations to his flippy actuators in the video. He tried making them oscillate faster by putting a hole in the middle to reduce drag. Other tricks include getting the arm thickness just right, and experimenting with rigidity through adding or removing sections of soldermask.
Fundamentally, though, he learned the key to longevity laid in the copper traces on the flex PCBs themselves. After enough flexural cycles, the traces would fail, killing the actuator. He experimented with a variety of solutions, eventually devleoping a ruggedized two-arm version of his actuator. Twenty samples were put to the test, oscillating at 25 Hz for two weeks straight. All samples survived the test, in which they were put through around 107,820,000 cycles.
[Carl] has put in plenty of hard work on this project, and his actuators have come a long way
since we saw them last.
He hopes to use the better actuators to improve
his FlexLED display.
Video after the break. | 23 | 8 | [
{
"comment_id": "6648550",
"author": "Mr Beniz",
"timestamp": "2023-06-01T21:44:14",
"content": "With proper magl-ev bearing and powerful enough solenoids it should be possible to create a toilet seat that can toggle between “open” and “closed” states with frequency of 100 kHz or more. It may create... | 1,760,372,280.055332 | ||
https://hackaday.com/2023/06/01/hackaday-prize-2023-building-a-relay-alu/ | Hackaday Prize 2023: Building A Relay ALU | Dave Rowntree | [
"computer hacks",
"The Hackaday Prize"
] | [
"2023 Hackaday Prize",
"adder",
"ALU",
"arduino",
"computer",
"logic",
"relay"
] | There’s much truth in the advice that, to truly understand something, you need to build it yourself from the ground up. That’s the idea behind [Christian]’s entry for the
Re-engineering Education
category of the 2023 Hackaday Prize. Built as an educational demonstrator, this is
a complete arithmetic-logic unit (ALU) using discrete relays
— and not high-density types either — these are the big honking clear-cased kind.
The design is neatly, intentionally, partitioned along functional lines, with four custom PCB designs, each board
operating on 4-bits. To handle a byte-length word, boards are simply cascaded, making a total of eight. The register, adder, logic function, and multiplex boards are the heart of the build with an additional two custom boards for visualization (using an Arduino for convenience) and IO forming the interface. After all, a basic CPU is just an ALU and some control around it, the magic is really in the ALU.
The fundamental logical operations operating upon two operands, {A, B} are A, ~A, B, ~B, A or B, A and B, A xor B, can be computed from just four relays per bit. The logic outputs do need to be fed into a 7-to-1 bit selector before being fed to the output register,
but that’s the job of a separate board. The adder function is the most basic, simply a pair of half-adders and an OR-gate to handle the chaining of the carry inputs and generate the carry chain output.
3D printed cable runs are a nice touch and make for a slick wiring job to tie it all together.
For a more complete relay-based CPU, you could check out
the MERCIA relay computer project
, not to mention this
wonderfully polished build
.
The
Hackaday
Prize 2023
is Sponsored by: | 9 | 4 | [
{
"comment_id": "6648528",
"author": "spaceminions",
"timestamp": "2023-06-01T19:43:42",
"content": "I like the 4-relay-per-bit thing. It’s so nice to try and make logic when you can manage to get the inputs and their complements at full strength as well as at least some of the other operations.At o... | 1,760,372,280.165266 | ||
https://hackaday.com/2023/06/01/books-you-should-read-red-team-blues/ | Books You Should Read:Red Team Blues | Jonathan Bennett | [
"Hackaday Columns",
"Reviews"
] | [
"books you should read",
"cory doctorow",
"cryptocurrency"
] | Martin Hench really likes playing on the Red Team — being on the attack. He’s a financial geek, understands cryptocurrency, understands how money is moved around to keep it hidden, and is really good at mining data from social media. He puts those skills together as a forensic accountant. Put simply, Martin finds money that people want hidden. Against his better judgment, Marty does the job of a lifetime, and makes an absolute mint. But that job had hair, and he’s got to live through the aftermath. It turns out, that might just be a challenge, as three separate groups want a piece of him.
Red Team Blues
, a work of fiction by [Cory Doctorow] about cryptocurrency, trust, finance, and society as a whole. When [Doctorow] offered to send us a copy to review, we jumped at the chance, and can give it a hearty recommendation as a fun and thoughtful tale. The moral seems to be that while everyone plays the sordid finance game, the government should really work harder to disentangle the mess, but maybe we would do better if more people opted for integrity. There is also a real point to be made about the dark side of cryptocurrency, in that it enables crime, ransomware, and money laundering on a global scale. For all the pluses for privacy and anonymity, there’s some real downsides. The characters spend most of the book wrestling with that dichotomy in the background.
The book took something of a moralizing turn just over halfway through. Which, depending on your viewpoint, you’ll either really appreciate, or have to hold your nose a bit to get through. But the suspense pulls the reader through it, making for an overall enjoyable read. As an added bonus, you might end up with a better mental image of how the pieces of digital privacy, finance, and the real world all fit together.
The book has all the fun references to Tor, Signal, Bitcoin, and computer history you could want. And the central MacGuffin is an interesting one: a cryptocurrency that runs on proof-of-secure-enclave, eliminating the ridiculous power consumption of proof-of-work schemes. All of this with some rich Silicon Valley lore setting up the background. Our conclusion? Two wrenches up. | 12 | 7 | [
{
"comment_id": "6648484",
"author": "KDawg",
"timestamp": "2023-06-01T17:45:10",
"content": "I never learned to read you insensitive clod",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648525",
"author": "Paul",
"timestamp": "2023-06-01T19:... | 1,760,372,280.252294 | ||
https://hackaday.com/2023/06/01/old-clock-transformed-into-mesmerizing-light-display/ | Old Clock Transformed Into Mesmerizing Light Display | Lewin Day | [
"clock hacks"
] | [
"cd",
"clock",
"Compact Disc"
] | It’s easy to find a cheap clock at any dollar store that will manage to tell the time, but chances are that the plastic-fantastic construction won’t do you any aesthetic favors. Fear not, though, for [ROBO HUB]’s upcycled design
turns a humble clock into a mesmerizing horological display of beauty.
The build starts by scavenging the movement out of a cheap plastic clock. A CD is then glued to the front of the movement to serve as a reflective backing plate. For numerals, the clock uses F3, F6, F9, and F12 keys nabbed from a keyboard.
The real party trick, though, is in the lighting. This build is elevated beyond hackneyed 90s desk clocks by the inclusion of a ring of LED strip lighting. When switched on, the LED light reflects and refracts on the surface of the CD, creating a mesmerizing shifting pattern featuring all the colors of the rainbow.
CDs are actually quite magical from an optical perspective
and have all kinds of nifty uses. | 4 | 3 | [
{
"comment_id": "6648476",
"author": "ono",
"timestamp": "2023-06-01T17:30:12",
"content": "Looks really nice, + minimalist approach, really cool!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648582",
"author": "Staple_nutz",
"timestamp": "2023-06-0... | 1,760,372,280.206316 | ||
https://hackaday.com/2023/06/01/farewell-american-computer-magazines/ | Farewell American Computer Magazines | Al Williams | [
"Current Events",
"Featured",
"Original Art",
"Rants",
"Slider"
] | [
"magazine",
"Rant"
] | I grew up in a small town with a small library. The next town over had what I thought at the time was a big library, but it was actually more like my town had a tiny library, and the next one over had an actual small library. When I left to go to University, I found out what a real library looked like, and I was mesmerized. Books! Lots of books, many of them written in the current decade. My grades probably suffered from the amount of time I spent in the library reading things that didn’t directly relate to my classes. But there was one thing I found that would turn out to be life-changing: A real computer magazine. Last month, Harry McCracken pointed out that the last two
widely-distributed American consumer computer magazines ceased paper publication
. It is the end of an era, although honestly, it is more like a comatose patient expiring than a shocking and sudden demise.
Dr. Dobb’s first issue was far from the slick commercial magazine it would become.
Actually, before I had gone to college, I did have a subscription to Kilobaud, and I still have some copies of those. No offense to Wayne Green, but Kilobaud wasn’t that inspiring. It was more an extension of his magazine “73”, and while I enjoyed it, it didn’t get me dreaming. Dr. Dobb’s Journal — the magazine I found in the stacks of my University’s library — was tangibly different. There was an undertone of changing the world. We weren’t sure why yet, but we knew that soon, everyone would have a computer. Maybe they’d balance their checkbook or store recipes. A few people already saw the potential of digital music reproduction, although, I must admit, it was so poor at the time, I couldn’t imagine who would ever care.
I say it was life-changing to discover the few issues of Dr. Dobb’s that were published back then because I would go on to contribute to Dr. Dobb’s throughout its storied history. I wrote the infamous DOS extender series, produced special issues, and, when it went mostly digital, was the embedded system blogger for them for more years than I care to admit. In fact, I have the dubious distinction of having the final blog posted; although the website has suffered enough bit rot, I’m not sure any of it has survived other than, maybe, on the Wayback machine. While I wasn’t with the magazine for its entire 38-year run, I read it for at least 35 and had some function there for about 24 of those.
$2 bought a lot of computer magazine in 1977!
Like a lot of nostalgia, you miss it, but it isn’t coming back. You can argue for or against it, but it doesn’t really matter.
What I think Harry got right his thought piece, though, is that while digital distribution and access are awesome — look at Hackaday, for example — the magazine industry failed to figure out how to stay solvent. McCracken points out that substantial ad revenue fueled huge test labs and hardline investigative journalism in addition to the physical printing. Don’t forget that old-school magazines never made money from your subscriptions either, it was all in the ads. Now, it is hard to generate that kind of revenue and, therefore, to provide those kinds of services. So even if you prefer digital — I do — the big money is mostly gone and gone forever, it seems.
Hard to imagine if the lads needed a day job
Imagine a world where music is easily distributed for free. You’d hear a lot more music, and, in fact, you do today because independent artists can easily reach listeners directly. But how would the Beatles catalog be different if George, Paul, John, and Ringo needed day jobs? You’d imagine they might produce less and maybe even very different music.
Then again, day jobs may be in short supply soon, too, at least the ones a bunch of young musicians might take. Order taker at a fast food restaurant? That’ll be AI soon enough. Fry cook? That’s already probably a robot arm.
You have to wonder if the destruction of traditional media — TV, movie theaters, magazines, newspapers, books, and record labels — will lead to a different way to compensate creators fairly or if the jobs related to creation will just eventually dwindle to nothing but volunteers. Either way, the days of the big computer magazine is gone, just like the days you could make a living
harvesting ice
. | 80 | 30 | [
{
"comment_id": "6648427",
"author": "Nico Verduin",
"timestamp": "2023-06-01T14:32:43",
"content": "This sounds familiar.. I bought a KIM-1 sometime around 1976/77 here in Holland. And I found a PC store (well PC store? eh-m) that sold US magazines. I spent a fortune on magazines and books in thos... | 1,760,372,280.452447 | ||
https://hackaday.com/2023/06/01/getting-a-close-up-view-of-chip-formation-with-an-sem/ | Getting A Close-Up View Of Chip Formation With An SEM | Dan Maloney | [
"Science"
] | [
"Carbide",
"chip formation",
"chips",
"electron microscope",
"metalwork",
"sem",
"shear zone"
] | When all you’ve got is a hammer, everything looks like a nail. And when you’ve got a scanning electron microscope, everything must look like a sample that would be really, really interesting to see enlarged in all its 3D glory. And this is what [Zachary Tong] delivers with
this up close and personal look at the chip formation process
.
We’ve got to hand it to [Zach] with this one, because it seems like this was one of those projects that just fought back the whole time. Granted, the idea of cutting metal inside the vacuum chamber of an SEM seems like quite an undertaking right up front. To accomplish this, [Zach] needed to build a custom tool to advance a cutting edge into a piece of stock by tiny increments. His starting point was a simple off-the-shelf linear stage, which needed a lot of prep work before going into the SEM vacuum chamber. The stage’s micrometer advances a carbide insert into a small piece of aluminum 50 microns at a time, raising a tiny sliver of aluminum while it slowly plows a tiny groove into the workpiece.
Getting the multiple shots required to make a decent animation with this rig was no mean feat. [Zach]’s SEM sample chamber doesn’t have any electrical connections, so each of the 159 frames required a painstaking process of advancing the tool, pulling down a vacuum in the chamber, and taking a picture. With each frame taking at least five minutes, this was clearly a labor of love. The results are worth it, though; stitched together, the electron micrographs show the chip formation process in amazing detail. The aluminum oxide layer on the top of the workpiece is clearly visible, as are the different zones of cutting action. The grain of the metal is also clearly visible, and the “gumminess” of the chip is readily apparent too.
For as much work as this was, it seems like [Zach] had things a bit easier than [Ben Krasnow] did when
he tried something similar
with a much less capable SEM. | 16 | 2 | [
{
"comment_id": "6648389",
"author": "C",
"timestamp": "2023-06-01T11:35:35",
"content": "I wonder if you can make a mechanical clock like system that moves it automatically in small increments or continuously (without too much vibration). That way you don’t have to open the chamber to take snapshot... | 1,760,372,280.618815 | ||
https://hackaday.com/2023/06/01/tinytendo-is-a-miniscule-yet-real-nes/ | TinyTendo Is A Miniscule Yet Real NES | Lewin Day | [
"Nintendo Hacks"
] | [
"nes",
"nintendo",
"tinytendo"
] | These days, it’s possible to get a single-board computer the size of a stick of gum. This will give you the power to emulate thousands of games and you can run one off batteries inside a handheld of your own devising. [Redherring32] took an altogether more creative and old-school approach with the TinyTendo, however.
This is one pocket-sized NES that actually runs on genuine hardware
. (
Nitter
)
The feat was achieved by drastically reducing the size of the original NES hardware to make it fit into a Game Boy style form factor. Key to this work was creating a custom cut-sized motherboard which uses original Nintendo DIP chips that have been machined down to become
more like QFN-style surface mount packages.
With that done, the chips can be assembled onto the TinyTendo PCB which is even smaller than a contemporary Raspberry Pi 3. It’s all assembled in a custom case, with USB C for charging and a bright and colorful LCD screen.
The TinyTendo is designed to use mini-cartridges created by [Bucket Mouse], a hacker
who’s no stranger to impressive custom Game Boy hardware
. By virtue of running genuine NES hardware, there’s also the possibility that the TinyTendo could play full-sized NES carts with a simple adapter.
This project has been a long time in the making; we first looked at [Redherring32]’s efforts
back in 2021.
It begs the question why the original NES was so big when Nintendo clearly had plenty of space to spare in those hefty DIP packages! It’s amazing what can be done with some creativity and perseverance.
This is TinyTendo, a real hardware NES handheld that is the size of the original GameBoy.
This is not emulation, it is not a Pi, it is not a NOAC, and it is not an FPGA.
This is real NES hardware from a real NES.
This project will also be open sourced in a few weeks.
pic.twitter.com/Csf10EYPcc
— Redherring32 (@redherring32)
May 24, 2022 | 3 | 3 | [
{
"comment_id": "6648457",
"author": "Hobo Lobo",
"timestamp": "2023-06-01T16:00:38",
"content": "> why the original NES was so bigas a unit, the original NES was so big because the designers wanted it to be taken seriously by the American market and designed it to look and work like something that ... | 1,760,372,280.551327 | ||
https://hackaday.com/2023/05/31/a-simple-guide-to-cams/ | A Simple Guide To Cams | Danie Conradie | [
"Parts"
] | [
"automata",
"cams",
"camshaft"
] | With the availability of precision controllable actuators, it’s easy to overlook the simple but versatile mechanisms that got us here. In the video after the break, [Teaching Tech] explores the
basics of cams
and how to use them in your projects.
Cams are used to convert rotation into linear motion, and are probably best known for their use in engines and locking mechanisms. [Teaching Tech] first goes over the basic design and terminology in CAD, and demonstrates it’s use with a cam follower, locking mechanism, cam plate, and a knob that snaps to predefined positions. Of course a cam shape is not limited to a single lobe, but can have multiple lobes of various heights to create different motion patterns.
Cams are especially useful when you need to operate multiple mechanisms from a single input drive, as [Teaching Tech] demonstrates with the 3D printed automaton of a polar bear attempting to swipe a seal. We’ve also seen cams on a
mechanical 7-segment display
, and they were used to safely
fire machine guns through aircraft propellers
up to the 1950’s.
So next time you’re thinking adding another actuator to a project, take a moment to consider if a cheap and simple cam could do the job. | 10 | 4 | [
{
"comment_id": "6648354",
"author": "YGDES",
"timestamp": "2023-06-01T05:15:15",
"content": "So it’s not the end of the cam era ?…",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648373",
"author": "Andrew",
"timestamp": "2023-06-01T09:37:25... | 1,760,372,280.499947 | ||
https://hackaday.com/2023/05/31/neural-network-helps-with-radar-pipeline-diagnostics/ | Neural Network Helps With Radar Pipeline Diagnostics | Lewin Day | [
"Machine Learning"
] | [
"ai",
"mmwave",
"neural network",
"pipeline",
"radar"
] | Diagnosing pipeline problems is important in industry to avoid costly or dangerous failures from cracked, broken, or damaged pipes. [Kutluhan Aktar] has built an system
that uses AI to assist in this difficult task
.
The core of the system is a MR60BHA1 60 GHz mmWave radar module, which is most typically used for breathing and heartrate detection. Here, it’s repurposed to detect fluctuating vibrations as a sign that a pipeline may be cracked or damaged. It’s paired with an Arduino Nicla Vision module, with the smart camera able to run a neural network model on the captured radar data to flag potential pipe defects and photograph them. The various modules are assembled on a PCB resembling Dragonite, the Dragon/Flying-type Pokemon.
[Kutluhan] walks us through the whole development process, including the creation of a web interface for the system. Of particular interest is the way the neural network was trained on real defect models that [Kutluhan] built using PVC pipe.
We’ve looked at industrial pipelines in detail before, too
. Video after the break. | 3 | 3 | [
{
"comment_id": "6648411",
"author": "Ostracus",
"timestamp": "2023-06-01T12:53:20",
"content": "Same idea for roads (which need it coming out of winter).https://www.cyclomedia.com/us/producten/data-insights/road-surface-analysis",
"parent_id": null,
"depth": 1,
"replies": []
},
{
... | 1,760,372,280.886387 | ||
https://hackaday.com/2023/05/31/more-ideas-for-setting-up-an-electronics-workbench/ | More Ideas For Setting Up An Electronics Workbench | Dave Rowntree | [
"hardware",
"Tool Hacks"
] | [
"bench equipment",
"electronics",
"organisation",
"solder fume extractor",
"workarea"
] | Setting up an electronics work area is a highly personal and situational affair, with many interesting problems to be solved, and for many of us, significant budget constraints. The requirements for electronics development vary wildly depending upon the sort of work to be undertaken, but there is core equipment that many of us would consider a bare minimum for usability. [Badar Jahangir Kayani] is at the start of his career as an electrical engineer, and has
documented the kitting out of his personal work areas
for others to learn from.
A place for everything, everything in its place
As we already touched upon, the cost is often the main driving factor determining what we end up with, and this cost-vs-performance/quality tradeoff is what makes some of us fret over a buying decision. Buying secondhand off eBay is an option, but a lack of warranty and the unknowable condition are not great selling points.
[Badar] has a good grasp of the basic concepts of usability, such as keeping the most frequently used tools, instruments, and components out in the open. Less frequently used stuff is stored in drawers, bins, and compartment boxes. Buying the same storage systems keeps things as consistent as much as possible since it makes storing them easier. We were particularly interested in the use of the cloud-based database solution,
Airtable used to create a parts database
for minimal outlay.
Oooh! Cable tray action
There is also a lot of detail about how to walk that cost/quality/performance tightrope and get the best-valued gear currently on the market. Some notable examples are the UNI-T UT61E Digital Multimeter for general test use, the Controleo3 reflow controller for SMT assembly, and the Omnifixo OF-M4 magnetic fixament kit for that fiddly wiring part. [Badar] also recommends the
FumeClear Solder Fume Extractor, although they lament that particular bit of kit is still under evaluation.
Obviously, we’ve talked about work areas a lot on these pages,
like this time
. For those with more space, this
flippin’ awesome bench
will be of interest, and if space is tight (or travel is a regular thing) might we suggest this
3D printed DIN-rail mounting cube
as a starting point? | 37 | 20 | [
{
"comment_id": "6648306",
"author": "DerAxeman",
"timestamp": "2023-05-31T23:28:04",
"content": "A built-in mini fridge is a must for me.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6649175",
"author": "Tracy A Scott",
"timestamp": "2023-... | 1,760,372,280.719576 | ||
https://hackaday.com/2023/05/31/can-hobbyists-bring-sgis-irix-os-back-to-life/ | Can Hobbyists Bring SGI’s IRIX OS Back To Life? | Lewin Day | [
"News",
"Retrocomputing",
"Reverse Engineering"
] | [
"irix",
"operating system",
"sgi",
"silicon graphics"
] | Irix was the operating system developed by Silicon Graphics from 1988 to 1998. The OS supported the company’s high-end workstations and served in many serious roles. The company cut off support for the UNIX-based OS in 2006,
but now a diehard community is looking to bring the ancient codebase back to life.
SGI workstations used to cost big money before the company collapsed. It failed to make the leap to a new era when x86 architecture began to dominate the wider computing industry. Credit:
Bruno Cordioli,
CC-BY-2.0
While SGI’s workstations once sold for five or six figures, surviving examples can now often be had for just a few hundred dollars on eBay. The MIPS-based hardware was potent for its time, often used for 3D rendering work for video games, films, or for scientific purposes. IRIX was SGI’s own OS built specifically to support these use cases.
The IRIX Network is a hobbyist community that loves these old machines and their software. The group hopes to raise $6,500 through crowdfunding to reverse-engineer IRIX. The hope is to use those learnings to create an open-source derivative version named IRIX-32, based on IRIX 5.3, the last 32-bit version of the OS.
It’s a monumental task, but admirable nonetheless. Whether we one day see IRIX reborn,
akin to what happened to AmigaOS
, remains to be seen. | 33 | 14 | [
{
"comment_id": "6648260",
"author": "Julian Skidmore",
"timestamp": "2023-05-31T20:23:13",
"content": "Cool, maybe I can run it on my Indy (64-bit computer from the mid 1990s!!!) :-)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648263",
"author": "Seve... | 1,760,372,280.845842 | ||
https://hackaday.com/2023/05/31/hackaday-prize-2023-low-cost-braille-embosser-from-3d-printer-parts/ | Hackaday Prize 2023: Low Cost Braille Embosser From 3D Printer Parts | Danie Conradie | [
"Tech Hacks",
"The Hackaday Prize"
] | [
"2023 Hackaday Prize",
"assistive device",
"braille",
"braille printer"
] | The limited availability of texts transcribed to Braille and the required embossing equipment is a challenge world wide, but especially in poorer countries. To alleviate this problem, a team makers from in Cameroon have been developing
BrailleRAP
, an open source Braille embosser.
BrailleRAP is built built using commonly available 3D printer components, printed parts, and a laser-cut acrylic or wood frame. Paper is fed between a pair of carriages, the bottom one punching dots with a solenoid while the other acts as the anvil. Sheets of paper are fed in one or two at a time with stepper controlled rollers to control the position. At a cost of about $250, it is about a tenth of the price of the cheapest commercial solution, and the team have created
excellent documentation
so anyone can build it.
BrailleRAP was inspired by
BRAIGO
, another Hackaday-featured embosser assembled
LEGO Mindstorm
parts. We also featured another simple, but ingenious
handheld embosser
for portable use.
The
Hackaday
Prize 2023
is Sponsored by: | 8 | 4 | [
{
"comment_id": "6648231",
"author": "Jason O'Donnell",
"timestamp": "2023-05-31T18:45:55",
"content": "Nice!",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6648264",
"author": "CRJEEA",
"timestamp": "2023-05-31T20:37:36",
"content": ... | 1,760,372,280.928057 | ||
https://hackaday.com/2023/05/31/hackaday-prize-2023-this-challenge-makes-it-so-easy-being-green/ | Hackaday Prize 2023: This Challenge Makes It So Easy Being Green | Elliot Williams | [
"contests",
"green hacks",
"Hackaday Columns"
] | [
"2023 Hackaday Prize",
"environmental",
"prize"
] | This year’s
Hackaday Prize
is our first nice round number – number ten! We thought it would be great to look back on the history of the Prize and cherry-pick our favorite themes from the past. Last year’s entire theme was sustainable hacking, and we challenged you to come up with ways to generate or save power, keep existing gear out of the landfill, find clever ways to encourage recycling or build devices to monitor the environment and keep communities safer during weather disasters, and you all came through. Now we’re asking you to do it again.
There are hundreds of ways that we can all go a little bit lighter on this planet, and our Green Hacks Challenge encourages you to make them real. Whether you want to focus on clean energy, smarter recycling, preventing waste, or even cleaning up the messes that we leave behind, every drop of oil left unburned or gadget kept out of the landfill helps keep our world running a little cleaner. Here’s your chance to hack
for
the planet.
Inspiration
One thing we really loved about last year’s Green Hacks was that it encouraged people to think outside the box. For instance, we got some solar power projects as you’d expect, but we also got a few really interesting wind power entries, ranging from the superbly polished
3D Printed Portable Wind Turbine
that won the Grand Prize to the experimental kite turbine in
Energy Independence While Travelling
, to say nothing of the offbeat research project toward making a
Moss Microbial Fuel Cell
.
3D Printed Portable Wind Turbine
Moss Microbial Fuel Cell
Energy Independence While Travelling
Plastic was also in the air last year, as we saw a number of projects to reuse and recycle this abundant element of our waste stream. From a
Plastic Scanner
that uses simple spectroscopy to determine what type of plastic you’re looking at, to
filament recyclers
and
trash-based 3D printers
to make use of shredded plastic chips.
Polyformer
The Trash Printer – Version 3
Plastic Scanner
Finally, you all really put the science into citizen science with projects like
OpenDendrometer
that helps monitor a single tree’s health, and the
Crop Water Stress Sensor
that does the same for a whole field. Bees didn’t get left out of the data collection party either, with the
Beehive Monitoring and Tracking
project. And [Andrew Thaler]’s tremendously practical
Ocean Sensing for Everyone: The OpenCTD
brought the basics of oceanic environmental monitoring down to an affordable level.
OpenDendrometer
Crop Water Stress Sensor
Beehive Monitoring and Tracking
Ocean Sensing for Everyone: The OpenCTD
Now It’s Your Turn to be Green
If any of the above resonates with your project goals, it’s time to put them into action! Start up a new project
over on Hackaday.io
, enter it into the Prize, and you’re on your way. Ten finalists will receive $500 and be eligible to win the Grand Prizes ranging from $5,000 to $50,000. But you’ve only got until Tuesday, July 4th to enter, so don’t sleep.
As always, we’d like to thank our sponsors in the Hackaday Prize, Supplyframe and DigiKey, but we’d also like to thank Protolabs for sponsoring the Green Hacks challenge specifically, and for donating a $5,000 manufacturing grant for one finalist. Maybe that could be you?
The
Hackaday
Prize 2023
is Sponsored by: | 2 | 2 | [
{
"comment_id": "6648299",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-31T23:04:32",
"content": "The thumbnail photo is different than the Title Photo.I can’t make out what it is.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "666555... | 1,760,372,280.771814 | ||
https://hackaday.com/2023/05/31/moon-phase-lamp-uses-rotating-shade/ | Moon Phase Lamp Uses Rotating Shade | Lewin Day | [
"Arduino Hacks",
"LED Hacks"
] | [
"lamp",
"moon",
"moon lamp"
] | The Moon has fascinated humanity for centuries. These days, though, it’s a trial and a bore to go outside and stare upwards to check on the natural satellite. Instead, why not bring the Moon to your bedside
with this rotating phase lamp?
The build comes to us from [payasa_manandhar], who did a good job of replicating the Moon in both form and function. It’s based around
a lithophane
of the lunar surface, which adequately duplicates the Moon’s grey pockmarked visage thanks to topographical data sourced from NASA. It looks a treat when backlit from the inside. However, this is no mere ornamental lamp. With the aid of a stepper motor controlled by an Arduino, a shade inside the lamp actually rotates to shadow the Moon as per the appropriate phase.
It’s a build that is both fun and educational, in both the electronic and astronomical disciplines. We’ve seen
some other great Moon lamps before, too
. | 9 | 6 | [
{
"comment_id": "6648180",
"author": "craig",
"timestamp": "2023-05-31T16:20:05",
"content": "I think that is the worst video ever posted to hackaday. Normally I’d say looking at linked videos is a waste of time but, like watching a train wreck, that was so bad it was amusing and actually funny to ... | 1,760,372,283.283298 | ||
https://hackaday.com/2023/05/31/ask-hackaday-whats-your-tactical-tool-threshold/ | Ask Hackaday: What’s Your “Tactical Tool” Threshold? | Dan Maloney | [
"Featured",
"Rants",
"Slider",
"Tool Hacks"
] | [
"automotive",
"diy",
"harbor freight",
"repairs",
"tactical",
"tools"
] | With few exceptions, every field has a pretty modest set of tools that would be considered the minimum for getting most jobs done. A carpenter can make do with tools that would fit in a smallish bag, while a mechanic can handle quite a few repairs with a simple set of socket wrenches and other tools. Even in electronics, a lot of repairs and projects can be tackled with little more than a couple of pairs of pliers, some cutters, and a cheap soldering iron.
But while the basic kit of tools for any job may be enough, there will always be those jobs that need more tools. Oh sure, sometimes you can — and should — make do with what you’ve got; I can’t count the number of times I’ve used an elastic band wrapped around the handles of a pair of needlenose pliers as an impromptu circuit board vise. But eventually, you’re going to come upon a situation where only the “real” tool will do, and substitutes need not apply.
As I look around my shop and my garage, I realize that I may have a problem with these “tactical tool” purchases. I’ve bought so many tools that I’ve used far fewer times than I thought I would, or perhaps even never used, that I’m beginning to wonder if I tackle projects just as an excuse to buy tools. Then again, some of my tactical purchases have ended up being far more useful than I ever intended, which has only reinforced my tendency toward tool collecting. So I thought I’d share a few of my experiences with tactical tools, and see how the community justifies tactical tool acquisitions.
Blame It on Harbor Freight
Back in the day, avoiding the tactical tool purchase was a much easier prospect than it is today. Before the days of big box retailers, if you needed a tool to finish a job, your choices were pretty limited. The local hardware store was usually your best bet, but it was hit-or-miss — you weren’t likely to find any specialized tools there. Trade suppliers, like plumbing or electrical supply houses, would have been a good place if you were looking for a tool particular to that trade, but they tended to keep hours that made it hard for the home gamer to patronize them, and the atmosphere in those places can be unwelcoming to the do-it-yourselfer, to say the least.
One place that was always a great source of tactical tools for me was the local rental house. While most people associate tool rental with once-a-year needs like a lawn aerator or a pressure washer, most rental houses have a nice selection of specialty tools available on the cheap, and importantly for the DIY set, they’re usually open at least some of the weekend. I’ve lost track of the number of gear pullers I’ve had to rent over the years, usually on a Saturday afternoon when all other options have been exhausted.
But my visits to rental houses have become much rarer over the years, primarily because there are so many more places to buy tools for not much more than you can rent them. Home Depot was the first big box that managed to enable my tactical tool problem, with that great big “tool crib” stocked full of just about anything you might need on short notice, and critically on weekends. Lowe’s followed, with completely different brands of tools but functionally the same offerings.
Part of my one-time (and no-time) use tool collection. Apparently I’m a sucker for black blow-molded carrying cases.
The real problem for me, though, was when Harbor Freight started expanding aggressively. The discount tool retailer has been around for decades, but it’s only relatively recently that I’ve had the mixed blessing of having one of their stores close enough that it made sense to take a quick trip to get a tool that would make the job at hand either possible to complete, or more likely, make it marginally easier. And now that I have a Harbor Freight store a mere five-minute drive away, there’s very little that’s stopping me from dropping everything right in the middle of a job and heading off to get just the right tool.
Quality or Quantity?
Now, I know what you’re thinking: Harbor Freight is just full of cheaply made tools that are as likely to fall apart on first use as they are to actually help you get a job done. That’s certainly true of a lot of tools they sell, and I’ve been bitten by this a time or two myself. But I do have to say that Harbor Freight’s quality has really gone up lately, especially for their power tools. That monster right-angle drill in the picture above, which I bought to drill a hole in a well casing in a confined space about 4 feet underground, is a remarkably powerful machine. It performed admirably, and while I might not want to rely on it for daily use, for one-off jobs and other occasional uses, it was perfectly fine. And as a bonus, it cost less than I would have spent getting someone to do the job for me.
For me, I guess that’s the driver for my tactical tool obsession. I like being the guy who not only knows how to get the job done, but just happens to have the right tool for it. It may be a long time before I need a drill capable of twisting your arm off if you’re not careful, but when I do, I can just get the job done without much further fanfare. I find this to be especially true with automotive tools, because car problems stand the very real problem of rapid escalation into the territory of financial ruin. This almost happened to me a couple of weeks ago, when my usually rock-solid 2003 Toyota Tundra started hesitating and bucking just as I was starting a trip. I nearly broke down in the center of a one-lane bridge, which would have resulted in a towing charge and whatever the garage I ended up at decided to charge for the diagnosis and repair. Instead I managed to nurse the truck home; the fuel pressure gauge seen in the picture above will be used to diagnose what I strongly suspect is a fuel flow problem. Fifty bucks for tools plus maybe a fuel pump or filter sure beats the $1,000 or so that I would have been looking at otherwise.
Your Turn
Look, I admit it — I’ve got a tactical tool problem. But the tendency to over-tool my life hasn’t really caused me any problems, at least none that I’ll admit to. My family thinks it’s pretty cool that I’m likely to have the exact tool needed to tackle any job, even if they poke a little fun at my collecting habits from time to time. And at the end of the day, when nobody has to pay a plumber to make an emergency call for a leaking water heater, and oil changes and brake jobs are done gratis in my driveway, everyone wins.
But what about you? What’s your feeling on tactical tool purchases? I suspect there may be a better balance between buying one-time-use tools and the alternatives, like paying a pro or making do with what I have. I’m willing to admit that maybe I need to change my approach a bit, but only if it makes sense overall. Have you found the proper balance in your tool purchases? We’d also love to hear about any tactical tool purchases that have turned out to be widely useful. Sound off in the comments below.
Now if you’ll excuse me, I have to check out that fuel problem in the Tundra. | 130 | 48 | [
{
"comment_id": "6648107",
"author": "Ivan",
"timestamp": "2023-05-31T14:20:08",
"content": "I have a simple strategy for this. If I want a tool, I add it to my amazon save for later, then I do without it. I leave it there, and every time I think I want that tool I come back to it and reconsider whe... | 1,760,372,283.238852 | ||
https://hackaday.com/2023/05/31/what-next-for-the-sbc-that-has-everything/ | What Next For The SBC That Has Everything? | Jenny List | [
"computer hacks",
"Raspberry Pi"
] | [
"raspberry pi",
"SBC",
"single board computer"
] | In the decade-and-a-bit since the first Raspberry Pi was launched we’ve seen an explosion of affordable single-board computers (SBCs), but as the prices creep up alongside user expectation and bloat, [Christopher Barnatt]
asks where the industry will go next
.
The Pi started with an unbeatable offer, $35 got you something similar to the desktop PC you’d had a decade earlier — able to run a Linux desktop on your TV from an SD card. Over the years the boards have become faster and more numerous, but the prices for ARM boards are now only nominally as affordable as they were in 2012, and meanwhile the lower end of x86 computing is now firmly in the same space. He demonstrates how much slower the 2023 Raspberry Pi OS distribution is on an original Pi compared to one of the early pre-Raspbian distros, and identifies in that a gap forming between users. From that he sees those people wanting a desktop heading towards the x86 machines, and the bare-metal makers at the lower end heading for the more powerful microcontrollers which simply weren’t so available a decade ago.
We have to admit that we agree with him
, as the days when a new Raspberry Pi board was a special step forward rather than just another fast SBC are now probably behind us. In that we think the Pi people are probably also looking beyond their flagship product, as the hugely successful lunches of the RP2040 and
the industrial-focused Compute Module 4
have shown.
What do you think about the SBC market? Tell us in the comments. | 113 | 37 | [
{
"comment_id": "6648059",
"author": "Gregg Eshelman",
"timestamp": "2023-05-31T11:20:00",
"content": "I’d like for someone to take the H3droid project to the next level, bump it up a few Android versions from 4.x. There are TV boxes with the Allwinner H3 running versions as new as 7 while H3droid i... | 1,760,372,283.064987 | ||
https://hackaday.com/2023/05/31/jitx-spits-out-handy-usb-cable-tester/ | JITX Spits Out Handy USB Cable Tester | Bryan Cockfield | [
"Tool Hacks"
] | [
"cad",
"jitx",
"led",
"tester",
"testing",
"tools",
"usb",
"USB C"
] | When USB first came on the scene, one of the benefits was that essentially any four conductors could get you to the point where you could send information at 12 Mbps. Of course everything is faster these days, and reaching today’s speeds requires a little bit more fidelity in the cables.
This simple tester makes sure that your modern cables
are actually up to the task.
One of the design goals of this project is to automate away the task of testing cables or finding one that works, especially before thinking a problem with a device is somewhere in software, spending hours or days debugging, before realizing that it’s actually being caused by a hardware malfunction. The small PCB has two USB-C fittings to plug in both of the ends of a cable to, and between those connectors there is a number of LEDs. Each LED is paired to one the many conductors within the USB cable, and not only does it show continuity of these conductors but it can also show a high resistance connection via a dimly-lit or off-color display from an LED.
One of the other interesting facets of this build is the use of JITX, which is a software-defined electronics CAD tool which allows PCB design to be automated by writing out the requirements of the PCB into code, rather than drawing it manually. It’s worth a look, and a lot of the schematics of this particular project as well as some discussion on this software can be found on
the project’s GitHub page
. Incidentally, if this tester looks familiar, it’s probably because your’re
thinking of the open source hardware USB tester created by [Álvaro Prieto]
. | 12 | 5 | [
{
"comment_id": "6648044",
"author": "rastersoft",
"timestamp": "2023-05-31T09:57:44",
"content": "But what about a cable with the pins connected in the wrong way? Like the one that fried the laptop of one Google engineer because it swapped the power pins in one of the connectors, IIRC.",
"paren... | 1,760,372,283.32824 | ||
https://hackaday.com/2023/05/30/secret-bookshelf-door-uses-hidden-fingerprint-scanner/ | Secret Bookshelf Door Uses Hidden Fingerprint Scanner | Lewin Day | [
"Misc Hacks"
] | [
"door",
"secret door"
] | What is it that compels us about a secret door? It’s almost as if the door itself and the promise of mystery is more exciting than whatever could lay beyond. In any case, [Scott Monaghan] is a lover of the form,
and built his own secret door hidden in a bookshelf
, as all good secret doors should be.
The door is activated by pulling down on the correct book. This then reveals a fingerprint scanner. Upon presenting the right digit, the door will elegantly swing open to reveal the room beyond. Secret door experts will note there’s an obvious tell due to the light spilling through the cracks, however [Scott] reports that the finishing stages of the build solved this issue. The door was also fitted with a manual release for easier daily use.
Details are light, but the basics are all there. Really all you need is a cheap hardware store door opener, a secret activation lever or authentication method, and a well-hinged bookcase to achieve this feat yourself.
We’ve seen some other great secret doors before, too
. Video after the break.
Bookshelf secret door with thumb scanner—ran on AAs.
https://t.co/2F1843nUME
pic.twitter.com/HQqO329N80
— 🤖ScottsRobots🤖 @ OPEN SAUCE (SF 7/15-16) (@scottmonaghan)
May 24, 2023 | 4 | 3 | [
{
"comment_id": "6648166",
"author": "Greg A",
"timestamp": "2023-05-31T15:56:41",
"content": "i mean, it’s a hack!for something like this, security through obscurity really is more effective imo. the entrance looks like a door frame and seems to be exactly where you’d expect a door to be in a hous... | 1,760,372,282.625504 | ||
https://hackaday.com/2023/05/30/simple-cubes-show-off-ai-driven-runtime-changes-in-vr/ | Simple Cubes Show Off AI-Driven Runtime Changes In VR | Donald Papp | [
"Artificial Intelligence",
"Software Development",
"Virtual Reality"
] | [
"ai",
"ar",
"proof of concept",
"prototype",
"speech interface",
"unity",
"vr"
] | AR and VR developer [Skarredghost] got pretty excited about a virtual blue cube, and for a very good reason. It marked a successful prototype of an augmented reality experience in which the logic underlying the cube as a virtual object was
changed by AI in response to verbal direction by the user
. Saying “make it blue” did indeed turn the cube blue! (After a little thinking time, of course.)
It didn’t stop there, of course, and the blue cube proof-of-concept led to a number of simple demos. The first shows off a row of cubes changing color from red to green in response to musical volume, then a bundle of cubes change size in response to microphone volume, and cubes even start moving around in space.
The program accepts spoken input from the user, converts it to text, sends it to a natural language AI model, which then creates the necessary modifications and loads it into the environment to make runtime changes in Unity. The workflow is a bit cumbersome and highlights many of the challenges involved, but it
works
and that’s pretty nifty.
The
GitHub repository is here
and a good demonstration video is embedded just under the page break. There’s also
a video with a much more in-depth discussion
of what’s going on and a frank exploration of the technical challenges.
If you’re interested in this direction, it seems [Skarredghost] has rounded up the relevant details. And should you have a prototype idea that isn’t necessarily AR or VR but would benefit from AI-assisted speech recognition that can run locally?
This project has what you need
. | 6 | 4 | [
{
"comment_id": "6648026",
"author": "Butt Licker",
"timestamp": "2023-05-31T07:28:39",
"content": "Given some of the stuff I’ve seen lately, this is just a nice project he put together.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6648029",
"author": "s... | 1,760,372,282.673486 | ||
https://hackaday.com/2023/05/30/pretty-small-robot-is-capable-nonetheless/ | Pretty Small Robot Is Capable, Nonetheless | Lewin Day | [
"Robots Hacks"
] | [
"ESP32",
"mqtt",
"robot",
"robots"
] | When science fiction authors imagined robots in the 20th century, many of them were huge imposing steel automatons. [Shane]’s designs for the Pretty Small Robot are quite contrary to that,
being tiny in stature and cute in affect
.
The whole robot is an exploration in nifty engineering. It uses an easy clip-together structure with fasteners and glue not required. The chassis is 3D printed, with all the components sliding into place. Two small DC gearmotors are used for differential drive, with each side of the robot having a pair of wheels wrapped in a rubber band for traction. The brains of the robot is an ESP32, providing it with both plenty of processing power and good connectivity options.
Control is over WiFI via MQTT
.
At this stage the robot doesn’t do a whole lot, though [Shane] has some exciting plans.
He’d like to add a camera in future
and let it explore a maze under human command.
If you’ve ever wanted to build a robot with an almost coin-sized foot print, this build is for you. Files are available
on GitHub
for those wishing to dive deeper. Video after the break. | 5 | 4 | [
{
"comment_id": "6647946",
"author": "Mike",
"timestamp": "2023-05-31T00:59:01",
"content": "I think it could pass the butter..",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647958",
"author": "Dan (No, the OTHER one)",
"timestamp": "2023-05-31T03:0... | 1,760,372,282.719818 | ||
https://hackaday.com/2023/05/28/bbc-master-128-revealed/ | BBC Master 128 Revealed | Al Williams | [
"Retrocomputing"
] | [
"6502",
"acorn bbc master",
"bbc",
"corrosion",
"repair"
] | [Adrian] comments that the
BBC Master 128
is a rare 8-bit computer, and we agree — we couldn’t remember hearing about that particular machine, although the BBC series is quite familiar. The machine has a whopping 128 K of RAM, quite a bit for those days. It also had a 6502 variant known as the 65C12, which has an extra pin compared to a 6502 and doesn’t use the same clock arrangement. A viewer sent him one of these machines, which apparently was used in the BBC studios. You can see this rare beauty in the video below.
The computer has a very nice-looking keyboard that includes a number pad. There are also expansion ports for printers and floppy disk drives. It has some similarities to a standard BBC computer but has a number of differences externally and internally.
Of course, we were waiting for the teardown about 15 minutes in. There were some corroded batteries but luckily, they didn’t do much damage. The power supply had a burned smell. Cracking it open for inspection was a good time to convert the power supply to run on 120 V, too.
After some power supply repair, it was time to power the machine up. The results were not half bad. It started up with a cryptic error message: “This is not a language.” Better than a dead screen. The keyboard wasn’t totally working, though. A bit of internet searching found that the error happens when the battery dies and the machine loses its configuration.
More walkthroughs will take a bit more work on the keyboard. But we were impressed it came up as far as it did, and we look forward to a future installment where the machine fully starts up.
[Adrian] mentioned the
co-processor slot accepting a Raspberry Pi
, something we’ve talked about before. Or, add an FPGA and make the plucky computer
think it is a PDP/11
. | 12 | 7 | [
{
"comment_id": "6647340",
"author": "sgerjk",
"timestamp": "2023-05-28T20:32:33",
"content": "Honestly not that rare, it was mostly built for export to Poland, Czech Republic, Albania and other members of the USSR. It was sold in the so called “behind yellow curtains” shops, and for USD only. One o... | 1,760,372,282.765248 | ||
https://hackaday.com/2023/05/28/mangle-videos-with-recurboy-and-a-raspberry-pi-zero/ | Mangle Videos With RecurBOY And A Raspberry Pi Zero | Elliot Williams | [
"Raspberry Pi",
"Video Hacks"
] | [
"raspberry pi",
"synthesizer",
"video"
] | You used to need a lot of equipment to be a video DJ. Now you can do it all with a Raspberry Pi Zero and
[cyberboy666]’s recurBOY
. And if you missed out on the 1970’s video-editing psychedelia, now’s your chance to catch up – recurBOY is a modern video synth with all of the bells and whistles, and it’ll fit in your pocket. Check out [cyberboy666]’s
demo video
if you don’t yet know what you’re getting into. (Embedded below.)
RecurBOY has four modes: video, shader, effects, and external input, and each of these is significantly cooler than the previous. Video mode plays videos straight off of the SD card through the recurBOY’s composite video out. Shader mode lets you program your own
shaders
using the GLES shader dialect for resource-constrained devices. And this is where the various knobs and buttons come in. You can program the various shader routines to read any of the pots as input, allowing you to tweak the graphics demos on the fly.
Effects mode overlays your shaders on the video that’s playing, and external mode allows you to plug in a USB video capture card or a webcam so you can do all that same mangling with a live camera feed. And these two modes are where it gets awesome. The shader effects in the demo video cover all of the analog classics – including bloom and RGB separation – but also some distinctly digital effects. And again, you can tweak them all live with the knobs. Or plug in a MIDI controller and control it all externally. What hasn’t he thought of?
Old school analog video effects are really fun, and recurBOY brings them to you with the flexibility of modern shader coding. What’s not to love? If you want to see the pinnacle of the pre-digital era, that would be the
Scanimate
. For a video synth that integrates with your audio synth, check out
Hypno
. And if
glitching the video
is more your style, you can hijack the RAM of a VGA/composite converter.
Trippy, man!
via
Adafruit
. | 6 | 2 | [
{
"comment_id": "6647369",
"author": "ehrichweiss",
"timestamp": "2023-05-28T23:41:39",
"content": "I’m going to have to study this some once I get the PCB in so I can see how easy it will be to output HDMI. I have several uses for this, just not as analog.",
"parent_id": null,
"depth": 1,
... | 1,760,372,282.81315 | ||
https://hackaday.com/2023/05/28/ai-creates-killer-drug/ | AI Creates Killer Drug | Al Williams | [
"Artificial Intelligence",
"Machine Learning",
"Medical Hacks"
] | [
"antibiotic",
"bacteria",
"machine learning"
] | Researchers in Canada and the United States have used deep learning to derive an antibiotic that can attack a resistant microbe, acinetobacter baumannii, which can infect wounds and cause pneumonia. According to the
BBC
, a paper in
Nature Chemical Biology
describes how the researchers used training data that measured known drugs’ action on the tough bacteria. The learning algorithm then projected the effect of 6,680 compounds with no data on their effectiveness against the germ.
In an hour and a half, the program reduced the list to 240 promising candidates. Testing in the lab found that nine of these were effective and that one, now called abaucin, was extremely potent. While doing lab tests on 240 compounds sounds like a lot of work, it is better than testing nearly 6,700.
Interestingly, the new antibiotic seems only to be effective against the target microbe, which is a plus. It isn’t available for people yet and may not be for some time — drug testing being what it is. However, this is still a great example of how machine learning can augment human brainpower, letting scientists and others focus on what’s really important.
WHO identified acinetobacter baumannii as one of the major
superbugs
threatening the world, so a weapon against it would be very welcome. You can hope that this technique will drastically cut the time involved in developing new drugs. It also makes you wonder if there are other fields where AI techniques could cull out alternatives quickly, allowing humans to focus on the more promising candidates.
Want to catch up on machine learning algorithms?
Google
can help. Or dive into an even
longer course
. | 60 | 17 | [
{
"comment_id": "6647253",
"author": "Ostracus",
"timestamp": "2023-05-28T14:04:51",
"content": "“While doing lab tests on 240 compounds sounds like a lot of work, it is better than testing nearly 6,700.”I imagine with the other buzzword (robots) that can be a manageable task.https://aabme.asme.org/... | 1,760,372,282.907984 | ||
https://hackaday.com/2023/05/28/math-reveals-how-many-shuffles-randomizes-a-deck/ | Math Reveals How Many Shuffles Randomizes A Deck | Donald Papp | [
"Games"
] | [
"cards",
"math",
"random",
"randomizing",
"shuffling"
] | Math — and some clever simulations — have revealed
how many shuffles are required to randomize a deck
of 52 cards, but there’s a bit more to it than that. There are different shuffling methods, and dealing methods can matter, too. [Jason Fulman] and [Persi Diaconis] are behind the research that will be detailed in an upcoming book,
The Mathematics of Shuffling Cards
, but the main points are easy to cover.
A riffle shuffle (pictured above) requires seven shuffles to randomize a 52-card deck. Laying cards face-down on a table and mixing them by pushing them around (a technique researchers dubbed “smooshing”) requires 30 to 60 seconds to randomize the cards. An overhand shuffle — taking sections from a deck and moving them to new positions — is a staggeringly poor method of randomizing, requiring some 10,000-11,000 iterations.
The method of dealing cards can matter as well. Back-and-forth dealing (alternating directions while dealing, such as pattern A, B, C, C, B, A) yields improved randomness compared to the more common cyclic dealing (dealing to positions in a circular repeating pattern A, B, C, A, B, C). It’s interesting to see different dealing methods shown to have an effect on randomness.
This brings up a good point: there is not really any such a thing as “more” random. A deck of cards is either randomized, or it isn’t. If even two cards have remained in the same relative positions (next to one another, for example) after shuffling, then a deck has not yet been randomized. Similarly, if seven proper riffle shuffles are sufficient to randomize a 52-card deck, there is not really any point in doing eight or nine (or more) because there isn’t any such thing as “more” random.
You can watch these different methods demonstrated in the video embedded just under the page break. Now we know there’s no need for a complicated
Rube Goldberg-style shuffling solution
just to randomize a deck of cards (well, no
mathematical
reason for one, anyway.) | 52 | 21 | [
{
"comment_id": "6647225",
"author": "Todd",
"timestamp": "2023-05-28T11:23:45",
"content": "“If even two cards have remained in the same relative positions (next to one another, for example) after shuffling, then a deck has not yet been randomized. ”If the two cards moved relative to each other at ... | 1,760,372,283.423324 | ||
https://hackaday.com/2023/05/28/3d-printing-bores-without-support/ | 3D Printing Bores Without Support | Danie Conradie | [
"3d Printer hacks"
] | [
"3d printing",
"3d printing techniques",
"maker's muse"
] | If you’ve done even a small amount of 3D printing, you probably ran into the challenge of printing a small hole on top of a larger hole. The conventional solution is just to add support, but in the video after the break, [Angus] of Maker’s Muse demonstrates an
alternative solution
you can implement in CAD, without having to do manual post-processing.
This is a common problem when you have a countersink feature for a bolt head or captured nut on the bottom of the part. [Angus] first demonstrates some other techniques, including printing the bore over empty space, adding a
sacrificial bridge
, and making the overhang 45°. Each of these work but have some trade-offs. The proposed solution is what [Angus] calls sequential overhangs. It involves bridging the sides of the open space in steps to create supporting edges onto which the bore perimeter can print. It starts with 2 or 3 bridging layers to create a rectangle the same width as the bore, and then a second set of bridges at 90° to turn the opening into a square. For smaller holes this should create enough of a support to start the bore perimeter, but for larger holes three sets of bridges at 60° offsets might be needed.
[Angus] does not claim to have invented the technique but states he borrowed the idea from parts printed by Prusa Research for their
popular line of 3D printers
. One of the comments on the [Maker’s Muse] video referenced a
2014 blog post by [nophead]
showing the same approach. Regardless of the idea’s lineage, it’s a great addition to anyone’s 3D printing design toolbox. | 14 | 9 | [
{
"comment_id": "6647207",
"author": "mkarliner",
"timestamp": "2023-05-28T08:04:31",
"content": "I just use a fillet for this.Much quicker to do.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6694747",
"author": "Daniel Robert Betzold",
"ti... | 1,760,372,283.471977 | ||
https://hackaday.com/2023/05/27/hacking-a-smart-electric-toothbrush-to-reset-its-usage-counter/ | Hacking A “Smart” Electric Toothbrush To Reset Its Usage Counter | Maya Posch | [
"Wireless Hacks"
] | [
"electric toothbrush",
"NFC"
] | The visible circuitry inside the brush head.
Following the trend of stuffing more electronics in everyday devices, the new Philips Sonicare electric toothbrush that [Cyrill Künzi] purchased ended up having a ‘brush head replacement reminder’ feature that wasn’t simply a timer in the handle or base of the unit, but ended up involving an NFC chip embedded in every single brush head containing the usage timer for that particular head. Naturally, this asked for it to be solidly
reverse-engineered and hacked
.
The NFC chip inside the brush head turned out to be an NXP
NTAG213
, with the head happily communicating with the NFC reader in a smartphone and the NFC Tools app. This also revealed the memory layout and a few sections that had write access protected by a password, one of which was likely to be the counter. This turned out to be address 0x24, with a few experiments showing the 32-bit value at this address counting the seconds the brush head had been used.
Decoding the NFC data stream from a toothbrush using NFC-laboratory. (Credit: Cyrill Künzi)
Naturally, with this memory address password protected, the next step was to sniff the password using an SDR sniffer setup. After passing the resulting raw data with a gnuradio script through a lowpass filter, the resulting WAV file was decoded with the
NFC-laboratory
tool, allowing the traffic to be analyzed for clues. What this revealed was that the password is being passed as plaintext in the NFC data stream, making it a snap to use it to reset the counter to zero or any other desired value.
During this process, [Cyrill] came across a few gotchas, including that you only get three attempts to guess the password before the NFC chip permanently refuses new authentication attempts, and the password is unique with each brush head as it’s generated from the NFC chip’s 7-byte UID, per the NXP datasheet. Fortunately, it appears that this system is only being used as a complex reminder system, and you can still use an ‘expired’ head, but it does turn spent brush heads into e-waste, which is less ideal. | 46 | 15 | [
{
"comment_id": "6647198",
"author": "William DeRieux",
"timestamp": "2023-05-28T07:15:52",
"content": "It’s nice to go through with all of that I guess……but I was expecting to read that the point of hacking it was because the device would stop working.It is nice to see that, at least one, mfg hadn’... | 1,760,372,283.724611 | ||
https://hackaday.com/2023/05/27/ai-image-generation-gets-a-drag-interface/ | AI Image Generation Gets A Drag Interface | Donald Papp | [
"Art",
"Artificial Intelligence"
] | [
"ai art",
"AI image generation",
"art",
"GaN",
"image manipulation",
"SIGGGRAPH",
"siggraph"
] | AI image generators have gained new tools and techniques for not just creating pictures, but modifying them in consistent and sensible ways, and it seems that every week brings a fascinating new development in this area.
One of the latest is
Drag Your GAN
, presented at SIGGRAPH 2023, and it’s pretty wild.
It provides a point-dragging interface that modifies images based on their implied structure. A picture is worth a thousand words, so this short animation shows what that means. There are plenty more where that came from at the project’s site, so take a few minutes to check it out.
GAN stands for generative adversarial network, a class of machine learning that features prominently in software like image generation; the “adversarial” part comes from the concept of networks pulling results between different goalposts. Drag Your GAN has a
GitHub repository
where code is expected to be released in June, but in the meantime, you can
read the full paper
or brush up on
the basics of how AI image generators work
, as well as see how image generation can be significantly enhanced
with an understanding of a 2D image’s implied depth
. | 15 | 4 | [
{
"comment_id": "6647183",
"author": "𐂀 𐂅",
"timestamp": "2023-05-28T02:18:21",
"content": "That looks like a useful composition tool particularly when paired with the initial pin the scene method, but can it fix the finger count problem that so many of these systems have?",
"parent_id": null,... | 1,760,372,283.633774 | ||
https://hackaday.com/2023/05/30/ultimate-garage-door-control-does-the-job-brilliantly/ | Ultimate Garage Door Control Does The Job Brilliantly | Lewin Day | [
"home hacks"
] | [
"ESP32",
"garage",
"garage door opener",
"home-assistant"
] | [Stephen Carey] had previously relied on an Insteon garage door controller, only to have it perform poorly and fail at integrating with Alexa properly. Thus, he did what any good hacker would do,
and built his own system instead.
The garage door was first outfitted with a pair of reed switches to sense when it was fully open or fully closed. The drive sprocket of the garage door was also set up to be monitored with magnets and Hall effect sensors, essentially creating a rotary encoder. This allows a ESP32 to monitor the door’s direction of travel, it’s position, and when it has hit the end stop in either direction. Using Micropython, [Stephen] whipped up some code to tie the garage door controls in with
Home Assistant
, complete with a neat visual display of the current door position.
There are millions of home automation products out there, many of which make annoying compromises that frustrate the end user. Sometimes,
doing it your own way is the only way to get satisfaction! | 21 | 6 | [
{
"comment_id": "6647898",
"author": "Piotrsko",
"timestamp": "2023-05-30T20:52:29",
"content": "What about the cat under the closing door sensor? Mine knows if it hasnt hit the stop verification switch it better not be drawing more than typical downcurrent else something is stuck underneath and m... | 1,760,372,283.969068 | ||
https://hackaday.com/2023/05/30/hackaday-prize-2023-eyebreak-could-be-a-breakthrough/ | Hackaday Prize 2023: EyeBREAK Could Be A Breakthrough | Matthew Carlson | [
"Machine Learning",
"Microcontrollers"
] | [
"ESP32",
"morse code",
"Tensorflow Lite"
] | For those with strokes or other debilitating conditions, control over one’s eyelid can be one of the last remaining motor functions. Inspired by [Jeremiah Denton] blinking in Morse code on a televised interview, [MBW] designed an
ESP32-based device to decode blinks into words
.
While an ESP32 offers Bluetooth for simulating a keyboard and has a relatively low power draw, getting a proper blink detection system to run at 20 frames per second in a constrained environment is challenging. Earlier attempts used facial landmarks to try and determine, based on ratios, whether an eye was open or closed. A cascade detector combined with an XGBoost classifier offered excellent performance but struggled when the eye wasn’t centered. Ultimately a 50×50, 4-layer CNN in TensorFlow Lite processes the camera frames, producing a single output, eye open or closed. For debugging purposes, it streams camera frames over Wi-Fi with annotations via OpenCV, though getting OpenCV to compile for ESP32 was also nontrivial.
[MBW] trained the model using the MRL dataset and then quantized to int8. Getting the Bluetooth and Wi-Fi stacks to run concurrently was a bit of a pain, as was managing RAM. After exhausting SRAM and IRAM, [MBW] had to move to PRAM. The entire system is built into some lightweight goggles and makes for a fairly comfortable experience.
While TensorFlow and microcontrollers might seem like a bit of an odd couple, at the end of the day, the inference engine is just doing some math on an array of inputs with some weights. We’ve
even seen TensorFlow Lite on a Commodore 64
. If you don’t know about [Admiral Jerimiah Denton]
we can shed some light on it for you
.
The
Hackaday
Prize 2023
is Sponsored by: | 4 | 4 | [
{
"comment_id": "6647924",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-30T22:44:09",
"content": "Wow!Communication only through eye blinks…No speech or sip and puff?",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647938",
"autho... | 1,760,372,283.909063 | ||
https://hackaday.com/2023/05/30/supercon-2022-jorvon-moss-gives-his-robots-a-soul/ | Supercon 2022: [Jorvon Moss] Gives His Robots A Soul | Arya Voronova | [
"Art",
"cons",
"Hackaday Columns",
"Robots Hacks",
"Slider"
] | [
"2022 Superconference",
"robot design"
] | How do you approach your robot designs? Maybe, you do it from a ‘oh, I have these cool parts’ position, or from a ‘I want to make a platform on wheels for my experiments’ perspective. In that case, consider that there’s a different side to robot building – one where you account for your robot’s influence on what other people around feel about them, and can get your creations the attention they deserve. [Jorvon ‘Odd-Jayy’ Moss]’s robots are catchy in a way that many robot designs aren’t, and they routinely go viral online. What are his secrets to success? A combination of an art background, a Bachelor of Fine Arts in illustration, and a trove of self-taught electronics skills helped him develop a standout approach to robot building.
Now, [Jorvon] has quite a few successful robot projects under his belt, and at Supercon 2022, he talks about how our robots’ looks and behaviour shapes their perception. How do your own robots look to others, and what feelings do they evoke? With [Jorvon], you will go through fundamentals of what makes a robot look lively, remarkable, catchy or creepy, and it’s his unique backgrounds that let him give you a few guidelines on what you should and should not do when building a certain kind of robot.
You’ll do good watching this video – it’s short and sweet, and shows you a different side to building robots of your dreams; plus, the robot riding around on the stage definitely makes this presentation one of a kind. No matter your robot’s technical complexity, it’s significant that it can make people go ‘wow’ when they see it. Not all robots are there to single-mindedly perform a simple task, after all – some are
meant to travel around the world. | 6 | 4 | [
{
"comment_id": "6647869",
"author": "TG",
"timestamp": "2023-05-30T19:16:49",
"content": "The random servo position for twitches and saccades is fun. I wonder what the cheapest, simplest, throw-away version of such a circuit would be, something you could make as a module and plug in all over a prop... | 1,760,372,284.009508 | ||
https://hackaday.com/2023/05/30/diy-3d-printed-rain-gauge-connects-to-home-assistant/ | DIY 3D Printed Rain Gauge Connects To Home Assistant | Danie Conradie | [
"home hacks",
"Microcontrollers"
] | [
"ESP32",
"esphome",
"homeassistant",
"weather station"
] | Measuring local rainfall has real practical uses, especially in agriculture, but most of us will have to admit that it’s at least partly about drawing cool graphs on a screen. Whatever your motivation, you can build this
open source electronic rain gauge
designed by [Sebastian] of
Smart Solutions for Home
, and integrate it with Home Assistant.
This 3D printed rain gauge is of the ubiquitous tipping bucket type and uses a magnet and hall effect sensor to detect every time the bucket tips out. The sensor is soldered to a custom PCB with ESP32 configured using
ESP Home
. By keeping it in deep sleep most of the time and only waking up when the tip of the bucket, [Sebastian] estimates it can run about a year on four AA batteries, depending on rainfall. The hinge mechanism is adjustable to ensure that both buckets will tip with the same volume of water.
FDM 3D printed enclosures are not known for being waterproof
, so [Sebastian] coated the PCB with varnish to protect it from moisture. This worked well enough that he could leave it running in a bowl of water for a few hours without any ill effects. The end result looks good and should be able to handle the outdoors for a long time.
Building a weather station is a popular DIY project. Some of the interesting varieties we’ve seen are
powered by supercapacitors
, show readings on
antique analog dials
and
convert parking distance sensor kit into a wind gauge
. | 17 | 8 | [
{
"comment_id": "6647796",
"author": "Paul d'Aoust",
"timestamp": "2023-05-30T16:03:01",
"content": "Excited to learn more, but the first link in the article goes to a wp-admin link in the guts of the Hackaday blog. Is it just supposed to point to the YouTube page for the embedded video?",
"pare... | 1,760,372,283.856753 | ||
https://hackaday.com/2023/05/30/methane-tracking-satellites-hunt-for-nasty-greenhouse-gas-emissions/ | Methane-Tracking Satellites Hunt For Nasty Greenhouse Gas Emissions | Lewin Day | [
"Current Events",
"Featured",
"Original Art",
"Slider"
] | [
"climate change",
"greenhouse gas",
"greenhouse gases",
"methane",
"pollution",
"satellite",
"Satellites"
] | Much of the reporting around climate change focuses on carbon dioxide. It’s public enemy number one when it comes to gases that warm the atmosphere, as a primary byproduct of fossil fuel combustion.
It’s not the only greenhouse gas out there, though. Methane itself is a particularly potent pollutant, and one that is being emitted in altogether excessive amounts.
Satellites are now on the hunt for methane emissions
in an attempt to save the world from this odorless, colorless gas.
Bad Gas
Methane stands out as an extraordinarily effective greenhouse gas, carrying a warming impact 28 times greater than that of CO2 on a weight-for-weight basis over 100 years. Prior to industrialization, it primarily originated from natural reservoirs, such as microbes breaking down organic matter in still bodies of water, or from melting permafrost.
Today, contemporary scientific consensus suggests that roughly 60% of the methane present in the atmosphere can be attributed to human actions. The agricultural sector plays a significant role, as livestock, especially ruminants, are significant producers of methane. As the global appetite for meat and dairy products shows no signs of decreasing, this source of emissions presents a challenging obstacle. Beyond farming, waste management facilities and sewage treatment plants release considerable amounts of methane. The substance is frequently a byproduct of both oil and gas extraction operations. Leaks from industrial facilities and municipal natural gas systems are not uncommon.
Historically, the concentration of methane in the atmosphere has been relatively small in comparison to carbon dioxide. However, recent years have seen levels rise beyond previous expectations, which could pose a challenge for the world’s efforts to stem rising global temperatures.
Hunt From The Skies
The fact of the matter is that you can’t quash what you can’t see. Without knowing where increased methane output is coming from, it’s hard for researchers and administrators to know where to start fixing the issue. Thankfully, there are tools that can help track down sources of methane emissions.
MethaneSAT aims to take space-based measurements to hunt down sources of methane emissions. Credit: Steven Wofsy, Harvard, MethaneSAT
MethaneSAT is the headline project in this area.
Scheduled to launch in early 2024, the satellite is the result of a collaboration between Harvard researchers, private space companies, activists, philanthropists, and the coordinating Environmental Defense Fund. Typically, full-scale satellite design and launches are the purview of multi-billion-dollar companies and governments alone, but MethaneSAT has been developed by a coalition on a mission.
Principle investigator Steven Wofsy noted the group’s hard work to make the project a reality after he costed the project at tens of millions of dollars. “We brought that back to EDF, and we assumed that that was the end of it,” Wofsy said. “But they went ahead and raised enough in private philanthropy to fund this thing.”
Mapping methane leaks is key to reducing emissions into the atmosphere. Credit: Harvard/MethaneSAT
The goal of MethaneSAT is to allow monitoring a wide area for sources of methane emissions far more quickly and easily than existing aerial-and ground-based methods. The prime instrument on the satellite is a spectrometer.
As light reflected from the ground passes through the atmosphere, the spectrometer can capture the telltale signature of methane in the spectrum of light it receives. A plume of methane in the air from a landfill, farm, or pipeline leak will become readily apparent as the satellite passes over. When leaks and strong sources are identified, then something can be done about it.
Existing Work
Methane hotspots in Kazakhstan, as spotted by the Sentinel 5P and Sentinel 2 satellites, respectively. Credit:
ESA
MethaneSAT won’t be the only game in town when it launches in early 2024. Other researchers have already been using satellites to monitor methane emissions around the world.
Recent surveys by NASA have shown “mind-boggling” emissions of methane
from fossil fuel fields in Turkmenistan
. The methane releases were so great, they effectively equaled the UK’s total annual emissions in equivalent tons of CO
2
. Suspicions are that operators in the area
may be simply venting methane to the atmosphere
now that “flaring,” or burning off excess methane, is frowned upon. Due to the potency of methane as a greenhouse gas, this is actually far worse for the climate.
The European Sentinel 5P satellite
has also been put to work on this task
. Using the Tropomi, or Tropospheric Monitoring Instrument, on the craft, researchers identified broad areas of interest that could be a source of higher methane emissions. The data revealed gas leaks from wells in the US, as well as emissions from pipelines feeding gas
from Russia to Europe
. These hotspots can also be used guide investigations with more precise satellites run by Canadian operator GHGSat, researchers can identify sources of methane emissions down to a resolution of 20 meters or so.
The First Step
Satellites are a great tool to hunt for methane emissions. Sadly, though, finding leaks and heavy emitters is just the first step in solving the problem. The real hard work starts when it comes time to fix leaks and reduce excessive pollution from industrial sources. As always, knowing is half the battle. | 41 | 15 | [
{
"comment_id": "6647754",
"author": "Skip Flem",
"timestamp": "2023-05-30T14:09:17",
"content": "activated charcoal suppositories for cows?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647760",
"author": "Joseph Eoff",
"timestamp": "2023-... | 1,760,372,284.265471 | ||
https://hackaday.com/2023/05/30/will-electric-tractors-farm-your-food/ | Will Electric Tractors Farm Your Food? | Jenny List | [
"Transportation Hacks"
] | [
"electric tractor",
"farming",
"tractor"
] | There are two professions used to driving single-seaters with hundreds of horsepower, one of which is very exclusive and the other of which can be found anywhere the ground is fertile enough to support agriculture. Formula One drivers operate fragile machines pushed to the edges of their performance envelope, while the tractor at the hands of a farmer is designed to reliably perform huge tasks on dodgy ground in all weathers. Today’s tractor is invariably a large machine powered by a diesel engine, and it’s the equal of all tasks on a modern farm. Against that backdrop then it’s interesting to read the Smithsonian magazine’s look at
the emerging world of electric tractors
. Will they replace diesel as the source of traction in the fields?
Farm-ng’s Amiga
The two firms they focus on first are
Monarch Tractor
, and
Solectrac
. Both manufacturers offer small machines of the type we’d be inclined to describe as an orchard tractor, and Monarch are offering an autonomous option as part of their package. They also feature
Farm-ng
, whose machine called amusingly the Amiga, is a much smaller affair which we are guessing would be super-useful on a very intensive operation such as market gardening. We’re especially pleased to see that the emerging small electric tractor industry is embracing right to repair, something the traditional manufacturers are famous for ignoring.
It’s obvious that none of these machines are going to revolutionize the world of large high-power tractors any time soon, as they are too small for the job and can’t offer the 24/7 operation required at busy times on a farm. But it’s obvious they would be very useful on a small farm, and in particular for those tractor applications where the machine is a platform which goes from place to place to aid static work, they could be better than their diesel equivalents.
It’s odd that over the years we’ve not covered any electric tractors before. Perhaps that is, until you search instead for
agricultural robots
. | 119 | 24 | [
{
"comment_id": "6647683",
"author": "Psycobob",
"timestamp": "2023-05-30T11:14:40",
"content": "Once electric tractors start using EV scale batteries, DC fast charging will allow them to come closer to the uptime diesel tractors have.Planting and harvest definitely need short recharge times or very... | 1,760,372,284.177689 | ||
https://hackaday.com/2023/05/30/south-korea-successfully-sends-satellites-to-orbit/ | South Korea Successfully Sends Satellites To Orbit | Chris Lott | [
"News",
"Space"
] | [
"KLSV",
"Nuri",
"satellite",
"south korea"
] | South Korea’s KARI (
Korea Aerospace Research Institute ) successfully put a commercial satellite into orbit Thursday, achieving another milestone in their domestic space program. The Nuri rocket (aka KLSV-2) left the Naro Space Center launch pad on the southern coast of the peninsula at 18:24 KST, after a communications glitch in the pad’s helium tank facility caused a one-day slip. The primary payload was the 180 kg refrigerator-sized Earth observation satellite
NEXTSat-2
. It uses synthetic aperture radar (SAR) and also has instruments to observe neutrons in near-Earth orbit due to the impact of solar activity on cosmic radiation.
In addition, seven CubeSats were successfully deployed:
Justek JLC-101-V1.2, to verify satellite orbital control system
Lumir, measuring cosmic radiation and testing rad-hardened microprocessor design
Cairo Space, weather observation and space debris technology demonstration
KASI-SAT (Korea Astronomy and Space Science Institute)
SNIPE
, actually four nano-sats which will achieve a 500 km – 600 km polar orbit and fly in formation to measure plasma variations.
It seems that SNIPE-C, Justek, and Lumir are having communication troubles and may be lost. Ground controllers are still searching. This launch comes almost one year after the previous launch of a dummy satellite in June, which we
wrote about last year
. | 8 | 3 | [
{
"comment_id": "6647704",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-30T12:26:34",
"content": "“Cairo Space, weather observation and space debris technology demonstration”Aren’t all cubesats space debris?B^)",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,284.362004 | ||
https://hackaday.com/2023/05/29/mat-boards-are-spendy-so-diy-cnc-tool-to-the-rescue/ | Mat Boards Are Spendy, So DIY CNC Tool To The Rescue | Donald Papp | [
"Art",
"cnc hacks"
] | [
"3d printed",
"cnc tool",
"diy",
"mat board",
"mat cutting"
] | Mats are flat pieces of paper-based material that fill the space between a frame and the art within. They perform a number of aesthetic and practical functions, and they can also be expensive to purchase. Making them by hand is an option, but it’s an exacting process. [wooddragon48] felt that a CNC solution would serve this need nicely, and began
designing a DIY CNC tool to do exactly that
.
One of the tricky parts about cutting mat boards is that cuts are at an angle, and there is really no tolerance for overcuts or any kind of visual blemish. CNC control would seem to offer a great solution to both the need for precisely straight cuts, as well as fine control over where cuts begin and end in a way that opens the door to complex designs that would be impractical to do by hand.
[wooddragon48]’s design has an angled cutter designed to plunge perfectly on demand, surrounded by a ring — similar to that on a router — which ensures the cutting tool is always consistently positioned with the material. It’s still in the design phase, but this is a type of tool that doesn’t yet exist so far as we can tell. The ability to CNC cut mat board, especially in complex designs, would be a huge timesaver.
Art and DIY CNC have a long history of happy intersection, as we have seen with a
CNC router repurposed for string art
, a CNC
painting robot
, and even an interactive
abstract sculpture generator
. | 22 | 11 | [
{
"comment_id": "6647677",
"author": "dongwaffle",
"timestamp": "2023-05-30T10:24:30",
"content": "They have hand tools that will cut holes yet people buy drills.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647735",
"author": "ono",
"time... | 1,760,372,284.421646 | ||
https://hackaday.com/2023/05/29/your-engineering-pad-in-browser/ | Your Engineering Pad In Browser | Al Williams | [
"Tool Hacks"
] | [
"math",
"mathcad"
] | It was always easy to spot engineering students in college. They had slide rules on their belts (later, calculators) and wrote everything on engineering pads. These were usually a light brown or green and had a light grid on one side, ready to let you sketch a diagram or a math function. These days, you tend to sketch math functions on the computer and there are plenty of people willing to take your money for the software. But if you fire up your browser, head over to
EngineeringPaper.xyz
and you might save a little cash.
Although it looks a lot like a Jupyter notebook, the math cells in EngineeringPaper keeps track of units for you and allows you to query results easily. Want to read more? Luckily, there is
an EngineeringPaper worksheet
that explains how to use it. If you prefer your explanations in video form, check out their channel, including the video that appears below.
If you don’t have the patience for reading documentation, you can jump right into
a sheet to compute the parameters of a parallel plate capacitor
. If you click the little hamburger above the cell that says “Air” you can select from a few dozen dielectric materials.
By default, the program replies to queries in SI units even if you didn’t use them in the original data. You can, though, force the answers to be in your favorite units if you like. Well, within reason. It stubbornly refused to answer us in furlongs per fortnight. It did, however, accept rods per picosecond.
While we still miss the ubiquitous engineering pad, we have to admit the graphs this thing creates look better than ours. Not to mention the inclusion of a system solver which our old paper pad lacked.
Wolfram Alpha
is mostly free and very capable, but they do want you to pay for certain things. If you don’t mind writing Python or some other “
real language
” there’s always
Jupyter
.
Thanks to [Daniel Crowley] for the tip! | 15 | 7 | [
{
"comment_id": "6647636",
"author": "Oikos",
"timestamp": "2023-05-30T04:37:00",
"content": "Nice idea, but what a dreadful user interface.Press “insert cell” and the dialogue box times out after five seconds or so.Seems to dislike the system keyboard on mobile browsers too.What a shame, a terrible... | 1,760,372,284.318246 | ||
https://hackaday.com/2023/05/29/google-nest-hub-teardown/ | Google Nest Hub Teardown | Matthew Carlson | [
"Reverse Engineering"
] | [
"DSLogic",
"google hub",
"radar chip",
"teardown"
] | Seeing the guts of devices is a fascination that many hackers share. [Txyz] tore down
a 2nd gen Google Nest Hub
for all of us to enjoy. The video after the break is well produced and relaxing to watch as various heat shields are removed and debug cables are soldered on.
The main SOC is an Amlogic S905D3G, a 4-core A55-based SoC. The important chips are meticulously documented, and it’s a fascinating look inside a device common in many people’s homes. One chip that’s of note is the BGT60TR13C, otherwise known as Project Soli. It is an 8x10mm chip that uses radar to detect movement with sub-millimeter accuracy. This allows the device to measure your sleep quality or recognize gestures. Luckily for us, [Txyz] has included a datasheet and a block diagram. First, the chip fills a FIFO with data samples. Once full, it will issue an interrupt to the main SoC, which empties the buffer via SPI.
The debug cables allowed him to capture traces of the SPI commands to the BGT60TR13C. [Txyz] focused on decoding the various data blocks and the configuration registers. Unfortunately, only a few registers are documented in the datasheet, and it isn’t apparent what they do.
If a hardware teardown isn’t enough for you, perhaps a
software teardown to bypass Secure Boot
might sate your interest. | 16 | 6 | [
{
"comment_id": "6647611",
"author": "Ostracus",
"timestamp": "2023-05-29T23:05:28",
"content": "Apparently a Google phone uses the same.https://techtime.news/2019/10/16/radar/",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647628",
"author": "ScubaBearLA... | 1,760,372,284.475053 | ||
https://hackaday.com/2023/05/29/automate-handwritten-postcards-with-robots/ | Automate Handwritten Postcards With Robots | Danie Conradie | [
"Robots Hacks",
"Tool Hacks"
] | [
"handwriting",
"pen plotter",
"stuff made here"
] | As someone notorious for not doing things the old-fashioned manual way, we’re not sure by [Shane] of Stuff Made Here was thinking when he promised to send out a few hundred handwritten letters. Predictably he built an
automated production line
for the task. Video after the break.
With “handwritten” and “automated” not being particularly compatible, [Shane] set out to create a robot to create believable handwritten letters, which is significantly harder than it may seem at first glance. It turns out that turning your handwriting into a font is too consistent to be believable, which led down the rabbit of generated handwriting. [Shane] first spend a ridiculous amount of time trying to implement a machine learning model for the task, only to find there’s already an
open source library
good enough to fool a forensic handwriting expert.
On the robot side, [Shane] used a pen plotter from Amazon that’s it’s actually cheaper than building one from scratch. With the “handwriting” taken care of, [Shane] set up an automated loading system with the industrial robot arm he also used for his
CNC chainsaw
. The feeders for the empty and full postcards are 3D printed with a spring-loaded mechanism to keep the top card at the same height all the time.
Although this project contained less custom hardware and software than
[Shane’s] other projects
, it served as an excellent reminder that it’s unnecessary to reinvent the wheel when building a car. It’s easy to get caught up in the small details of a project that don’t matter much in the final implementation and usage. | 15 | 6 | [
{
"comment_id": "6647557",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-29T20:09:38",
"content": "“The weather is here, wish you were beautiful!”B^)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647573",
"author": "MmmDee",
... | 1,760,372,284.528378 | ||
https://hackaday.com/2023/05/29/hackaday-prize-2023-scratch-made-8-bit-educational-computer/ | Hackaday Prize 2023: Scratch Made 8-Bit Educational Computer | Joseph Long | [
"computer hacks",
"The Hackaday Prize"
] | [
"2023 Hackaday Prize",
"8 bit",
"educational",
"homebrew"
] | To demonstrate the functionality of an 8-bit computer processor at a very basic level, [Mazen Gomaa] assembled a
Homemade 8-Bit Educational Computer
using common CMOS logic chips, a handful of prototyping boards, and an impressive number of carefully connected wires. [Mazen] was inspired by Ben Eater’s
8-bit TTL Breadboard Computer
but opted to solder the chips and other components onto proto boards instead of using solderless breadboards.
The 8-Bit computer is based on the
Simple-As-Possible (SAP)
computer architecture described in the book “Digital Computer Electronics” by [Paul Malvino] and [Jerald Brown]. These useful educational examples demonstrate data, computer logic, and even programming in the context of basic electronic components. Tinkering with such simple computers provides a real “zeros and ones” exposure to computation.
[Mazen] added some additional features and functionality to his computer, including an instruction keypad, an address keypad, a dot matrix memory data viewer, a Schottky diode matrix ROM, and a boot loader that initializes the RAM with data stored in ROM. With clock speeds up to 100 Hz, the computer consumes around 300-500 mA of current.
Future plans include expanding the memory and instruction set from the present 128-bit (8×16) RAM, 64-bit (8×8) ROM, and a set of ten instructions. Already, this project is a great addition to an ever-growing catalog of homemade
solderless breadboard computers
,
LCD snake games
, and
VGA video cards
.
The
Hackaday
Prize 2023
is Sponsored by: | 6 | 5 | [
{
"comment_id": "6647554",
"author": "grumbly",
"timestamp": "2023-05-29T19:51:29",
"content": "Ah, the MSI days, when buses were buses, tri-state outputs were our friends, and you didn’t have to have as many multiplexers as everything else combined. Yes, yes, multiple tri-state devices on a bus con... | 1,760,372,284.56904 | ||
https://hackaday.com/2023/05/29/all-your-robots-are-belong-to-us-you-just-rent-them/ | All Your Robots Are Belong To Us: You Just Rent Them | Al Williams | [
"Hackaday Columns",
"Rants",
"Slider"
] | [
"Rant",
"robotics as s service",
"software as a service"
] | Monthly bills. Everyone has them. Except if you go far enough back, not everyone had them. After all, you might live in a home your family has owned for generations. You might be able to produce all the basic necessities using your homestead: food from a garden, water from a well, textiles, soap, and candles. You might have to buy the occasional animal, but your recurring bills could be modest outside of the ever-present tax burden.
But as people moved to cities, they had to pay rent. Buy gas or coal and, eventually, electricity. Water and trash collection are pretty essential, too. But at some point, everyone realized that being in a position to bill you monthly is a good idea. Now we pay for the internet, movie subscriptions, meal plans, alarm monitoring, shopping clubs, cell phones, spa memberships. Soon we might be paying a monthly fee for our robots, too.
Rent To (Not) Own
In industry, this is a common occurrence. You often don’t buy a robot arm or similar device. That, after all, is a capital expense, and most tax codes require you to count it as an asset that slowly depreciates. Instead, you hire a robot from a service provider. Not only does that make it a pure expense, but the provider worries about software, repairs, and all that.
But at home, it is different. There’s no tax advantage in most places between owning a car and leasing it. Yet vendors want to adopt a rent-a-robot strategy. Case in point: a startup named
Matician
wants you to sign up for a robotic vacuum. For $125 a month, you get a super smart robot vacuum. You could, of course, buy a Roomba, but — according to Matician — the Matic robot uses computer vision to map your house and automatically finds messes. You can also voice command it to clean up areas. It also avoids wire and furniture. They didn’t mention if it can
avoid presents left by your pets
or not. It will avoid pets and kids, though.
On the face of it, we predict a bad future for Matician. Even if their tech is better than the brand-name robot vacuums, it can’t be that hard to build a similar or better robot that you can buy and own. Unless, of course, all the other vendors realize that the monthly fee bandwagon is the place to be. Then all bets are off.
But you can’t help but wonder if it isn’t going to be just robot vacuums. How long before you pay a monthly fee for your hot water heater? Pay per flush in the bathroom? Already we’ve seen cars
that can perform better for a fee
and motorcycle protection that
shuts off if you fail to make your required payment
.
Smart Consumers
DIVX: Buy the disc, rent the movie.
Consumers have too wary to fall for this, but it seems like that may be changing. For example, consider the recent historical example of DIVX, the Digital Video Express format from Circuit City (and not the DivX codec). DIVX players had a feature where you could rent a DVD and never return it. Later, if you wanted to watch it again, the DIVX player could charge you a fee to watch it, or if you fed enough virtual coins into the virtual slot, you could own the disk forever.
Renting might actually make sense for something you don’t use very often. Most people can’t justify buying a cement mixer, but you can rent one for a weekend every few years. But a floor vacuum? Your car? Your word processing software?
Just like DIVX, though, there is only one way to combat this: with your wallet. Companies will do what they can make money doing, and honestly, you can’t blame them for that. Don’t get me wrong, paying for an actual service is great. If someone comes to your home and cleans for you, they should be getting paid. Maybe they even have a robot helper. If someone monitors your home alarm or stores your files remotely, they have expenses that must be paid, and they are entitled to a fair profit. But it is hard to swallow that someone expects you to pay for something that you already own that requires no further action from them.
The Cost
It is one of those things that is hard to articulate but easy to identify. In cases where something is expensive, and you rent to own, that makes sense. Renting might also make sense for something that requires frequent, costly maintenance, or that you use infrequently. Computers and copy machines used to fit that description, and companies rarely bought them but rented them — and also enjoyed having an expense instead of a capital asset. Of course, once those things got cheap… look at
fax machines
; same story.
There are other hidden costs of renting. For example, today, you can decide that version 2.0 of a program meets your needs and refuse to upgrade. But if you subscribe to that same program, the vendor may discontinue your subscription or price it higher to force you to change because, of course, it “costs more” to offer support for the older software.
Another example is a slowdown in innovation. If you build a circuit simulation program and offer it for sale, you improve it for at least three reasons. First, you want to entice people away from buying competitors. Second, you want to attract new customers. But you must also convince people who already paid you for the software to invest in an upgrade. That last reason goes away if the user pays you every month, rain or shine.
In the end, the free market will decide. If you continue to pay for services, they will happily oblige you. However, it seems like a market opportunity to create new devices and programs that replace pay-as-you-go with something of equal capability that you can buy outright. Smart people ought to flock to a product like that. | 34 | 12 | [
{
"comment_id": "6647513",
"author": "Joseph Eoff",
"timestamp": "2023-05-29T17:13:01",
"content": "That’d have to be one more hell of a vacuum cleaner for $1500 per year, every year.For that price, it better come with free electricity, free replacement, and free 24/7 emergency service. It better b... | 1,760,372,284.746024 | ||
https://hackaday.com/2023/05/29/open-source-ar-hack-chat/ | Open-Source AR Hack Chat | Dan Maloney | [
"Hackaday Columns",
"Slider"
] | [
"Hack Chat"
] | Join us on Wednesday, May 31 at noon Pacific for the
Open-Source AR Hack Chat
with Raj Nakaraja!
We may live in a soup of electromagnetic waves that range in wavelength from the diameter of Jupiter down to a fraction of the radius of a hydrogen atom, but our eyeballs have evolved to only let us sense a tiny slice of that spectrum. That’s too bad, really, because there’s a lot going on in the rest of the spectrum that could potentially inform our ROYGBIV-centric view of the world. Think of the possibilities of being able to see UV the way an insect does, or being able to watch the radiation pattern of an antenna and make adjustments on the fly. Sounds like a job for augmented reality.
If seeing the world with different eyes sounds as cool to you as it does to us, you won’t want to miss Raj Nakaraja’s stop by the Hack Chat. Raj is head of engineering at
Brilliant Labs
, an augmented reality company that’s looking to bring AR into the mainstream. They’ve got some cool ideas about AR, and we’re going to take the opportunity to talk to Raj about open-source AR in general, Brilliant’s products specifically, and how AR can be incorporated into not only our projects, but into our lives as well.
Our Hack Chats are live community events in the
Hackaday.io Hack Chat group messaging
. This week we’ll be sitting down on Wednesday, May 31 at 12:00 PM Pacific time. If time zones have you tied up, we have a
handy time zone converter
.
Click that speech bubble to the right, and you’ll be taken directly to the Hack Chat group on Hackaday.io. You don’t have to wait until Wednesday; join whenever you want and you can see what the community is talking about. | 0 | 0 | [] | 1,760,372,284.786279 | ||
https://hackaday.com/2023/05/29/macro-pad-cheap-enough-to-give-away/ | Macro Pad Cheap Enough To Give Away | Matthew Carlson | [
"Microcontrollers",
"Peripherals Hacks"
] | [
"CH552",
"macropad",
"makerfaire"
] | Supercon 2022 showed that hackers are starting to come together again in Maker Faires, conventions, and festivals. [Toby Chui] plans to be one of those hackers and wants something to give to fellow attendees. Thus,
the $3 Macro Pad was born
.
We’ve seen our fair share of macro pads, so a simple four-key pad isn’t exactly novel. However, the focus on size and cost makes it stand out. The pad is the size of a business card, making it easy to give away. For a microcontroller, [Toby] used a CH552G, which is cheap and compatible with the Arduino IDE. Although, with 10 GPIO, a matrix layout could have supported a full-sized number pad, the diodes required would have added to the cost significantly. A cheap PCB and 3d-printed base make up the device’s bulk.
[Toby]
provides a handy tool for assigning keys
from your browser without coding. However, the source code is
on GitHub
if you want to develop a more complicated scheme. This isn’t the
first time we’ve featured the CH552 chip
, and it likely won’t be the last. | 24 | 8 | [
{
"comment_id": "6647499",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-29T15:34:45",
"content": "Nice!(Though at first thought, upon seeing CH552 in the Title Photo, I thought it was a relative of the 555 B^)",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,284.847149 | ||
https://hackaday.com/2023/05/29/chatgpt-v-the-legal-system-why-trusting-chatgpt-gets-you-sanctioned/ | ChatGPT V. The Legal System: Why Trusting ChatGPT Gets You Sanctioned | Maya Posch | [
"Artificial Intelligence",
"Current Events",
"Featured",
"Slider"
] | [
"ChatGPT",
"GPT-4",
"large language model",
"LLM"
] | Recently, an amusing anecdote made the news headlines pertaining to the use of ChatGPT by a lawyer. This all started when a Mr. Mata
sued the airline
where years prior he claims a metal serving cart struck his knee. When the airline filed a motion to dismiss the case on the basis of the statute of limitations, the plaintiff’s lawyer filed a submission in which he argued that the statute of limitations did not apply here due to circumstances established in prior cases, which he cited in the submission.
Unfortunately for the plaintiff’s lawyer, the defendant’s counsel pointed out that none of these cases could be found, leading to the judge requesting the plaintiff’s counsel to submit copies of these purported cases. Although the plaintiff’s counsel complied with this request, the
response from the judge
(
full court order PDF
) was a curt and rather irate response, pointing out that none of the cited cases were real, and that the purported case texts were bogus.
The defense that the plaintiff’s counsel appears to lean on is that ChatGPT ‘assisted’ in researching these submissions, and had assured the lawyer – Mr. Schwartz – that all of these cases were real. The lawyers trusted ChatGPT enough to allow it to write an affidavit that they submitted to the court. With Mr. Schwartz likely to be sanctioned for this performance, it should also be noted that this is hardly the first time that ChatGPT and kin have been involved in such mishaps.
Gullible Counsel
With the breathless hype that has been spun up around ChatGPT and the underlying Large Language Models (LLMs) such as GPT-3 and GPT-4, to the average person it may seem that we have indeed entered the era of hyperintelligent, all-knowing artificial intelligence. Even more relevant to the legal profession is that GPT-4 seemingly
aced the Uniform Bar Exam
, which led to many to suggest that perhaps the legal profession was now at risk of being taken over by ‘AI’.
Yet the evidence so far suggests that LLMs are, if anything, mostly a hindrance to attorneys, as these LLMs have no concept of what is ‘true’ or ‘false’, leading to situations where for example ChatGPT will spit out a
list of legal scholars
convicted of sexual harassment, even when this is provably incorrect. In this particular 2023 case where law professor Jonathan Turley saw himself accused in this manner, it was fortunately just in an email from a colleague, who had asked ChatGPT to create such a list as part of a research project.
The claim made by ChatGPT to support the accusation against Turley was that a 2018 Washington Post article had described Mr. Turley as having sexually harassed a female student on a trip to Alaska. Only no such trip ever took place, the article cited does not exist, and Mr. Turley has never been accused of such inappropriate behavior. Clearly, ChatGPT has a habit of making things up, which OpenAI – the company behind ChatGPT and the GPT-4 LLM – does not deny, but promises will improve over time.
It would thus seem that nothing that ChatGPT generates can be considered to be the truth, the whole truth, or even a grain of truth. To any reasonable person – or attorney-at-law – it should thus be obvious that ChatGPT and kin are not reliable tools to be used with any research. Whether it’s for a case, or while doing homework as a (legal) student.
Use Only As Directed
Darth Kermit meme by Hannah Rozear and Sarah Park at Duke University Libraries.
In recent years, the use of LLMs by students to dodge the responsibility of doing their homework has increased significantly, along with other uses of auto-generated text, such as entire websites, books and YouTube videos. Interestingly enough, the actual generated text is often believable enough that it is
hard to distinguish
whether a specific text was generated or written by a person. But especially when the “
temperature
” is turned up — the LLM has been set to accept a broader range of next-word probabilities in generating its strings — the biggest give-away is often in citations and references in the text.
This is
helpfully pointed out
by Hannah Rozear and Sarah Park, both librarians at the Duke University Libraries, who in their article summarize why students at Duke and elsewhere may not want to lean so heavily on asking ChatGPT to do their homework for them. They liken ChatGPT to talking with someone who is hallucinating while under the influence of certain substances. Such a person will confidently make statements, hold entire conversations, but fail to follow any coherent reasoning or be able to provide evidence to back up these statements. This is basically why we stopped going to oracles to get life advice.
What both of them do think ChatGPT is good for is asking for leads on a specific topic, as well as where to find more information, such as library databases. You can even use ChatGPT as a fancy grammar and style checker, playing more to the strengths of an LLM. What they explicitly warn against, however, is to ask ChatGPT to summarize a source, to write a literature review for you, or for it to have any knowledge of current events.
In the end, you do not want to be the student who hands in work that ChatGPT ‘helped’ with, only to learn afterwards that your literature review paper references points that were not in the reviewed literature, and half the cited works and/or authors have never existed. Although this would be probably less awkward than when it happens to you as a lawyer, in the midst of a court case.
Never Trust Commercials
When Microsoft
announced its GitHub Copilot ‘AI’
, which was supposed to make it possible to generate entire blocks of code, or even programs with the press of a button, it had many people imagining that before long manually writing code would become obsolete, and even executives could generate the Next Big Thing with a simple query describing the application. It didn’t take long for reality to set in here, of course.
As reality began to set in, it dawned on people that writing code is (generally) more involved than simply asking Google and blindly copying code from the resulting StackOverflow and similar links. When does code contain a security vulnerability? What is the right way to elegantly encapsulate these complex dataflows without negatively impacting performance and future maintenance? Will Copilot maintain this code that I do not understand for me? Will Copilot write the accompanying documentation?
The same principle applies with writing a literature review and legal dissertation, in that as the person responsible for its production you are expected to understand every part of it. When you blindly trust that citations and references spit out by an LLM are true without due diligence, then it makes you the dunce.
In the case of Mr. Schwartz and his ill-fated attempts to improve his legal prowess, he failed to do even the barest modicum of cross-referencing, beyond asking ChatGPT whether it was sure these cases were real, with the following ChatGPT transcript from the affidavit illustrating the chatbot’s false confidence:
[Q:] ls varghese a real case
[A:] Yes, Varghese v., China Southern Airlines Co Ltd, 925 F.3d 1339 (11th Cir. 2019) is a real case.
[Q:] What is your source
[A:] I apologize for the confusion earlier. Upon double-checking, I found that the case Varghese v. China Southern Airlines Co. Ltd., 925 F.3d 1339 (11th Cir. 2019), does indeed exist and can be found on legal research databases such as Westlaw and LexisNexis. I apologize for any inconvenience or confusion my earlier responses may have caused.
[Q:] Are the other cases you provided fake
[A:] No, the other cases I provided are real and can be found in reputable legal databases such as LexisNexis and Westlaw.
What is likely to trip the average person up here is that ChatGPT maintains the same tone that a real person would, employing the first person (‘I apologize’) form, making it appear as if there is an intelligence capable of reasoning and comprehension behind the chat box. Thus when ChatGPT insists that it has found these cited cases in these real legal databases, it can instill a level of confidence that this is true, even when the proper course of action is to perform this check oneself.
More experienced ChatGPT users will certainly recognize “I apologize for the confusion earlier.” along with “
As an AI language model…
” as a warning sign to seek legal advice elsewhere.
Make-Believe AI
Although it is tragic that an attorney stands to lose his job due to ‘AI’, it’s illustrative that the reason for this is the exact opposite of what the media has been breathlessly warning about would happen. In the expectation that LLMs somehow express a form of intelligence beyond that of a basic SQL database, we have been both working up our fears of the technology, as well as using it for purposes for which it is not suitable.
Like any technology there are things for which it is suitable, but true intelligence is displayed in knowing the limitations of the technologies one uses. Unfortunately for those who failed the LLM intelligence test, this can have real-life consequences, from getting a failing grade to being fired or sanctioned. As tempting as it is here to point and laugh at Mr. Schwartz for doing a dumb thing, it would probably be wise to consider what similar ‘shortcuts’ we may have inadvertently stumbled into, lest we become the next target of ridicule. | 67 | 15 | [
{
"comment_id": "6647486",
"author": "Not Tragic",
"timestamp": "2023-05-29T14:32:08",
"content": "“Although it is tragic that an attorney stands to lose his job due to ‘AI’”I don’t think so. If he is taking this kind of shortcut in this case, what other clients has he served poorly? If he lacks the... | 1,760,372,285.113238 | ||
https://hackaday.com/2023/05/29/musical-robot-lets-you-play-the-recorder-hands-free/ | Musical Robot Lets You Play The Recorder Hands-Free | Robin Kearey | [
"Musical Hacks",
"Robots Hacks"
] | [
"arduino nano",
"recorder",
"robotic instruments",
"solenoid"
] | Although many people might remember the recorder as just a simple instrument from their introductory music classes, it can nevertheless produce rich and varied melodies in the hands of a virtuoso like Frans Brüggen. [Luis Marx] also took music lessons as a child, but never progressed much beyond an elementary level. Instead, he preferred to spend his time honing his engineering skills, which eventually enabled him to get back into music.
Initially, he wanted to build a piano-playing exoskeleton, to marionette his fingers up and down the ivories, but had to bail on that one because of the insane complexity. So instead, he built himself
a robot that helps him play the recorder
. (Video, in German, embedded below, fast-forwarded to the recorder part.)
A recorder has eight finger holes, which can be covered or uncovered in various combinations to produce tones. [Luis] therefore used eight solenoids, mounted on a 3D-printed frame, to actuate the finger holes. The basic idea worked, but getting the solenoids to fully cover the holes each time turned out to be a challenge: even a slight misalignment would cause air to leak past the plug and produce a horrible off-key sound.
After a lot of trial and error, [Luis] found foam earplugs to be a pretty good material for emulating human fingertips. He also discovered that relying on the solenoids’ spring tension to keep the holes closed was not reliable; a better solution was to flip the solenoids around and use the much larger force from their powered stroke to create an air-tight seal.
The solenoids are driven by an Arduino Nano through a set of MOSFET modules, powered by a lithium battery. [Luis] wrote some Arduino sketches with famous melodies like
Beethoven’s
Für Elise
, which sound quite decent on the robo-recorder: perhaps not on Frans Brüggen’s level, but pretty impressive for a self-declared “music noob” like [Luis].
Many robotic musicians play instruments like
pianos
or
xylophones
. Instruments from the flute family are harder to automate, but it has been
done
before
. We’ve even seen a
MIDI-powered harmonica
. | 6 | 5 | [
{
"comment_id": "6647460",
"author": "imqqmi",
"timestamp": "2023-05-29T11:26:28",
"content": "Nice project! Controlling your breath is also necessary depending on what note you play though. Some soft silicone casts could help with better finger simulates. Some kind of padding for the recoil of the ... | 1,760,372,285.003022 | ||
https://hackaday.com/2023/05/29/the-cctv-cameras-that-recorded-the-chernobyl-disaster-and-aftermath/ | The CCTV Cameras That Recorded The Chernobyl Disaster And Aftermath | Maya Posch | [
"Teardown"
] | [
"CCTV",
"Chernobyl",
"Chornobyl",
"vidicon"
] | The Soviet KTP-63-based remote-controlled camera system, including switch and control panel. (Credit: Chernobyl Family on YouTube)
When we picture the Chernobyl Nuclear Power Plant disaster and its aftermath, we tend to recall just the commonly shared video recorded by television crews, but the unsung heroes were definitely the robotic cameras that served to keep an eye on not only the stricken reactor itself but also the sites holding contaminated equipment and debris. These camera systems are the subject of a
recent video
by the [Chernobyl Family] channel on YouTube, as they tear down, as well as plug in these pinnacles of 1980s vidicon-based Soviet engineering.
When the accident occurred at the #4 reactor at the Chernobyl Nuclear Power Plant (
ChNPP
) in 1986, engineers not only scrambled to find ways to deal with the immediate aftermath but also to monitor and enter radioactive areas without exposing squishy human tissues. This is where the KTP-63 and KTP-64 cameras come into play. One is reminiscent of your typical security camera, while the other is a special model that uses a mirror instead of directly exposing the lens and tube to radiation. As a result, the latter type was quite hardy. Using a central control panel, multiple cameras could be controlled.
When mounted to remotely controlled robots, these cameras were connected to an umbilical cord that gave operators eyes on the site without risking any lives, making these cameras both literally life-savers and providing a solid template for remote-controlled vehicles in future disaster zones.
Editor’s note: Historically, the site was called
Чернобыль
, which is romanized to Chernobyl, but as a part of Ukraine, it is
now Чорнобиль or Chornobyl. Because the disaster and the power plant occurred in 1986, we’ve used the original name Chernobyl here, as does the YouTube channel. | 9 | 3 | [
{
"comment_id": "6647445",
"author": "Lee",
"timestamp": "2023-05-29T09:44:43",
"content": "To think I worked on some odd CCTV cameras, these take the cake.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647449",
"author": "Andrew",
"timestamp": "2023... | 1,760,372,285.165473 | ||
https://hackaday.com/2023/05/28/the-fascinating-evolution-of-micromouse/ | The Fascinating Evolution Of Micromouse | Danie Conradie | [
"Robots Hacks"
] | [
"autonomous robot",
"maze",
"micromouse"
] | You would think there are only so many ways for a robotic mouse to run a maze, but in its almost 50 year history, competitors in Micromouse events have repeatedly proven this assumption false. In the video after the break, [Veritasium] takes us on a fascinating journey through the
development of Micromouse
competition robots.
The goal of
Micromouse
is simple: Get to the destination square (center) of a maze in the shortest time. Competitors are not allowed to update the programming of their vehicles once the layout is revealed at the start of an event. Over the years, there have been several innovations that might seem obvious now but were groundbreaking at the time.
The most obvious first challenge is finding the maze’s center. Simple wall following in the first event in 1977 has developed into variations of the “flood fill” algorithm. Initially, all robots stopped before turning a corner until someone realized that you could cut corners at 45° and move diagonally if the robot is narrow enough. The shortest path is not always the fastest since cornering loses a lot of speed, so it’s sometimes possible to improve time by picking a slightly longer router with fewer corners.
More speed is only good if you can keep control, so many robots now
incorporate fans to suck them down
, increasing traction. This has led to speeds as high as 7 meters/second and cornering forces of up to 6 G. Even specks of dust can cause loss of control, so all competitors use tape to clean their wheels before a run. Many winning runs are now
under 10 seconds
, which require
many design iterations
to increase controllable speed and reduce weight.
All these innovations started as experiments, and the beauty of Microhouse lies in its accessibility. It doesn’t require much of a budget to get started, and the technical barrier to entry is lower than ever. We’ve looked at another
Micromouse design
before. Even if they aren’t micromice, we can’t get enough of
tiny robots
. | 15 | 9 | [
{
"comment_id": "6647418",
"author": "Jan",
"timestamp": "2023-05-29T05:54:32",
"content": "“You would think there are only so many ways for a robotic mouse to run a maze, but in its almost 50 year history, competitors in Micromouse events have repeatedly proven this assumption false.”The only thing... | 1,760,372,285.265832 | ||
https://hackaday.com/2023/05/28/electronic-connect-4-console-doesnt-use-lcd/ | ElectronicConnect 4Console Doesn’t Use LCD | Al Williams | [
"Arduino Hacks",
"Games"
] | [
"arduino",
"neopixel",
"ws2812"
] | You might think that making your own electronic games would require some kind of LCD, but lately, [Mirko Pavleski] has been making his using inexpensive 8X8 WS2812B LED panels. This lets even a modest microcontroller easily control a 64-pixel “screen.” In this case, [Mirko] uses an Arduino Nano, 3 switches, and a buzzer along with some 3D printed components to make
a good-looking game
. You can see it in action in the video below.
The WS2812B panels are easy to use since the devices have a simple protocol where you only talk to the first LED. You send pulses to determine each LED’s color. The first LED changes color and then starts repeating what you send to the next LED, which, of course, does the same thing. When you pause a bit, the array decides you are done, and the next train of pulses will start back at the first LED.
It looks like the project is based on
a German project from [Bernd Albrecht]
, but our German isn’t up to snuff, and machine translation always leaves something to be desired. Another developer added a play against the computer mode. This is a simple program and would be easy to port to the microcontroller of your choice. [Mirko]’s execution of it looks like it could be a commercial product. If you made one as a gift, we bet no one would guess you built it yourself.
Of course, you could play
a real robot
. You could probably repurpose this hardware for
many different games
, too. | 9 | 5 | [
{
"comment_id": "6647388",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-29T02:26:03",
"content": "“but our German isn’t up to snuff, and machine translation always leaves something to be desired.”“Paging Mr. Williams!Mr. Elliot Williams! “",
"parent_id": null,
"dept... | 1,760,372,285.213871 | ||
https://hackaday.com/2023/05/28/hackaday-links-may-28-2023/ | Hackaday Links: May 28, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"3d scan",
"am radio",
"borked",
"bricked",
"calculator",
"ev",
"firmware",
"ford",
"hackaday links",
"HP",
"HP-15C",
"inkjet",
"RPN",
"shipwreck",
"titanic"
] | The Great Automotive AM Radio War of 2023 rages on, with the news this week that
Ford has capitulated, at least for now
. You’ll recall that the opening salvo came when the US automaker declared that AM radio was unusable in their EV offerings thanks to interference generated by the motor controller. Rather than fixing the root problem, Ford decided to delete the AM option from their EV infotainment systems, while letting their rolling EMI generators just keep blasting out interference for everyone to enjoy. Lawmakers began rattling their sabers in response, threatening legislation to include AM radio in every vehicle as a matter of public safety. Ford saw the writing on the wall and reversed course, saying that AM is back for at least the 2024 model year, and that vehicles already delivered without it will get a fix via software update.
In other corporate oopsie news,
HP has apparently borked a bunch of printers with a firmware update
. The issue appears to go back to around May 8, and impacts OfficeJet 902x series printers. HP customer service reps seem to have been taken by surprise by this at first, telling people that the “83C0000B” error displayed on the locked-up screen on their printers was due to a print head problem. It didn’t take long to figure out that something had gone wrong with a firmware upgrade, but HP didn’t have much to offer by way of a solution. As of this writing, there still doesn’t appear to be a fix, so if you own one of these printers, you’re out of luck for now.
Speaking of HP,
they’re now selling a 40-year-old calculator for $120
, and we’re not the slightest bit mad about it. The HP-15C “Collector’s Edition” is a reissue of the iconic scientific calculator that first hit the market in 1982, a machine that many engineers made their bones on. Everything about the look and feel of the original, from the chunky and satisfyingly clicky keys to the blocky LCD display to the landscape-format layout is just like you remember it. We never owned one of these; we never really got the hang of RPN, so
the HP-22S
was a better fit for us. But we’ve been banging on this thing for the better part of 40 years now, so maybe it’s time to grab one of these. And really, $120 is a bargain considering that the 15C was originally priced at $135, and that was in 1982 dollars. Expect more unboxing videos like the one below as people get their hands (back) on the 15C.
Thallasophobia warning: those who wisely fear the yawning depths of the ocean really don’t need to check out
the new 3D scans of
Titanic
in her watery grave
. The ill-fated ship, which has been lying off the coast of Nova Scotia in almost 4,000 meters of water since 1912, has been photographed hundreds of times since being discovered in 1985. But getting a full portrait of the ship has never been possible, at least until now. A deep-sea mapping company, Magellan Ltd., spent most of 2022 collecting thousands of images with ROVs, which served as raw data for producing the 3D scans. The results are eerie, to say the least, and the level of detail is astonishing. Check out this guided tour of the wreck, from someone who really knows the Titanic, from stem to stern.
https://www.youtube.com/watch?v=zNWeUm0WnNw
And finally, if you’re looking for the best in automotive repairs and you just happen to be in the Houston metro area, you should check out
Hackaday’s own service center
. Sure, maybe they spell the name a little differently, but there’s no doubt they’ll get you fixed up and on your way in no time. | 20 | 11 | [
{
"comment_id": "6647365",
"author": "Dan",
"timestamp": "2023-05-28T23:02:41",
"content": "4000 meteres… What is that like 13,000 feet?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647372",
"author": "scott_tx",
"timestamp": "2023-05-28T2... | 1,760,372,285.3857 | ||
https://hackaday.com/2023/05/27/headsets-poor-range-fixed-by-replacing-antenna/ | Headset’s Poor Range Fixed By Replacing Antenna | Donald Papp | [
"Wireless Hacks"
] | [
"2.4 ghz",
"3d printed",
"antenna",
"corsair",
"enclosure",
"headset",
"range boost",
"usb",
"wireless"
] | [rafii6312]’s Corsair HS80 wireless headset had a big problem: short range. The sound quality was great, but the wireless range wasn’t winning any friends. Fortunately,
the solution was just to swap the small SMT antenna on the USB transmitter for an external one
.
Original SMT antenna (blue component) offers small size, but poor range.
This particular headset relies on a USB dongle to transmit audio from PC to headset over its own 2.4 GHz wireless connection. By popping open the USB dongle, [rafii6312] was able to identify an SMT antenna and easily desolder it, replacing it with a wired connection to a spare 2.4 GHz external antenna. That’s all it took to boost the headset’s range from barely one room to easily three rooms, which is a success by any measure.
Sadly, the USB transmitter dongle doesn’t have any intention of being opened and puts up a fight, so the process was a bit destructive. No problem, [rafii6312] simply fired up Fusion360 to design a new 3D-printed enclosure that accommodated the new antenna. Pictures, instructions, and 3D model files are all available on the project page, if you want to improve your headset, too.
This kind of antenna upgrade is reasonably straightforward, but if one is armed with the right knowledge,
antenna upgrades from scratch
using scrap wire and dollar store hardware are entirely possible. Just be sure to pick
an antenna that doesn’t weigh down your headset
. | 14 | 7 | [
{
"comment_id": "6647166",
"author": "Cyna",
"timestamp": "2023-05-27T23:10:11",
"content": "USB transceiver, not only transmitter.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647167",
"author": "TG",
"timestamp": "2023-05-27T23:25:52",
"conten... | 1,760,372,285.322447 | ||
https://hackaday.com/2023/05/27/minecraft-in-minecraft-on-the-chungus-ii/ | Minecraft In Minecraft On The CHUNGUS II | Elliot Williams | [
"Games"
] | [
"computer",
"cpu",
"CPU architecture",
"emulation",
"minecraft",
"redstone"
] | Minecraft is a simple video game. Well, it’s a simple video game that also has within it the ability to create all of the logic components that you’d need to build a computer. And building CPUs in Minecraft is by now a long-standing tradition.
Enter CHUNGUS II. The Computational Humongous Unconventional Number and Graphics Unit by [Sammyuri] is the biggest and baddest Minecraft computer that we’ve ever seen. So big, in fact, that it was finally reasonable to think about porting a stripped-down version of Minecraft to the computer itself. Yes, that’s right,
Minecraft running in Minecraft
. (Video embedded below.) Writing the compiler and programming the game brought two more hackers to the party, [Uwerta] and [StackDoubleFlow], and quite honestly, we’re amazed that a team as small as three people pulled this off.
Anyway, once you’ve picked your jaw up off the floor, also check out [Sammyuri]’s video on
just the CHUNGUS II computer itself
. (Also embedded below.) Seeing the architecture is interesting, even if you don’t speak Redstone as fluently as our heroes here. We love that the assembler creates a block of ROM – out of Minecraft blocks – that you can then cut/paste into the game’s reality.
For a “simple” game about breaking blocks and punching trees, Minecraft has inspired hackers to make the game better both inside and outside of the real world. For instance, for the latest in performant open-source Minecraft servers,
check out Folia
. Maybe, one day, they’ll build CHUNGUS II in the real world.
It could happen
.
Thanks [dbcdr] for the tip! | 16 | 7 | [
{
"comment_id": "6647155",
"author": "sears",
"timestamp": "2023-05-27T21:56:56",
"content": "Insert Ian Malcolm “You did it, you crazy SOB. You did it” meme here.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647194",
"author": "ono",
"tim... | 1,760,372,285.487111 | ||
https://hackaday.com/2023/05/27/beepberry-brings-memory-lcd-and-a-physical-keyboard-to-your-pi/ | Beepberry Brings Memory LCD And A Physical Keyboard To Your Pi | Navarre Bartz | [
"blackberry hacks",
"handhelds hacks"
] | [
"blackberry",
"keyboard",
"messaging",
"mobile messaging",
"physical keyboard",
"pi zero",
"raspberry pi",
"RPi"
] | As the 2020s are seeing the return of the flip phone, could we see a rebirth of other device form factors from before the slab era? [Eric Migicovsky] and [SQFMI] are working on a new physical keyboard device with
the Beepberry
.
Featuring a high contrast Sharp Memory LCD and the tried-and-true reliability of a BlackBerry keyboard, the device is designed for messaging all your contacts over WiFi without the distractions of a smartphone. As this is a collaboration with the Matrix-based chat service Beeper, the device is designed around the CLI version of their client.
If you want to eschew the distraction-free nature of the device, since it’s Pi-powered it can run any ARM Linux programs you might want as well being a playground for hardware mods. Add a DSP and headphone jack and this could be a neat little
pianobar
player. [Migicovsky] stresses this is currently a dev board and by no means should be assumed to be an off-the-shelf piece of kit.
If this looks like a familiar reuse of a BlackBerry keyboard, you might be remembering [arturo182]’s
Keyboard Featherwing
or this
LoRa Messenger
. | 9 | 4 | [
{
"comment_id": "6647118",
"author": "Maddie",
"timestamp": "2023-05-27T17:32:21",
"content": "Anyone know what the watch is in the picture at the top of the article?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647124",
"author": "Upgrade pi-top ... | 1,760,372,285.432069 | ||
https://hackaday.com/2023/05/27/hack-simple/ | Hack Simple | Elliot Williams | [
"Hackaday Columns",
"Rants"
] | [
"diy",
"ESP8266",
"esphome",
"hacks",
"home automation",
"mqtt",
"newsletter",
"simple"
] | Here at Hackaday, we definitely love to celebrate the hard hacks: the insane feats of reverse engineering, the physics-defying flights of fancy, or the abuse of cutting edge technology. But today I’d like to raise a rhetorical glass in tribute of the simple hacks. Because, to be perfectly honest, the
vast
majority of my hacks are simple hacks, and it’s probably the same for you too. And these often go unsung because, well, they’re simple. But that doesn’t mean that something simple can’t be helpful.
Case in point:
an ESP8266 press-buttons device
that we featured this week. It doesn’t do much. It’s main feature is that it connects to a home automation network over WiFi and enables you to flip three relays. Wires coming off the board are to be soldered to the not-yet-smart device in question, simply connected to each side of the button you’d like to press. In the example, a coffee machine was turned on and the “go” button pressed, automating one of the most essential kitchen rituals. While recording the podcast, I realized that I’ve built essentially this device and have it controlling our house’s heating furnace.
For the experienced hacker, there’s not much here. It’s a simple board design, the software heavily leverages
ESPHome
, so there’s not much work on that front either. But imagine that you lacked any of the wide-ranging skills that it takes to make such a device: PCB layout, ESP8266 software wrangling, or the nuances of designing with relays. You could just as easily build this device wrong as right. The startup costs are non-trivial.
Making a simple design like this available to the public isn’t a technical flex, and it’s not contributing to the cutting edge. But it just might be giving someone their first taste of DIY home automation, and a sweet taste of success. There’s not much easier than finding a switch and soldering on two wires, but if that’s the spark that pushes them on their path to greater hacks, that’s awesome. And even if it doesn’t, at least it’s another appliance under user control, connected to a private WiFi network rather than spying you out and phoning home to Big Toaster.
So here’s to the simple hacks!
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
! | 7 | 3 | [
{
"comment_id": "6647093",
"author": "Dan",
"timestamp": "2023-05-27T14:37:45",
"content": "Yay! Agree!Often the simplest things are the best, and the ones that last longest.I’ve got an arduino + Ethernet hat (long predates ESP+WiFi!) linked to my doorbell, to send push notifications to my phone for... | 1,760,372,285.536427 | ||
https://hackaday.com/2023/05/27/a-bullet-time-video-booth-you-can-build/ | A Bullet Time Video Booth You Can Build | Dave Rowntree | [
"digital cameras hacks"
] | [
"bullet",
"bullet time",
"dslr",
"Pico-W",
"video"
] | [Sebastian Staacks] built a video booth for his wedding, and the setup was so popular with family, that it was only fitting to do one better and
make some improvements to the setup
,
Matrix
-style. The “bullet time” video effect was introduced by the classic movie franchise and makes for a splendid video transition effect for video montages.
Hardware-wise, the effect is pretty expensive, requiring many cameras at various angles to be simultaneously triggered, in order to capture the subject in a fixed pose with a rotating camera. Essentially you need as many cameras as frames in the sequence, so even at 24 frames per second (FPS), that’s a lot of hardware. [Sebastian] cheated a bit, and used a single front-facing camera for the bulk of the video recording, and twelve individual DSLRs covering approximately 90 degrees of rotation for the transition. More than that is likely impractical (not to mention rather expensive) for an automated setup used in as chaotic an environment as a wedding reception! So, the video effect is quite the same as in the movies, as this is a fixed pose, but it still looks pretty good.
A Pico-W hidden in there providing a BT connected interface button
[Sebastian] did consider going down the Raspberry Pi plus Pi-cam route, but once you add in a lens and the hassle of the casing and mounting hardware, not to mention availability and cost, snagging a pile of old DLSRs looks quite attractive. Connectivity to the camera is a simple 3.5 mm jack for the focus and trigger inputs, with frames read out via a USB connection.
For practical deployment, the camera batteries were replaced with battery eliminator adapters which step-up the 5 V from the USB connection to the 7.4 V the cameras need, but the current spike produced by the coordinated trigger of all twelve cameras overwhelmed any power supply available. The solution, to be practical, and not at all elegant, is to just have lots of power supplies hidden in a box. Sometimes you’ve just got a job to do.
Reproducing this at home might be a bit awkward unless you have exactly the same hardware to hand, but the principles are sound, and there are a few interesting details to dig into, if you were so inclined.
We’ve seen a few takes on the bullet-time effect over the years. We featured a
Raspberry Pi-based hack
, a couple of years back, and earlier still, someone even
built a rig to take bullet-time videos of Tesla coil discharges
, because why not? | 8 | 5 | [
{
"comment_id": "6647075",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-05-27T12:51:11",
"content": "A lot of work and expense involved, but impressive results.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6647080",
"author":... | 1,760,372,285.643879 | ||
https://hackaday.com/2023/05/27/restoring-dot-matrix-printer-cartridges-for-2023/ | Restoring Dot Matrix Printer Cartridges For 2023 | Jenny List | [
"Retrocomputing"
] | [
"dot matrix printer",
"printer cartridge",
"printer ribon"
] | The noise of a dot matrix printer is probably as synonymous with 1980s computing as the modem handshake would become with the desktop experience a decade or more later. But unlike the computers that would have driven it, a dot matrix printer can still be a very useful device here in 2023. And why not? They’re cheap to operate and can produce surprisingly good quality when paired with suitable drivers. There is a snag though; while cartridges for popular models can still be found, there are plenty whose consumables are long gone. [Drygol] had an Apple ImageWriter II with exactly that problem, and after finding all his cartridges were non-functional,
took a look at how to bring them back
.
Inside a dot matrix cartridge is a fabric ribbon similar to the one that might once have been found on a typewriter. It’s not on a roll but folded into the space, and it’s drawn through by a pair of rollers. Not only had the ink on the fabric dried out, but the foam on the rollers had also disintegrated. Some careful dismantling, and a solution presented itself in the form of O-rings to replace the rollers. Those and a bit of mineral oil to soften the ink had the vintage Apple printing again as though it was the ’80s once more.
It’s a subject we’ve looked at before, as it turns out
WD-40 makes a good ink solvent
. | 17 | 10 | [
{
"comment_id": "6647067",
"author": "Dissy",
"timestamp": "2023-05-27T11:41:30",
"content": "I still have my ImageWritter II from the 2e days. It’s been awhile since I had it out but it was still working enough to show off the thunder scanner.The a2m0077 cartridges are still being produced, both i... | 1,760,372,285.951017 | ||
https://hackaday.com/2023/05/26/generating-hydrogen-peroxide-for-disinfecting-water-using-a-solar-driven-catalyst/ | Generating Hydrogen Peroxide For Disinfecting Water Using A Solar-Driven Catalyst | Maya Posch | [
"Science"
] | [
"hydrogen peroxide",
"water purification"
] | Ensuring that water is safe to use and consume can be a real chore, especially for those who live in impoverished areas without access to safe drinking water. Here is where researchers at Stanford University hope that their
recently developed low-cost catalyst
can make a difference. This catalyst comes in the form of nano-sized particles (nanoflakes) consisting out aluminium oxide, molybdenum sulfide, copper and iron oxide. When exposed to sunlight, the catalyst performs like a photon-sensitive semiconductor/metal junction (Cu-MoS
2
), with the dislodged electrons going on to react with the surrounding water, resulting in the formation of hydrogen peroxide (H
2
O
2
) and hydroxy radicals.
Disinfectant powder is stirred in bacteria-contaminated water (upper left). The mixture is exposed to sunlight, which rapidly kills all the bacteria (upper right). A magnet collects the metallic powder after disinfection (lower right). The powder is then reloaded into another beaker of contaminated water, and the disinfection process is repeated (lower left). (Image credit: Tong Wu/Stanford University)
Waterborne diseases are very common, with even the US
reporting
7,000 deaths and 120,000 hospitalizations in 2021, according to the US CDC, and many more affected worldwide. Much of the harm is done by microbes, in particular bacteria such as
E. coli
, which are prolific in aquatic environments. By using this catalyst powder in contaminated water, the researchers
reported
that the
Escherichia coli
colonies in the tested samples were fully eradicated after a 60 second exposure to sunlight.
The reason for this is that hydrogen peroxide and similar reactive oxygen species are highly destructive to living cells, yet they are simultaneously very safe. Because of their high reactivity they are very unstable and thus short-lived. This is useful when the water with the now very dead microbes is consumed afterwards, with the catalyst itself being ferromagnetic and thus easily separated using a magnet.
With this proof of concept in hand, it’d be interesting to see what the product will look like, especially when it comes to the final separation step and making this as easy as possible. Since the catalyst is not consumed or presumably contaminated, it can last pretty much forever, making it an attractive alternative to water purification tablets and expensive filtration systems.
(Heading image: Microscopic images of E. coli before (left) and after disinfection. The bacteria died quickly after sunlight produced chemicals that caused serious damage to the bacterial cell membranes, as shown in the red circles.
(Image credit: Tong Wu/Stanford University) ) | 35 | 11 | [
{
"comment_id": "6647046",
"author": "Gérald",
"timestamp": "2023-05-27T08:14:14",
"content": "About hydrogen peroxyde, beside microbes/bacteria, can it also kill fungus, especially spores? How long would it take, and what concentration is recommended?",
"parent_id": null,
"depth": 1,
"r... | 1,760,372,285.798169 | ||
https://hackaday.com/2023/05/26/where-exactly-did-that-network-packet-come-from/ | Where Exactly Did That Network Packet Come From? | Al Williams | [
"Network Hacks"
] | [
"ip geolocation",
"ipv4",
"IPv6"
] | Have you ever noticed that some websites can figure out, at least roughly, where you are? Sometimes they use it to find you a closer content provider. Or they might block you from seeing certain things while offering you other things specific to your location. This is possible because there are
databases that map IPs to locations
. [Mark Litwintschik] looks at using those databases from an API or downloading them into your own database. He also shows some very large database queries, which is interesting, too. He uses IPInfo, although there are other providers. Some only provide a limited number of lookups, but there are
plenty of free tiers
for low-volume usage.
The database changes every day. Of course, each provider has a different way of getting data, and so there are differences. [Mark] compares the IPInfo dataset against MaxMind’s also free database. That involved comparing over 3 billion records! Actually, the 3 billion are the number of IPs that matched up in both databases. There were an additional 118 million that didn’t match and 34 million that were not in the MaxMind database.
Of course, of the ones that didn’t match it is hard to say which one was correct. As [Mark] mentions, IP address get sold — they are worth about $45 each, he says — so an IP that is in Texas one day might be in Johannesburg tomorrow.
What would you do with this data? Beats us. Maybe your home automation system wants to reject IPs from outside your country. Perhaps your robot needs to show a different user interface based on the remote requestor’s location. Tell us your thoughts in the comments.
We are surprised the value of the
vanishing IPV4 addresses
isn’t higher. Of course, that’s partly because your IP address isn’t always the one
the rest of the world sees
. | 11 | 6 | [
{
"comment_id": "6647021",
"author": "Ostracus",
"timestamp": "2023-05-27T02:19:26",
"content": "Considering how leaky browsers are a lot can be found out.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6647061",
"author": "Alexander Wikström",
"timest... | 1,760,372,286.147536 | ||
https://hackaday.com/2023/05/26/fly-like-you-drive-with-this-flying-rc-drift-car/ | Fly Like You Drive With This Flying RC Drift Car | Dan Maloney | [
"drone hacks"
] | [
"dRehmFlight",
"drift car",
"drone",
"esc",
"flight controller",
"open source",
"quadcopter",
"rc",
"uav"
] | So it’s 2023, and you really feel like we should have flying cars by now, right? Well, as long as you ignore the problem of scale presented by
[Nick Rehm]’s flying RC drift car
, we pretty much do.
At first glance, [Nick]’s latest build looks pretty much like your typical quadcopter. But the design has subtle differences that make it more like a car without wheels. The main difference is the pusher prop at the aft, which provides forward thrust without having to pitch the entire craft. Other subtle clues include the belly-mounted lidar and nose-mounted FPV camera, although those aren’t exactly unknown on standard UAVs.
The big giveaway, though, is the RC car-style remote used to fly the drone. Rather than use the standard two-joystick remote, [Nick] rejiggered his
dRehmFlight
open-source flight control software to make operating the drone less like flying and more like driving. The lidar is used to relieve the operator of the burden of altitude keeping by holding the drone at about a meter or so off the deck. And the video below shows it doing a really good job of it, for the most part — with anything as complicated as the multiple control loops needed to keep this thing in the air, it’s easy for a sudden input to confuse things.
We have to admit that [Nick]’s creation looks like a lot of fun to fly, or drive — whichever way you want to look at it. Either way, we like the simplification of the flight control system and translating the driving metaphor into flying — it seems like that’ll be something we need if we’re ever to have full-size flying cars. | 9 | 6 | [
{
"comment_id": "6647010",
"author": "Ebin Beniz",
"timestamp": "2023-05-27T00:10:29",
"content": "There was a time where they drone manufacturers cared nothing for control theory. When their only experience of flight was a toilet seat, coming at them down a steel corridor.",
"parent_id": null,
... | 1,760,372,286.102429 | ||
https://hackaday.com/2023/05/26/nice-try-but-its-not-aperture-synthesis/ | Nice Try, But It’s Not Aperture Synthesis | Jenny List | [
"Radio Hacks"
] | [
"antenna array",
"satellite TV",
"tailgater"
] | Some of the world’s largest radio telescopes are not in fact as physically large as they claim to be, but instead are a group of telescopes spread over a wide area whose outputs are combined to produce a virtual telescope equal in size to the maximum distance between the constituents of the array. Can this be done on the cheap with an array of satellite dishes? It’s possible, but as [saveitforparts] found out
when combining a set of Tailgater portable dishes
, not simply by linking together the outputs from a bunch of LNBs.
The video below the break still makes for an interesting investigation and the Tailgater units are particularly neat. It prompted us to read up a little on
real aperture synthesis
, which requires some clever maths and phase measurement for each antenna. Given four somewhat more fancy LNBs with phase-locked local oscillators and an software-defined radio (SDR) for each one then he might be on to something.
If you’re curious about the cyberdeck in the video,
you might like to read our coverage of it
. And the Tailgater might be a bit small, but
you can still make a useful radio telescope from satellite TV parts
. | 17 | 7 | [
{
"comment_id": "6647009",
"author": "12AU76L6GC",
"timestamp": "2023-05-26T23:52:23",
"content": "It might not be synthetic aperture and obviously phase alignment won’t work at all (without special handling) with LEOs and MEOs, one of the methods of improving fairly unreliable Ku and KA band links ... | 1,760,372,286.055596 | ||
https://hackaday.com/2023/05/26/nokia-n-gage-qd-becomes-universal-bluetooth-gamepad/ | Nokia N-Gage QD Becomes Universal Bluetooth Gamepad | Donald Papp | [
"Cellphone Hacks",
"Games",
"Wireless Hacks"
] | [
"attiny85",
"bluetooth",
"gamepad",
"HC-06",
"N-Gage",
"nokia"
] | The Nokia N-Gage might not have put up much of a fight against Nintendo’s handheld dynasty, but you can’t say it didn’t have some pretty impressive technology for the time. [BeardoGuy] happens to have a perfectly functional N-Gage QD, which he
turned into a universal Bluetooth gamepad
.
The handheld runs a program that makes it act as a gamepad, and a DIY Bluetooth dongle is required on the client side. The dongle consists of an ATtiny85-based development board and HC-06 Bluetooth module, and will be recognized as a USB gamepad by just about anything it plugs in to.
[BeardoGuy]’s custom
GamepadBT
program sends button events via Bluetooth to the dongle, and those events are then sent via USB and look just like those from any standard gamepad.
This project can be used as a resource for how to implement a USB gamepad, whether on a Nokia N-Gage or not. You can see all the details at the project’s
GitHub repository
, and watch it in action in the video embedded below.
As for the
Nokia N-Gage
itself, one might be interested to know there’s an
up-to-date development environment
and even
Wordle
has been ported
to the N-Gage. It may look like a relic of the past, but it is far from being forgotten. | 5 | 3 | [
{
"comment_id": "6646967",
"author": "elwing",
"timestamp": "2023-05-26T19:19:39",
"content": "but can you phone with it?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6646987",
"author": "Michael Fitzmayer",
"timestamp": "2023-05-26T21:18:5... | 1,760,372,285.999014 | ||
https://hackaday.com/2023/05/26/learning-3d-printing-best-practices-from-a-pro/ | Learning 3D Printing Best Practices From A Pro | Tom Nardi | [
"Engineering",
"Hackaday Columns"
] | [
"3d printing",
"Additive Manufacturing",
"cnc",
"Hack Chat",
"machining",
"metal 3d printing"
] | It might seem like 3D printing is a thoroughly modern technology, but the fact is, it’s been used in the industry for decades. The only thing that’s really new is that the printers have become cheap and small enough for folks like us to buy one and plop it on our workbench. So why not take advantage of all that knowledge accumulated by those who’ve been working in the 3D printing field, more accurately referred to as additive manufacturing, since before MakerBot stopped making wooden printers?
That’s why we asked Eric Utley, an applications engineer with Protolabs, to
stop by the Hack Chat this week
. With over 15 years of experience in additive manufacturing, it’s fair to say he’s seen the technology go through some pretty big changes. Hes worked on everything from the classic stereolithography (SLA) to the newer Multi Jet Fusion (MJF) printers, with a recent focus on printing in metals such as Inconel and aluminum. Compared to the sort of 3D printers he’s worked with, we’re basically playing with hot, semi-melted, LEGOs — but that doesn’t mean some of the lessons he’s learned can’t be applied at the hobbyist level.
Eric Utley
The Chat started off with questions about what Eric’s day-to-day looks like, and what kind of awesome machines he gets to play with. After all not many of us will get access to a printer that can spit out something the size of a car engine, so we’ve got to live vicariously through others more fortunate than ourselves. This lead to something of a primer about the different printing technologies currently in use by the “Big Boys” for both plastic and metal parts.
Rather than fused deposition modeling (FDM), the process by which our desktop printers work, Eric says most of the time he’s dealing with some form of sintering. There’s several reasons for this, but one of the major ones is speed. Since there’s no time penalty for printing multiple objects, they can load the entire print surface up and maximize their efficiency. In one case Eric recalls they ran off 3,000 individual parts in a single 48 hour print.
Eventually the discussion moved on to the actual design of parts destined for a 3D printer, which is where things were arguably the most applicable for home gamers. Eric mentioned that sintering and jet fusion printing doesn’t require supports, as the powdered plastic itself provides a sort of scaffolding for the part as it’s being built up. But even if the part is being produced with a technology that would require support material, good designers try to avoid it as much as possible. Especially in the medical and aerospace fields, where internal supports could pose problems. As it turns out the rules here are pretty similar to what those of us with desktop machines are used to, such as making sure to keep angles steeper than 45°, and using chamfers in place of hard edges.
The same part, before and after optimizing for 3D printing.
Interestingly, Eric says one of the biggest problems they have is with wall thickness. Obviously there’s a minimal wall thickness for each different combination of material and printing technology, but more than that, he says rapidly varying the wall thickness of a printed metal part can lead to differential shrinkage which can compromise the whole part. If you can’t use a consistent wall thickness through your design, his recommendation is to make the transitions as gradual as possible, for example by using fillets.
It was also somewhat comforting to hear that, even with high-end industrial 3D printers, there are still dimensional accuracy issues to contend with. Case in point: holes on the side of objects. Eric says openings on the top and bottom aren’t so much of a problem since they’re essentially a stack of two-dimensional shapes, but once you have the a hole on the side of the object, the layer height of the print adds a new variable. The problem is serious enough that, if a part needs holes on the side, it will often be handled in an additional processing step: plastic parts will have the holes drilled after printing, and metal ones will have the openings machined to the proper tolerances. Just like at home!
In fact, for metal parts, there’s usually a fair amount of machining required after they come off the printer. Eric says that even in the best case, they shoot for a metal part to be 95% complete when the print is done. From there, it almost always needs a trip to the machine shop to be cleaned up. But he also says this isn’t really a quirk limited to 3D printing, and that cast metal components often need a similar level of post-processing to get the details right. As a side-effect, he notes that those who have experience designing parts for casting tend to do well when switching over to additive manufacturing.
We’d like to thank Eric for taking the time to join us this week in the Hack Chat. While we might never get to work on the class of machines at his disposal, we enjoyed hearing about the little details they have in common with our far more simplistic desktop printers — there’s a certain satisfaction in knowing even the pros occasionally struggle with the same issues we do.
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. | 13 | 5 | [
{
"comment_id": "6646972",
"author": "Conor Stewart",
"timestamp": "2023-05-26T19:53:14",
"content": "If you are going to do a comparison of a standard part and a part designed for 3D printing, you really need to keep the functionality the same or explain why the new model is more suitable. Having t... | 1,760,372,286.254389 | ||
https://hackaday.com/2023/05/26/hackaday-podcast-220-transparent-ice-fake-aliens-and-bendy-breadboards/ | Hackaday Podcast 220: Transparent Ice, Fake Aliens, And Bendy Breadboards | Al Williams | [
"Hackaday Columns",
"Podcasts"
] | [
"Hackaday Podcast"
] | You can join Elliot and Al as they get together to talk about their favorite hacks of the week. There’s news about current contests, fake alien messages, flexible breadboards, hoverboards, low-tech home automation, and even radioactive batteries that could be a device’s best friend.
We have a winner in the
What’s that Sound
competition last week, which was, apparently, a tough one. You’ll also hear about IC fabrication, FPGAs, and core memory. Lots to talk about, including core memory, hoverboards, and vacuum tubes.
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!
Or
download all the things
!
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 220 Show Notes:
News:
Hackaday Prize Assistive Tech Challenge Ending Soon
Op Amp Challenge End is in Sight
What’s that Sound?
Congratulations to this week’s winner, [Zach]! The sound was a trip hammer.
Interesting Hacks of the Week:
Simulated ET to Phone Home From Mars This Afternoon
If Aliens Came By, Would We Even Notice?
Building Circuits Flexibly
Slip and Clip (page 81)
According to [Robot Room] the tiny breadboards are “Contact Point Blocks”
Hoverboard Rides on Eddy Currents
Hoverboard Test (Hacksmith)
Tony Hawk Rides World’s First Real Hoverboard
The Wizard of Semiconductors
ESPClicker – An Elegant Solution for Integrating Dumb Devices into Home Assistant
SwitchBot
Bringing the PIO to the FPGA
Quick Hacks:
Elliot’s Picks:
Supercon 2022: Andy Geppert is Bringing Core Memory Back
Supercon 2022: Nick Poole Makes a Jolly Wrencher Tube
Keeping the Noise Down Under the Sea
Al’s Picks:
The Thousand Year (Radioactive) Diamond Battery
Remote-Controlled Hypercar Slices through Air
Will Carmakers Switch Clay for Computers?
Watch a Web Page Fetch Itself Over TLS, Complete with Commentary
(
The first rule of tautology club
)
Can’t-Miss Articles:
Airtags, Tiles, Smarttags and the Dilemmas of Personal Tracking Devices
Note: In the podcast, Elliot said that Airtags transmit the same number all the time. This is wrong. While they use a constant public key for encryption,
they also implement a rolling algorithm
based on a pre-shared key so that a new key is generated every 15 minutes.
The Art and Science of Making Beautiful Transparent Ice | 7 | 4 | [
{
"comment_id": "6646943",
"author": "Dude",
"timestamp": "2023-05-26T17:15:42",
"content": "Beer based drinks with ice is no travesty though. Some nice crisp Pilsener topped with lime soda, fresh mint, and crushed ice… mm-mm.",
"parent_id": null,
"depth": 1,
"replies": [
{
... | 1,760,372,286.201185 | ||
https://hackaday.com/2023/05/26/uav-flight-controller-saves-weight/ | UAV Flight Controller Saves Weight | Bryan Cockfield | [
"drone hacks",
"Raspberry Pi"
] | [
"compute module 4",
"fixed-wing",
"flight computer",
"quadcopter",
"raspberry pi",
"sandbox",
"uav",
"unmanned aerial vehicle"
] | When building autonomous airborne vehicles like drones or UAVs, saving a little bit of weight goes a long way, literally. Every gram saved means less energy needed to keep the aircraft aloft and ultimately more time in the air, but unmanned vehicles often need to compromise some on weight in order to carry increased computing abilities. Thankfully
this one carries a dizzying quantity of computer power for an absolute minimum of weight
, and has some clever design considerations to improve its performance as well.
The advantage of this board compared to other similar offerings is that it is built to host a Raspberry Pi Compute Module 4, while the rest of the flight controllers are separated out onto a single circuit board. This means that the Pi is completely sandboxed from the flight control code, freeing up computing power on the Pi and allowing it to run a UAV-specific OS like OpenHD or RubyFPV. These have a number of valuable tools available for unmanned flight, such as setting up a long range telemetry and camera links. The system itself supports dual HD camera input as well as additional support for other USB devices, and also includes an electronic speed controller mezzanine which has support for quadcopters and fixed wing crafts.
Separating non-critical tasks like cameras and telemetry from the more important flight controls has a number of benefits as well, including improved reliability and simpler software and program design. And with a weight of only 30 grams, it won’t take too much cargo space on most UAVs. While the flight computer is fairly capable of controlling various autonomous aircraft, whether it’s a multi-rotor like a quadcopter or a fixed wing device, you might need a little more computing power if you want
to build something more complicated
. | 12 | 3 | [
{
"comment_id": "6646935",
"author": "Myself",
"timestamp": "2023-05-26T16:40:47",
"content": "Wow! This is an impressive piece of work. I’ve had a similar idea tossing around in the back of my head for a while, but now I’m glad I didn’t pursue it yet because they’ve done it so much better!Of course... | 1,760,372,286.30665 | ||
https://hackaday.com/2023/05/26/this-week-in-security-gitlab-keypassmini-and-horse/ | This Week In Security: Gitlab, KeyPassMini, And Horse | Jonathan Bennett | [
"Hackaday Columns",
"Security Hacks"
] | [
"gitlab",
"KeyPass",
"This Week in Security",
"wordpress"
] | There’s
a really nasty CVSS 10.0 severity vulnerability in Gitlab 16.0.0
. The good news is that this is the only vulnerable version, and the fix came a mere two days after the vulnerable release. If you happened to be very quick to go to 16.0.0, then be very quick to get the fix, because CVE-2023-2825 looks like a bad one.
An unauthenticated malicious user can use a path traversal vulnerability to read arbitrary files on the server when an attachment exists in a public project nested within at least five groups.
That’s a very specific set of requirements for vulnerability, so it seems like hardly any installs would be vulnerable. The rest of the story is that regular users can create groups, and many installs allow for open user registration. So if you’re running Gitlab 16.0.0, update now!
KeyPassMini
A Redditor got a surprising notice that someone attempted to access a bank account, but failed two-factor authentication. That seemed odd, and
led the Redditor down the rabbithole of auditing applications
. And one iOS app in particular stood out as maybe problematic — KeyPassMini.
The app was
a
mobile client for KeyPass, the password manager. The problem was some analytics. It looks like KeyPassMini was bundling up some system information and uploading it to a server controlled by the creator. Analytics are often unpopular, but this app was including the system clipboard contents in the uploaded data. Yikes! And it gets worse: The app does password fills by using that same clipboard, so some of the protected passwords may have been scooped up into that analytics data. And sent unencrypted. Oof.
This is crazy. An iOS KeePass app was sending the clipboard contents *unencrypted via UDP* to a server. The developer "fixed" it by still sending it via UDP, but this time with fixed key and IV. 🤦♂️
The app is simply a credential stealer and probably in violation of some laws.
pic.twitter.com/yjzok2jkB1
— stacksmashing (@ghidraninja)
May 21, 2023
Now, the app author has pulled the plug on the app altogether, and
responded on the old Github project page
. It’s a bit odd, but it’s perfectly believable that there were no ill intentions here. Regardless, code to send the clipboard is a big problem, and definitely undoes a lot of trust in a project.
And KeyPass itself has a problem, though much less worrying.
KeyPass attempts to keep sensitive data out of its own memory when possible
. This approach aims to protect even in the event of a compromised machine.
[vdohney] on Sourceforge discovered that there is a channel to recover the master password
, by being just a bit clever. When a user types in the master password, by default, KeyPass will show the last letter typed, and replace the previous letters with bullets. But each iteration of that string ends up in program memory, so a privileged attacker can get a memory dump, look for the bullet characters, and find a set of leftover strings like
•a, ••s, •••s, ••••w, •••••o, ••••••r, •••••••d
. It’s an easy password grab. Now remember, this essentially implies an attacker has memory access on your system, so it’s not a gaping weakness in KeyPass.
As you can see from
the POC on GitHub
, the problem is that a .NET text box keeps the strings in memory, so it probably hits both Windows and Linux users under Mono. The proposed solution that the KeyPass team is taking is to poison the well with enough random characters that retrieving the correct password is a lot harder. It’s still getting fixed in the next release.
Horse Shell for MIPS Routers
Checkpoint Research brings us news of the Horse Shell
, a bit of malware specifically for MIPS architecture routers running Linux. It’s been found in TP-Link firmware images so far, but as so many of those routers are essentially based on the same Linux SDK, the malware appears to be applicable to many models. The exact firmware images being examined were found in a collection of tools used by Camaro Dragon, a rather catchy name for a Chinese APT group.
The firmware images have some of the normal bits you would expect, like data collection, remote shell, and remote proxy support. They have some really sneaky tricks, too, like storing part of the data on the partition reserved for WiFi calibration data. One has to wonder if hijacking that partition negatively affects the router’s wireless performance. In the firmware images examined, the quickest tell is to go to the firmware upgrade page. If it’s blank, without a form to upload new firmware, you may have the malicious image.
WordPress
WordPress 6.2.1 has a security fix, that is then improved upon in 6.2.2, where
block themes could parse user-generated shortcodes
. A shortcode is tags inside [brackets], that gets replaced by more complicated data. We use a code shortcode all the time here on Hackaday, to try to get source code to render nicely, angle brackets and all.
It turns out, the fix in 6.2.1
went a little overboard, breaking quite a few sites
by disabling shortcodes in block themes altogether. The situation in 6.2.2 is a bit better, with most of the problems being dealt with. Sometimes it’s hard to tell the bugs and the features apart.
And a WordPress plugin,
Beautiful Cookie Consent Banner, is under active attack
for a Cross-Site Scripting vulnerability. The attack is odd, as WordPress.org shows just 40,000 active installs, and almost 1.5 million sites have been sent the malicious payload to try to exploit the plugin. And the kicker?
It looks like the payload on this attack is a dud
, and fails to actually infect a vulnerable site. It can still goober a vulnerable site, so make sure to check your plugins.
Bits and Bytes
Speaking of plugins, be careful what VScode plugins you use.
They’re not all friendly
. Microsoft has been working to keep malicious plugins off the official marketplace, but that arms race never seems to have an end. And as such, there were a couple known malicious plugins with nearly 50,000 installs.
For some in-depth fun, check out
this PDF paper on Android Fingerprint Reader attacks
. It seems simple, right? Take a screenshot of a finger, compare it to a known data set, and lock the phone if the test fails too many times. It is, of course, not quite that simple. Researchers formulated two loopholes, Cancel-After-Match-Fail and Match-After-Lock, both of which abuse user-friendly features to manage way more attempts at a fingerprint read. Read the paper for the juicy details.
And finally, Troy Hunt had some fun at the expense of a scammer. Troy’s wife was selling a fridge on Gumtree, and they decided to play along with a suspicious “buyer”. Turns out, it’s the old agent fee scam. I’ll give you the money you asked for, plus $800 to cover the fee. Can you forward that extra money on? But of course, the Paypal confirmation message was faked, and there was no money paid. Troy managed to get an impressive bit of information, including that the scam is actually being run out of, you guessed it, Nigeria. Shipping would be a pain. ><
So
@Charlotte_Hunt_
is selling a fridge on Gumtree and immediately starts getting messages like this. The first one gets a bit of “no, we can discuss here” and they disappear. This one… gets a burner address to see how weird shit gets. What’s the angle? There’s always an angle…
pic.twitter.com/MRWep1MukS
— Troy Hunt (@troyhunt)
May 22, 2023 | 6 | 3 | [
{
"comment_id": "6646917",
"author": "Jan Praegert",
"timestamp": "2023-05-26T14:55:57",
"content": "P-P-P-PowerBook! Those were the times. Still laughing.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6646926",
"author": "asheets",
"timesta... | 1,760,372,286.353498 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.