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/2023/02/10/homebrew-ball-drop-machine-rings-in-the-new-year/ | Homebrew Ball Drop Machine Rings In The New Year | Lewin Day | [
"home hacks",
"LED Hacks"
] | [
"ball drop",
"New Year's Eve",
"nye"
] | The New Year’s Ball Drop in New York City stems from an old English naval tradition. These days, it’s more of a celebratory thing, and [Jon Gonzalez] wanted to bring a bit of that joy to his own celebrations.
Thus enter the Ball-Drop-O-Matic 3000.
The ball itself consists of two 3D printed halves assembled together with a linear bearing in the middle. It’s loaded up with a ton of addressable LEDs to give it plenty of flash, pomp, and circumstance as it rides down the flagpole. Animations are coded in to the K-1000C display controller using LEDEdit2014, an older piece of software which can turn Flash animations into commands to run WS2812B LED strips.
Lowering the ball is handled by a motorized winch. The winch is mounted at the base of the flagpole for aesthetic reasons, with the cable travelling up to the top of the pole, over a pulley, and back down to the ball. The descent speed is set to countdown the last minute of the year, with numbers animated on the ball itself.
The build was clearly a great addition to [Jon’s] New Years celebrations, even if it wasn’t quite finished until 9:35 PM on the big night.
We’ve seen other fun ball drop builds before, too
. | 0 | 0 | [] | 1,760,372,402.848517 | ||
https://hackaday.com/2023/02/09/domino-ring-machine-tips-tiles-in-a-never-ending-wave/ | Domino Ring Machine Tips Tiles In A Never-ending Wave | Donald Papp | [
"Art",
"Toy Hacks"
] | [
"domino",
"dominos",
"lego",
"mindstorms",
"soliton"
] | Like to see dominoes fall? [JK Brickworks] has got what you need, in the form of
a never-ending ring of falling and resetting tiles.
LEGO pieces are the star in this assembly, which uses a circular track and moving ramp to reset tiles after they have fallen. Timed just right, it’s like watching a kinetic sculpture harmoniously generating a
soliton wave
as tiles fall only to be endlessly reset in time to fall again.
A Mindstorms IR sensor monitors a tile’s state for timing.
It’s true that these chunky tiles aren’t actually dominoes — not only are they made from LEGO pieces and hinged to their bases, they have a small peg to assist with the reset mechanism. [JK Brickworks] acknowledges that this does stretch the definition of “dominos”, but if you’re willing to look past that, it’s sure fun to see the whole assembly in action.
The central hub in particular is a thing of beauty. For speed control, an IR sensor monitors a single domino’s up/down state and a LEGO Mindstorms EV3 with two large motors takes care of automation.
The video does a great job of showing the whole design process, especially the refinements and tweaks, that demonstrate the truly fun part of prototyping. [JK Brickworks] suggests turning on subtitles for some added details and technical commentary, but if you’re in a hurry
skip directly to 4:55
to see it in action.
Want to see more automated domino action?
This domino-laying robot
sets them up for you to knock down at your leisure, and this entirely different robot
lays out big (and we do mean BIG) domino art displays
. | 9 | 4 | [
{
"comment_id": "6596850",
"author": "Marcus",
"timestamp": "2023-02-10T08:43:15",
"content": "This is just beautiful, I get so nostalgic thinking back to my Lego days :)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6596852",
"author": "limroh",
"tim... | 1,760,372,403.230967 | ||
https://hackaday.com/2023/02/09/getty-images-is-suing-an-ai-image-generator-for-using-its-images/ | Getty Images Is Suing An AI Image Generator For Using Its Images | Lewin Day | [
"Artificial Intelligence",
"News"
] | [
"ai",
"getty images",
"lawsuit",
"legal",
"stable diffusion"
] | As per the Getty Images legal complaint, the Stable Diffusion AI seems to reproduce gooey versions of the Getty Images watermark in some of its output. Credit: Getty Images
Many AI systems require huge training datasets in order to achieve their impressive feats. This applies whether or not you’re talking about an AI that works with images, natural language, or just about anything else. AI developers are starting to come under scrutiny for where they’re sourcing their datasets. Unsurprisingly, stock photo site Getty Images is at the forefront of this, and is now suing the creators of Stable Diffusion over the matter,
as reported by
The Verge.
Stability AI, the company behind Stable Diffusion, is the target of the lawsuit for one good reason: there’s compelling evidence the company used Getty Images content without permission. The Stable Diffusion AI has been seen to generate output images that actually include blurry approximations of the Getty Images watermark. This is somewhat of a smoking gun to suggest that Stability AI may have scraped Getty Images content for use as training material.
The copyright implications are unclear, but using any imagery from a stock photo database without permission is always asking for trouble. Various arguments will likely play out in court. Stability AI may make claims that their activity falls under fair use guidelines, while Getty Images may claim that the appearance of perverted versions of their watermark may break trademark rules. The lawsuit could have serious implications for AI image generators worldwide, and is sure to be watched closely by the nascent AI industry.
As with any legal matter, just don’t expect a quick answer from the courts.
[Thanks to Dan for the tip!] | 43 | 18 | [
{
"comment_id": "6596641",
"author": "Severe Tire Damage",
"timestamp": "2023-02-10T03:27:50",
"content": "Ask for trouble and sometimes you get it.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6596757",
"author": "gsmag",
"timestamp": "202... | 1,760,372,403.039402 | ||
https://hackaday.com/2023/02/09/goniometer-gives-you-an-edge-at-knife-sharpening/ | Goniometer Gives You An Edge At Knife Sharpening | Navarre Bartz | [
"how-to",
"Laser Hacks",
"Tool Hacks"
] | [
"cutting tools",
"diy knife sharpening",
"goniometer",
"knife",
"knife sharpener",
"knife sharpening",
"knives",
"laser",
"laser goniometer",
"laser measurement",
"laser measuring"
] | Sometimes you absolutely, positively need to know the angle of the cutting edge on a knife. When you do, the best tool for the job is a laser goniometer, and [Felix Immler] shows us
three different ways to build one
. (YouTube)
The underlying principle of all three of these builds is to project reflected laser light off a knife blade onto a scale going from 0-45˚. [Immler] shows a basic demonstration of this concept with a hinge toward the beginning of the video (after the break). Blades with multiple bevels will reflect light to each of the appropriate points on the scale.
The simplest version of the tool is a printed PDF scale attached to a wooden box with a hole for the blade to pass through. The next uses a large pipe end cap and a drilled-out piece of wood to create a more manageable measuring tool. Finally, [Immler] worked with a friend to design a 3D printed goniometer with differently-sized adapters to fit a variety of laser pointers.
Now that you’re ready to precisely sharpen your blades, why not sharpen
this guacamole bot
or try making your
own knife from raw ore
? | 11 | 4 | [
{
"comment_id": "6596590",
"author": "scott_tx",
"timestamp": "2023-02-10T02:03:15",
"content": "this is much better than the gonorrheameter.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6596681",
"author": "The Commenter Formerly Known As Ren",
... | 1,760,372,402.953203 | ||
https://hackaday.com/2023/02/09/decorative-clock-uses-led-strips-to-beautiful-effect/ | Decorative Clock Uses LED Strips To Beautiful Effect | Lewin Day | [
"clock hacks"
] | [
"clock",
"led",
"ws2812b"
] | Clocks used to be dowdy old things with mechanical hands and sometimes even little cuckoo birds that would pop out to chime the hour.
[David] built something altogether more modern that uses shifting colors on LED strips to tell the time.
The core of the build is an ESP8266, which queries an NTP time server to keep itself synced up with the current time as accurately as possible. It then controls a WS2812B LED strip to display the time. The strip itself is hidden in a 3D-printed housing behind an opaque wooden ring, with the light from the LEDs diffusing out nicely on to the wall upon which the clock is mounted.
The display shows three “hands” in the colors it projects on the wall. The red second hand is projected inside and outside the ring. The minute hand is green, and projects outside the ring. Meanwhile, the hour hand is blue, and projects inside the ring. Without any numerical markings, you won’t get an exact reading of the time, but you can figure it out closely enough. As a bonus, the clock looks like a stylish light-based wall sculpture and your guests may not even realizes it tells the time.
We’ve featured [David’s] work before too, in the form of
the handy ESP8266 breadboard socket
. Video after the break. | 19 | 7 | [
{
"comment_id": "6596464",
"author": "NQ",
"timestamp": "2023-02-09T23:14:39",
"content": "I guess we’ve gone down this rabbit hole. Define ‘make.’",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6596469",
"author": "NO-U",
"timestamp": "2023-02-09T23:... | 1,760,372,403.287514 | ||
https://hackaday.com/2023/02/09/reverse-engineering-british-rail-tickets/ | Reverse Engineering British Rail Tickets | Jenny List | [
"Reverse Engineering",
"Transportation Hacks"
] | [
"aztec barcode",
"electronic ticket",
"rail ticket"
] | There was a time when to take a British rail journey was to receive a ticket barely changed since Victorian times — a small cardboard rectangle printed with the destination through which the inspector on the train would punch a hole. In recent decades these were replaced by credit-card-sized thin card, and now increasingly with scanable 2D codes from an app. These caught the attention of [eta],
and she set about reverse engineering their operation
.
The codes themselves are Aztec barcodes, similar to a QR code but with a single central fiducial mark. At first glance they resemble the codes used by non-UK ticketing systems, but she soon found out that they don’t follow the same standard. There followed a lengthy but fascinating trail of investigation, involving app decompilation of a dodgy copy of the ticket inspector app to find public keys, and then some work with a more reputably sourced app from another ticketing company.
Along the way it revealed a surprising amount of traveler data that maybe shouldn’t be in the public domain, and raises the question as to why the ticketing standard remains proprietary. It’s well worth a read.
If you’d like more UK rail ticket hacking,
it formed the subject of a talk at EMF 2022
. | 21 | 5 | [
{
"comment_id": "6596351",
"author": "TG",
"timestamp": "2023-02-09T21:01:30",
"content": "I went to the UK recently and everything was absolutely exorbitant. A sheep-shearing operation. If I lived there, I’d want to reverse-engineer that barcode too. People were just getting absolutely screwed ther... | 1,760,372,403.175003 | ||
https://hackaday.com/2023/02/09/ski-season-sees-apples-crash-detection-system-fire-deluge-of-false-positives/ | Ski Season Sees Apple’s Crash Detection System Fire Deluge Of False Positives | Lewin Day | [
"Hackaday Columns",
"News",
"Slider"
] | [
"apple",
"apple watch",
"crash detection",
"iphone",
"safety",
"skiing"
] | Smartphone features used to come thick and fast. Cameras proliferated, navigation got added, and then Apple changed the game by finally making touch computing
just work.
Since then, truly new features have slowed to a trickle, but Apple’s innovative crash detection system has been a big deal where safety is concerned.
The problem? It’s got a penchant for throwing false positives when iPhone and Apple Watch users are in no real danger at all. We first covered this problem
last year
, but since then, the wintery season has brought yet more issues for already-strained emergency responders.
Was That a Crash Or Are You Just Happy To Be Skiing?
Apple’s crash detection system was rolled out with the launch of the iPhone 14 and Apple Watch 8. After a high-acceleration event, it prompts users for a response before calling authorities for help.
Credit:
Apple
The crux of Apple’s safety system is the motion hardware built into all of its smartphones and Apple Watches. In particular, the Apple Watch 8 and iPhone 14 rely on this hardware to detect extreme acceleration events.
The logic is simple. If a person wearing a smartwatch or carrying a phone is subject to a serious acceleration event in excess of a few G, they’ve probably been in a nasty accident. The devices combine their motion sensor data with contextual clues, too. If the user is paired with a car via Bluetooth, or getting driving directions, they’ve probably been in a car accident. If they were logging a hike, they may have had a fall. If the system decides that an incident has occurred, it will first throw up a prompt on screen. If the user doesn’t respond, it will automatically call first responders, and provide them with the location of the incident.
If you’re incapacitated as a result of a car crash or a fall, such a system could literally save your life. It’s particularly useful if the incident happens on a remote road or a deserted trail, where you might otherwise be all alone.
The problem is that Apple’s hardware is susceptible to false triggers from perfectly safe high-acceleration events. Previously, we’ve heard of the system triggering
due to phones falling off of motorcycles or people riding rollercoasters
. The winter season has brought a new deluge of false alarms, though, as Apple’s customers hit the ski slopes in earnest. Skiing, snowboarding, and other associated winter sports often involve high speeds and big jumps, which can readily generate high acceleration events. These are erroneously determined to be crashes or falls by iPhones and Apple Watches. Few skiers are checking their devices during the middle of a run, so the devices inevitably end up calling first responders after the user fails to respond. Authorities aren’t in the habit of ignoring 911 calls, and so much effort is wasted on responding to these needless false alarms.
In the US, iPhones and Apple Watches will contact 911 and play an automated message outlining what has occurred and the individual’s current location.
Credit:
Apple
The problem has been severe in Colorado,
where authorities have reported a deluge of false alarms from Apple devices. When callers don’t respond, dispatchers must send ski patrollers to head to the area of a reported incident to verify there isn’t an injured skier in need of assistance. The director of Summit County’s 911 Center reported that the agency hasn’t had a single legitimate call from the system, despite many false positives.
In British Columbia, Canada, helicopter rescuers have regularly flown out to reports
only to find nobody around
. In many cases, it’s suspected iPhones or Apple Watches may have bounced around sitting in backpacks or snowmobile storage compartments, triggering the calls. Utah has also seen significant numbers of calls
coming in from Apple devices activated by Crash Detection.
Agencies reported up to three to five calls per day during the December ski period. Most skiers called back by authorities were unaware their device had made a call at all, though many were able to give the all-clear prior to rescuers being dispatched.While the false alarms are frustrating, Utah authorities aren’t asking skiiers to switch the feature off. Instead, they’re glad that there is a safety net for those that may get injured on the mountains far from help.
Disabling Crash Detection does make sense in some contexts. On a rollercoaster, for example, the likelihood of injury is low. Plus, there are many bystanders and staff around to assist anyone that comes to harm. However, out on the ski slopes, there’s often nobody around for miles, so disabling the safety features isn’t necessarily the way to go. It’s a nice thing to have when you’re out skiing alone or in a small group.
Apple has made regular updates to its system, most recently with iOS 16.2. However, the regular occurrence of these false alarms indicate the software hasn’t been perfected yet. The latest revision of Crash Detection now asks users
if a false alarm has been triggered
, which should help Apple collect data to refine the system.
Apple really needs to be sending a few dozen engineers on a ski holiday to collect data and refine the detection regimes for winter sports use. Some measures to detect whether a device is being worn or simply left in a backpack to shake around may also be useful. In the latter case, high accelerations are always going to be a problem, and the user won’t be looking at the device to call off the alarm. At the very least, Apple would do well to better educate its users on how its Crash Detection system works, how it can best protect them, and how to ensure they’re not inadvertently causing grief for the hard-working emergency responders who are out there to help.
Featured image: “
Sturz
” by Yashima. | 39 | 13 | [
{
"comment_id": "6596234",
"author": "Ostracus",
"timestamp": "2023-02-09T18:28:19",
"content": "Geofencing, loud audio alerts, send drones to see if the situation is real.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6596400",
"author": "TG",
... | 1,760,372,403.430362 | ||
https://hackaday.com/2023/02/07/connecting-a-keyboard-to-a-vintage-pc-xt-the-hard-way/ | Connecting A Keyboard To A Vintage PC-XT, The Hard Way | Dan Maloney | [
"Retrocomputing"
] | [
"arduino",
"assembler",
"keyboard",
"Model 5160",
"motherboard",
"PC-XT",
"post",
"PS/2",
"video"
] | We’re not sure if there’s any single characteristic that qualifies someone as a hacker. After all, we’re a pretty eclectic bunch, with skills that range all over the map, and what one person feels is trivial, others would look upon as black magic. But there’s one thing we’re sure of: if you find yourself reading
the original POST code for the PC-XT motherboard just to get a keyboard working
, you’re pretty much our kind of people.
That was the position [Anders Nielsen] found himself in as work progresses on his “PC-XT from Scratch” project, which seeks to build a working mid-80s vintage IBM Model 5160 using as many period-correct parts as possible. The
first installment
of the series featured the delicate process of bringing the motherboard up, lest the magic smoke was released. After seeing some life out of the old board, [Anders] needed a little IO, specifically video and keyboard. The video side of the equation was relatively trivial, with an early-90s VGA card from eBay — not exactly period correct, but good enough to get something to display.
The keyboard was another matter entirely. It’s not too much of a chore to find a keyboard that’ll talk to a PC-AT, but the PC-XT had an entirely different protocol, not to mention that chunky 5-pin DIN connector. As with many things, the solution involved building an adapter out of an Arduino, but the process was not exactly low-friction. First, there was the question of dealing with the open-collector outputs on the keyboard, which required code changes. Next, [Anders] broke out the oscilloscope to check waveforms, and found a weird 9-Hz square wave on top of the keyboard clock signal. That ended up being a sign that the keyboard was stuck in a manufacturing test mode, according to a read-through of the power on self-test (POST) source code. A tiny tweak of the Arduino code got everything working.
We’ve got to say that we’re loving this deep dive into the internals of a piece of computer history. [Anders] teased the next step, which will use an empty ROM socket on an old network card to load some assembly code onto the XT. We’re very much looking forward to that exploit. | 16 | 6 | [
{
"comment_id": "6594867",
"author": "daveboltman",
"timestamp": "2023-02-08T06:46:37",
"content": "Great deep dive, thank you!Back in the day I needed print some code I wrote on my [Spectravideo SVI-328](https://en.wikipedia.org/wiki/SV-328), so I made it “type” the code into the keyboard input of ... | 1,760,372,403.349373 | ||
https://hackaday.com/2023/02/07/led-displays-may-get-vertical-integration/ | LED Displays May Get Vertical Integration | Al Williams | [
"LED Hacks",
"Science"
] | [
"display",
"led",
"MicroLED"
] | If you zoom into the screen you are reading this on, you’d see an extremely fine pattern of red, green, and blue emitters, probably LEDs of some kind. This somewhat limits the resolution you can obtain since you have to cram three LEDs into each screen pixel. Engineers at MIT, however, want to do it differently. By growing thin LED films and sandwiching them together, they can produce
4-micron-wide LEDs
that produce the full range of color, with each color part of a vertical stack of LEDs.
To put things in perspective, a standard TV LED is at least 200 microns across. Mini LEDs measure upwards of 100 microns, and micro LEDs are the smallest of all. A key factor for displays is the pitch — the distance from the center of one pixel to the center of the next. For example, the 44mm version of the Apple Watch has a pitch of around 77 microns. A Samsung Galaxy 10 is just over 46 microns. This is important because it sets the minimum size for a high-resolution screen, especially if you are building large screens (such as when you build custom video walls (see the video below for more about that).
For example, consider a 4K screen with 3840×2160 pixels. If you can only do a 0.1mm pitch, your monitor will have to be at least 16 inches wide. A 4K TV with a 75-inch screen needs a 432 micron pitch, but to make a 24-inch screen with the same resolution requires 138 microns. While that means it is easier to make a large high-resolution display, it is harder to view the large screen up close. This can be a problem for computer monitors or VR headsets.
But imagine if these new LEDs would allow, say, 10 micron pitch. Then you could pack a 4K screen into a bit more than an inch and a half! VR headsets could easily be 4K if this were possible.
So far, the team has made a single multicolor pixel. Of course, they want to continue to produce a true array. Some of the overhead of that will reduce the pixel density, but it still could offer impressive results.
If you want to read more
about microLED technology
, [Maya] can help with that. Until this new tech goes mainstream, OLED is still the one to beat. You can actually
make your own
. | 36 | 13 | [
{
"comment_id": "6594811",
"author": "UT",
"timestamp": "2023-02-08T03:23:46",
"content": "Um… most screens are LCDs with LED backlight these days. Some mobile device might use OLED, but they aren’t the norm.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6... | 1,760,372,403.110563 | ||
https://hackaday.com/2023/02/07/old-3d-cad-mouse-gets-new-lease-of-life/ | Old 3D CAD Mouse Gets New Lease Of Life | Anool Mahidharia | [
"computer hacks"
] | [
"3d mouse",
"3dconnexion",
"3DxWare",
"Magellan",
"pico",
"raspberry pi",
"Raspberry Pi Pico",
"rs-232",
"spacemouse",
"SpaceMouse Compact",
"UF2"
] | [Jacek Fedorynski] had an old Magellan/SpaceMouse 3D mouse with a serial interface which made it impossible for him to use with modern hardware and software. The problem he faced was two pronged – the absence of serial interfaces in the hardware and the lack of appropriate drivers for the operating system. So he built a low cost, simple adapter to use his
RS-232 Magellan/SpaceMouse with modern software
.
The hardware required to build the adapter was minimal. A Raspberry Pi Pico, a MAX3238 based RS-232 adapter, a null modem adapter and a DB9 gender changer. Of course, a combination null modem – gender changer would have made things even simpler. Four of the GPIO pins from the Pico are mapped to the serial RX, TX, RTS and CTS pins.
On the software side, the code emulates a 3DConnexion SpaceMouse Compact, so it can be used with software like Fusion 360, 3ds Max, SolidWorks, Inventor, Maya and many others. On the host computer, only the standard 3DxWare driver package is needed. On the host computer, the old Magellan/SpaceMouse 3D will appear like a modern SpaceMouse Compact connected over USB. The only downside to this is that the SpaceMouse Compact has just two programmable buttons, so only two of the many buttons on the old Magellan mouse can be mapped.
Flashing the code to the Pico is also straightforward using the BOOTSEL mode. Hold down the BOOTSEL button when plugging in the Pico and it appears as a drive onto which you can drag a new
UF2 file
. Just drag-n-drop [Jacek]’s magellan.uf2 firmware and you’re done.
If you’d rather build your own, modern 3D mouse, check out the
DIY Cad Mouse You Can Actually Build
. | 11 | 6 | [
{
"comment_id": "6594797",
"author": "Jon H",
"timestamp": "2023-02-08T02:31:34",
"content": "Seems like the Magellan’s buttons could be supported by having a second Pico to act as a second USB device, with the first Pico passing the button presses to the second Pi. Then those buttons wouldn’t be li... | 1,760,372,402.903285 | ||
https://hackaday.com/2023/02/07/clock-your-camera-with-this-shutter-speed-tester/ | Clock Your Camera With This Shutter Speed Tester | Chris Wilkinson | [
"Arduino Hacks"
] | [
"arduino",
"camera shutter",
"photography",
"shutterspeed"
] | Camera shutter speed is an essential adjustment in photography – along with the aperture, the shutter moderates the amount of light entering the camera. Older cameras (and some newer ones) use mechanical shutters that creep out-of-spec over the years, so
[Dean Segovis] built a handy shutter speed tester
.
With just a handful of basic components, this project is a great one for beginners to sink their teeth into. The tester is based around a photoresistor that measures light from another source (a flashlight) that travels through the camera body. When the shutter on the camera is released, the shutter speed can be measured and displayed on the OLED screen. An Arduino naturally handles all the computational duties. The whole thing can be easily assembled on a breadboard in just a couple of minutes.
The original project by [hiroshootsfilm] is over on
Project Hub
, however [Dean] takes a deeper dive with some code troubleshooting, as well as trying out a variety of old film cameras with the breadboard tester. His testing revealed that the photoresistor was better able to detect shutter speed when the camera lens was removed, which is a hot tip for anyone else that wants to try this.
While it’s not surprising that these older cameras are having trouble with their mechanical shutters, this little tester would be an invaluable tool when it comes time to start tweaking shutter mechanisms. If this project has brought out the shutterbug in you, make sure to check out this
brain transplant for a Polaroid 100-series Packfilm camera
that we covered way back in 2011. | 27 | 11 | [
{
"comment_id": "6594690",
"author": "Tweepy",
"timestamp": "2023-02-07T22:40:31",
"content": "Nice, but maybe overkill?I’ve been checking old camera shutter with no more than a scrap solar cell and a scope.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "659... | 1,760,372,403.598671 | ||
https://hackaday.com/2023/02/07/solar-powered-e-bike-replaces-car-trips/ | Solar Powered E-bike Replaces Car Trips | Navarre Bartz | [
"green hacks",
"Transportation Hacks"
] | [
"bicycle",
"bike",
"cargo bike",
"charge controller",
"charging",
"ebike",
"hub motor",
"motor controller",
"mppt",
"solar",
"solar bike",
"solar panel"
] | E-bikes can replace car trips for some people, and adding a solar panel can make the fun last longer. [Luke] did some heavy modifications to his RadWagon to make it
better, stronger, and faster
than it was before.
The first step was replacing the stock 750 W controller with a 1500 W model to give the motor twice the power. [Luke] plans to replace the motor if it gets fried pushing too much juice, but is planning on just being careful for now. To stop this super-powered ride, he swapped the stock mechanical discs out for a hydraulic set which should be more reliable, especially when loading down this cargo bike.
On top of these performance enhancements, he also added a 50 W solar panel and
maximum power point tracking (MPPT)
charge controller to give the bike a potential 50% charge every day. Along with the OEM kid carrier and roof, this bike can haul kids and groceries while laughing at any hills that might come its way.
Checkout this
other solar e-bike
or this one
making a trip around the world
for more fun in the sun. | 20 | 8 | [
{
"comment_id": "6594573",
"author": "Jan Praegert",
"timestamp": "2023-02-07T19:49:01",
"content": "“potential 50% charge every day” means: on a very sunny day. So in spring and autumn it might be at 20% and in the wintertime it is around nothing or below.Solution: two batteries and stationary moun... | 1,760,372,403.501427 | ||
https://hackaday.com/2023/02/07/fox-fined-for-broadcasting-emergency-tone-in-football-ad/ | Fox Fined For Using EAS Tone In Football Ad | Lewin Day | [
"Hackaday Columns",
"News",
"Slider"
] | [
"EAS",
"EBS",
"emergency alert system",
"Emergency Broadcast System",
"fcc",
"federal communications commission",
"fine",
"fox"
] | The Boy Who Cried Wolf
is a simple parable that teaches children the fatal risk of raising a false alarm. To do so is to risk one’s life when raising the alarm about a real emergency that may go duly ignored.
Today, we rarely fear wolves, and we don’t worry about them eating us, our sheep, or our children. Instead, we worry about bigger threats, like incoming nuclear weapons, tornadoes, and earthquakes. We’ve built systems to warn us of these calamities, and authorities take a very dim view of those who misuse these alarms. Fox did just that in a recent broadcast, using a designated alarm tone for an advert. This quickly drew the attention of the
Federal Communication Commission
.
The Emergency Alert System is Not To Be Trifled With
The Emergency Alert System (EAS) is a nationwide emergency broadcasting system that allows the quick and timely delivery of crucial information. It’s capable of broadcasting emergency updates via television, whether broadcast, satellite, or cable, as well as via AM, FM, and satellite radio. The EAS took over from the original
Emergency Broadcast System
in 1997, which itself was predated by the
CONELRAD system
which dated back all the way to 1951.
Emergency alert as captured on the Weather Channel. Some broadcasters will cut over video to a full textual display as above, while others will put the text in a thin red band over the regular content. Credit:
YouTube
The characteristic angry digital tones of the Emergency Alert System actually contain data encoded using the Specific Area Message Encoding protocol, a technology developed by the National Weather Service. Broadcast stations monitor other radio and TV stations, listening out for these tones. Alerts are first played out via a selection of 77 “primary” alert broadcasters, and other stations monitoring them then rebroadcast the same alerts in a daisy-chained fashion. The data within the tones tells equipment in any given TV or radio broadcaster who originated the emergency alert, what the alert is about, and the affected area, along with other metadata. Based on this data, equipment in any given broadcast station will determine whether or not to begin broadcasting the given alert. For example, a broadcast station in New York won’t rebroadcast tornado warnings for Texas. However, if the President is on the blower and desperately needs to talk to the nation, the station will broadcast the alert over normal programming. Broadcasters are legally required to play any applicable alert messages by diktat of the FCC. Outside of the digital tones containing the alert information, the EAS shortly follows this with an “attention tone” which combines 853 Hz and 960 Hz sine waves. This is an annoying and attention-grabbing sound that approximates the musically-ugly major second interval, and was carried over from the Emergency Broadcast System.
The characteristic tones of the Emergency Alert System are prohibited from general broadcasting by the Federal Communication Commission (FCC). They may not be played outside of real alerts, regular tests, or special pre-authorized public service announcements. This is for multiple reasons. Any such false alerts that end up on radio or TV could trigger the Emergency Alert System hardware in other broadcasters, which would cut over programming as in a genuine alert. Beyond that, there is the risk of individuals becoming desensitized to the alerts, and not taking them seriously. The attention tones, in particular, are intended to warn people of risks to their very lives. Outside of necessary routine testing, they shouldn’t be used.
A sample Emergency Alert System broadcast. Note the digital sounds of the alert data and the warning message cut-in. Don’t play this on radio or TV lest you want the attention of the FCC.
Fox’s Folly
Fox used three seconds of the EAS attention tone in this NFL football advert. That was enough to draw a half-a-million dollar fine from the FCC. Credit:
YouTube
Fox’s error was using three seconds of the Emergency Alert System’s attention tone to promote a football broadcast on several of its television channels. The idea is simple: use an emergency warning tone to capture the attention of viewers, and then deliver the desired advertising while they’re concentrating on the message. It’s a cheap and callous trick, so it’s perhaps little surprise it ended up in advertising.
The FCC looks dimly upon such tactics. The broadcaster was found guilty of playing the “comedic” ad on 190 affiliated broadcast TV stations as well as on Fox Sports Radio and the Fox Sports XM channel.
The proposed fine for the misdeed was $504,000.
Sadly, it’s not the only case of emergency alerts being misused for attention-grabbing adverts. WLTV in Florida similarly caught a large fine back in 2016 for using similar tactics to advertise the Summer Olympics, along with the phrasing “This is not a test, this is an emergency broadcast transmission.”
Outside of advertising, the FCC doesn’t allow broadcasts of these tones in context, either. Cable companies have received fines for broadcasting the tones within movies, and CBS drew punishment for including a masked tone in the background audio of a scene of Young Sheldon. In the latter case, the warning was completely anachronistic and didn’t make any sense. The characters in the show were watching television in the early 1990s, yet somehow the Texas broadcasters were using EAS tones that weren’t in use until 1997. CBS had pre-tested the masked audio in the episode with EAS equipment to ensure it wouldn’t cause other broadcasters to latch on to the tones and rebroadcast the alert message. However, the FCC deemed that it shouldn’t have been broadcasting the tones in the first place.
The Emergency Alert System is a vital piece of emergency infrastructure. One might expect broadcasting professionals to treat this system with respect. However, time and again, various broadcasters, both big and small, have chosen to use the EAS’s recognizable tones for their own gains. The rules are out there in black and white, and many have already fallen afoul of them. It’s thus hard to excuse any US broadcaster that willingly chooses to misuse emergency broadcast audio. | 82 | 25 | [
{
"comment_id": "6594490",
"author": "cbarn",
"timestamp": "2023-02-07T18:10:08",
"content": "Good – if only we could get them to fine advertisers who include sirens and horns as well, that’d be great. Those have triggered more than one “What the heck?!?” while driving the daily commute!",
"par... | 1,760,372,404.429994 | ||
https://hackaday.com/2023/02/07/come-join-us-for-hackaday-berlin/ | Come Join Us For Hackaday Berlin! | Elliot Williams | [
"cons",
"Hackaday Columns",
"News",
"Slider"
] | [
"conference",
"Hackaday Berlin",
"Hackaday Berlin 2023",
"lightning talks"
] | It’s been far too long since we’ve had an event in Europe, and we’re going to fix that right now.
Hackaday Berlin 2023
will be a day-long conference full of great talks, badge hacking, music, art, madness, and gathering with your favorite hackers on Saturday, March 25.
But it doesn’t stop there. We’ll have a pre-event party Friday night, and then a bring-a-hack brunch on Sunday with further opportunities to show off whatever projects you’re bringing along, hack some more on the badge, wind down, and/or play together. So if your travel plans allow it, come in Friday mid-day and don’t schedule your return ticket until Sunday evening.
Cutting to the chase: early bird tickets are on sale right now,
so go get one
! But even if you miss out on those, and they’ll go like hotcakes, the regular tickets are well worth it. Everything is fully catered, the badge and the swag are phenomenal, and the talks will be first-rate.
Last time we were in Europe, the party went on until 2 AM!
Saturday’s main events will include a handful of fantastic invited guest talks, but also a few hours of Lightning Talks given by you – yes, you! If you’ve never attended a lightning talk, you get seven minutes to run through one of your favorite projects. We want to know what’s on your workbench right now, what new skills you’ve been teaching yourself, or the groundwork you’ve been laying for the next big project. It’s your chance to inspire everyone in the room – grab it.
Everyone asked us to do a second run of the
2022 Hackaday Supercon badge
, and now we’ve got the perfect excuse! Designed by Voja Antonic, the badge is a standalone retrocomputer in the style of an Altair or similar, but it’s much more. Between blinking LEDs that display everything going on, down to the gates in the ALU, and a trimmed-down machine language, it’s an invitation to get deeply in touch with the machine. If you felt left out because you couldn’t travel to Pasadena last November, here’s your second chance.
And then there’s the crowd. Hackaday really is a global community of hackers, and Hackaday events tend to bring out the best. Even if you’re not planning to give a lightning talk (and you should!) be prepared to talk about what you’re doing, because everyone else there is just as interested in cool projects as you are. Hackaday Berlin will be a great opportunity to connect and reconnect with new and old friends alike. Come join us!
We’ll be following up with a speaker announcement next week, but if you have any questions, let us know in the comments below. Otherwise, we’ll see you in Berlin. | 54 | 23 | [
{
"comment_id": "6594478",
"author": "davedarko",
"timestamp": "2023-02-07T17:39:23",
"content": "Got my ticket, seems like it was a good idea to follow hackaday on eventbrite ;PIf anybody wants to stay in Berlin a bit longer, xHain Hack & Makespace has an open evening on Monday, but I can also offe... | 1,760,372,403.970686 | ||
https://hackaday.com/2023/02/08/building-a-plasma-piano-aint-easy/ | Building A Plasma Piano Ain’t Easy | Lewin Day | [
"Musical Hacks"
] | [
"arc",
"high voltage",
"hv",
"plasma"
] | Electronic arcs can be made to “sing” if you simply modulate them on and off at audible frequencies. We’ve seen it done with single Tesla coils, and even small Tesla choirs,
but [Mattias Krantz] took this to extremes by building an entire “plasma piano” using this very technique.
The build relies on ten transformers more typically used in cathode ray tubes. The transformers are capable of generating high enough voltages to create arcs in the air. The transformers are controlled by an Arduino, which modulates the arcs at musical frequencies corresponding to the keys pressed on the piano. Sensing the keys of the piano is achieved with a QRS optical sensor strip designed for performance capture from conventional pianos. For the peak aesthetic, the transformer outputs are connected to the metal hammers of the piano, and the arcs ground out on a metal plate in the back of the piano’s body. This lets arcs fly across the piano’s whole width as its played. Ten transformers are used to enable polyphony, so the piano to play multiple tones at once.
Building the piano was no mean feat for [Mattias], who admitted to having very limited experience with electronics before beginning the build. However, he persevered and got it working, while thankfully avoiding injury from high voltage in the process. This wasn’t easy, as Arduinos would regularly freeze from the noise produced by the arcs and the system would lose all control. However, with some smart software tweaks to the arc control and some insulating panels, [Mattias] was able to get the piano playable quite well with a beautiful chiptune tone.
It bears stating that HV work can be dangerous, and you shouldn’t try it at home without the proper understanding of how to do so safely. If you’re confident though,
we’ve featured some great projects in this space before
. Video after the break.
[Thanks to Dr Jon for the tip!] | 17 | 11 | [
{
"comment_id": "6595256",
"author": "George",
"timestamp": "2023-02-08T22:46:35",
"content": "I used to work in a High Voltage Research Lab. 1.8 Million volts and 300,000 AMps of 60 cycle power. I loved is and hated it because of the dangers. We would set up a test and the folks in production wo... | 1,760,372,403.735503 | ||
https://hackaday.com/2023/02/08/modulex-is-legos-long-lost-cousin/ | Modulex Is LEGO’s Long Lost Cousin | Navarre Bartz | [
"Toy Hacks"
] | [
"architecture",
"bricks",
"lego",
"LEGO Modulex",
"Modulex",
"plancopy",
"planning",
"planning tool",
"signage"
] | We love LEGO here at Hackaday, but did you know that LEGO spun off a parallel product line
made for architectural models
called Modulex?
[Peter Dibble] takes us on a deep dive through the history of Modulex, starting with
Godtfred Kirk Christiansen
needing a better way to model actual buildings after trying to design a house in LEGO. The LEGO brick’s 5:5:6 ratio proved challenging for modeling full-sized projects, so Modulex was conceived around a 1:1:1 ratio 5 mm cube. This change means Modulex is not compatible with LEGO System bricks.
As architectural styles morphed through the mid-20th Century, designs based around blocky shapes became passe, and Modulex pivoted to targeting factory and city planning customers. Products later branched out to include wall charts and Plancopy photocopy-able planners along with reconfigurable signage. Modulex (now ASI) still goes on as one of the biggest signage companies in the world, but discontinued the bricks in 2004. An attempt was made to revive Modulex bricks in 2015, but LEGO Group bought the company that had the rights to the bricks and has
no intention of producing Modulex
.
For more LEGO hacks, checkout this
machine learning LEGO sorter
or these
giant LEGO-like pieces
. | 24 | 10 | [
{
"comment_id": "6595149",
"author": "Jac Goudsmit",
"timestamp": "2023-02-08T20:32:17",
"content": "Another lost cousin is FischerTechnik. From Germany since the 1960s and it inspired Technic Lego in the 1980s.And of course there’s other distant relatives like Philiform, Meccano, Erectorset…===Jac"... | 1,760,372,404.488072 | ||
https://hackaday.com/2023/02/08/linux-fu-the-shell-forth-programmers-will-love/ | Linux Fu: The Shell Forth Programmers Will Love | Al Williams | [
"Hackaday Columns",
"Linux Hacks",
"Slider"
] | [
"linux",
"shell"
] | One of the most powerful features of Unix and Linux is that using traditional command line tools, everything is a stream of bytes. Granted, modern software has blurred this a bit, but at the command line, everything is text with certain loose conventions about what separates fields and records. This lets you do things like take a directory listing, sort it, remove the duplicates, and compare it to another directory listing. But what if the shell understood more data types other than streams? You might argue it would make some things better and some things worse, but you don’t have to guess, you can install
cosh
, a shell that provides tools to produce and work with structured data types.
The system is written with Rust, so you will need Rust setup to compile it. For most distributions, that’s just a package install (rust-all in Ubuntu-like distros, for example). Once you have it running, you’ll have a few new things to learn compared to other shells you’ve used.
Examples
A good way to get a quick flavor of the shell’s idiosyncracies is to contrast it with the usual shell syntax. The Github page has several good examples:
Find files matching a path, and search them for data:
sh
: find . -iname ‘*test*’ -print0 | xargs -0 grep data
cosh
: lsr; [test m] grep; [f<; [data m] grep] map
Find the total size of all files in the current directory:
sh
: ls | xargs stat -c %s | awk ‘{s+=$1} END {print s}’ –
cosh
: ls; [is-dir; not] grep; [stat; size get] map; sum
Get the second and third columns from each row of a CSV file:
sh
: cut -d, -f2,3 test-data/csv
cosh
: test-data/csv f<; [chomp; , split; (1 2) get] map
Sort files by modification time:
sh
: ls -tr
cosh
: ls; [[stat; mtime get] 2 apply; <=>] sortp
As you can see, sometimes commands are a little longer, but presumably, there is less to remember, and it is a bit more self-documenting.
But Why?
The key idea is that this shell understands multiple data types. In particular, it can deal with hash maps, sets, and lists. Basic items include booleans, integers (32-bit or of arbitrary size), floats, and strings.
The input prompt is more like a command prompt for a programming language. In fact, Forth programmers will appreciate the RPN capabilities:
/tmp/cosh$ 5 3 /
1
/tmp/cosh$ 5.0 3 /
1.6666666666666667
/tmp/cosh$
Storing into variables is similar to Forth, too, using ! and @ with the RPN-style notation. In fact, it all looks like Forth from
swap
and
drop
to the way if controls conditionals. However, the stack doesn’t exist between lines. So the above examples do not leave the result on the stack.
The
documentation
on Github is good, but there are a few things you’ll have to work out. For example, the string function ++ is documented, but the example uses the word append, which doesn’t seem to work.
/tmp/cosh$ hacka day ++
hackaday
/tmp/cosh$ hacka day append
hacka
day
append
Commands and Regular Expressions
Most shell commands exist in cosh, too, but not necessarily as external tools. Some have aliases, too. For example, you can use mv, but you can also use rename. Everything is, of course, using the RPN format for arguments.
If you want an external command, you need to prefix it with a dollar sign or, in an interactive shell, you can use a space if you prefer. For example, if you run ls, you’ll get the cosh version of ls. If you run $ls, that’s the actual ls command you expect. If you put the external name in braces, what is returned is a generator that allows you to walk through the output.
What’s a shell without regular expressions? With cosh, you have an “m” expression that tells you if you have a match or a “c” condition that returns captures from the expression. There are also “s” expressions for search and replace. You can also add flags to allow different options like case insensitivity.
I found the capture part confusing. You’d think it would provide a list of things matched in parenthesis, but either it doesn’t or I couldn’t find the right syntax to make it do so. For example:
/tmp/cosh$ name=al "name=(.*)$" c
(
0: name=al
)
/tmp/cosh$ name=al,name=jim "name=([a-zA-z]+)/g" c
(
0: name=al
1: name=jim
)
The documentation shows some examples of this that don’t work exactly right, too. For example, try this from the documentation:
/tmp/cosh$ asdf "(..)" c
To get the result the document shows, you need the /g flag on the regular expression. Otherwise, only the first match appears.
Parsing
One big feature of cosh is that it can parse json and XML. It can also write out files in that format. We’d love to see a proper CSV parser, although that’s a little easier to handle directly with cosh primitives than an XML file.
For example, if you want the 3rd and 4th fields from a CSV file, you can read it and use the split and get functions in a map:
/tmp/cosh$ test.csv f<; [chomp; , split; (3 4) get] map
Of course, that’s not going to handle things like quoted values, but that’s typically a problem in other simple shell scripts, too.
Working with json is easy. For example, if you want to find the fields that match a regular expression, you can do that:
file.json f<; from-json; keys; [.{4} m] grep;
v[gen (
0: asdf
1: qwer
2: tyui
3: zxcv
)] # from the official examples
Winner?
Will we start using cosh every day? Honestly, probably not. But it is interesting. We might keep it in our back pocket for writing scripts that need to process json or XML.
We like the Forth syntax, but not everyone will. We also like the data typing. But as a general-purpose shell, it seems to leave something to be desired.
Of course, what we really like is Linux gives you choices. If you like cosh, knock yourself out. Don’t like it? Pick another shell or — if you are feeling brave — write you own. The world is your oyster.
We couldn’t help but think of the database-like
Crush
shell while playing with cosh. Then here’s
cat9
, which is a strange shell, indeed. There are, too, some more
mainstream alternative shells
like zsh and fish. | 28 | 10 | [
{
"comment_id": "6595071",
"author": "Wojtow",
"timestamp": "2023-02-08T18:44:09",
"content": "PowerShell for Linux is probably a better bet. It understands structured data types as objects with named properties. (I.e. a directory listing has a named size field with an integer type)",
"parent_... | 1,760,372,404.127176 | ||
https://hackaday.com/2023/02/08/with-chatgpt-game-npcs-get-a-lot-more-interesting/ | With ChatGPT, Game NPCs Get A Lot More Interesting | Donald Papp | [
"Artificial Intelligence",
"Games"
] | [
"ai",
"ChatGPT",
"games",
"modding",
"mods",
"natural dialogue",
"NPC",
"openai"
] | Not only is AI-driven natural language processing a thing now, but you can even select from a number of different offerings, each optimized for different tasks. It took very little time for [Bloc] to mod a computer game to
allow the player to converse naturally with non-player characters (NPCs)
by hooking it into ChatGPT, a large language model AI optimized for conversational communication.
If you can look past the painfully-long loading times, even
buying grain (7:36)
gains a new layer of interactivity.
[Bloc] modified the game
Mount & Blade II: Bannerlord
to reject traditional dialogue trees and instead accept free-form text inputs, using ChatGPT on the back end to create more natural dialogue interactions with NPCs. This is a refinement of an earlier mod [Bloc] made and shared, so what you see in the video below is quite a bit more than a proof of concept. The NPCs communicate as though they are aware of surrounding events and conditions in the game world, are generally less forthcoming when talking to strangers, and the new system can interact with game mechanics and elements such as money, quests, and hirelings.
Starting
around 1:08 into the video
, [Bloc] talks to a peasant about some bandits harassing the community, and from there demonstrates hiring some locals and haggling over prices before heading out to deal with the bandits.
The downside is that ChatGPT is currently amazingly popular. As a result, [Bloc]’s mod is stuck using an overloaded service which means some painfully-long load times between each exchange. But if you can look past that, it’s a pretty fascinating demonstration of what’s possible by gluing two systems together with a mod and some clever coding.
Take a few minutes to check out the video, embedded below. And if you’re more of a tabletop gamer? Let us remind you that
it might be fun to try replacing your DM with ChatGPT
. | 24 | 14 | [
{
"comment_id": "6595031",
"author": "Reluctant Cannibal",
"timestamp": "2023-02-08T16:42:35",
"content": "I feel sorry for the horse. Seems like the rider was a bit rough with it pulling it’s head around like that :(",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_i... | 1,760,372,404.042182 | ||
https://hackaday.com/2023/02/08/keebin-with-kristina-the-one-with-the-breadboard-macropad/ | Keebin’ With Kristina: The One With The Breadboard Macropad | Kristina Panos | [
"Featured",
"Interest",
"Peripherals Hacks",
"Slider"
] | [
"dart marking machine",
"index typewriter",
"index typewriters",
"macropad",
"monoblock split"
] | For
their first custom, hand-wired keyboard
, [terryorchard] aka [70rch] didn’t want to mess with making a total split, and we don’t really blame them. However, as you can see, they ended up with a monoblock split, which aside from being our own personal preference, looks fantastic, and also happened to be what fit on the print bed.
What you’re looking at is a 40% remix of the Alice layout with a columnar stagger. It’s also a bit 6×3 Corne-inspired on the ergonomic front. Brain-wise, it’s got an exposed Elite Pi driving a matrix of Kailh Choc pinks and an EC11 encoder. The encoder scrolls by default, and then becomes a volume knob on the numbers and symbols layer. One super cool thing about this keyboard is the secret third layer, which is unlocked by pressing the rotary encoder. This leads to some home row mods and disables the outside columns, culminating in a test 3×5 with two layers.
Via
KBD #112
Historical Clackers: the Dart Marking Machine
Image via
Antikey Chop
While we largely think of shipping crates as being stenciled or even burned when they need identifying marks, they haven’t always been branded this way. Introducing
the Dart Marking Machine
, which is arguably not a typewriter since it doesn’t by nature ‘apply succeeding characters to paper’. Well, it’s my column, and I say it definitely clacks and in an historic manner.
The Dart Marking Machine was marketed as a moveable typewriter for the addressing of envelopes and packages with 1″ tall letters and numbers. The patent was awarded in 1890 to one Wilbur E. Goodwin since inventor Lewis Dart had died before it could be issued. The Goodwin family was quite prominent around Hartford, Connecticut, and Wilbur seems to have been known for buying up other people’s ideas and patents and giving them a push.
Wilbur Goodwin teamed up with his friend Samuel C. Hurlbut to improve the Dart and make it more nimble. They soon attempted to produce more index typewriters based on the Dart, but Goodwin died in 1905, and the dream died with him. Think of Dart, Goodwin, and Hurlbut whenever you use an old-timey embossing label maker.
The Centerfold: Breadboard Macropad
This installment’s centerfold comes courtesy of [SteBoards] via
r/mk
, and boy are these some tasty shots. If you know me at all, you know I love food in all its forms, especially (and emphatically) fake food. Although this isn’t your average centerfold material, I do hope you’ll excuse this foray into foodstuffs. All we really know about this macropad is that, aside from being delicious, it uses NovelKeys creams and looks just right with a lone yellow keycap in the middle position. But sometimes it’s nice when your centerfolds are a bit mysterious, eh?
Do you rock a sweet set of peripherals on a screamin’ desk pad?
Send a picture to Damn Fine Keyboards
along with your handle and all the gory details, and you could be featured there and here!
Or send it to me directly!
ICYMI: Wooden It Be Nice to Have Such a Macropad?
Sometimes you just
need
a macropad, and video editing is absolutely one of those times. Mostly, it’s all the dang shortcuts, though there are plenty of other programs with a ton of shortcuts.
This lovely offering from [SS4H]
is more than able to meet his needs, and features such extras as a magnetic rotary encoder and a built-in display.
I really can’t decide which one I like more. Both the 3D-printed and the wooden versions look fantastic and consumer-grade, but the wooden one is wooden. What do you think?
Got a hot tip that has like, anything to do with keyboards?
Help me out by sending in a link or two
. Don’t want all the Hackaday scribes to see it? Feel free to
email me directly
. | 6 | 5 | [
{
"comment_id": "6595138",
"author": "J. Peterson",
"timestamp": "2023-02-08T20:17:59",
"content": "Hi Kristina – you know about this? The Kickstarter just started yesterday:https://shifthappens.site/",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6597428",
... | 1,760,372,404.194613 | ||
https://hackaday.com/2023/02/08/developing-warp-drive-might-take-antifreeze/ | Developing Warp Drive Might Take Antifreeze | Al Williams | [
"Science",
"Space"
] | [
"faster than light",
"gravitational waves",
"warp bubble",
"warp drive"
] | In
Star Trek
, dilithium crystals — whatever those are — are critical to the operation of a starship’s warp drives. But a Texas professor thinks he can make a
baby step towards a warp drive using ethylene glycol
, which is commonly found in antifreeze.
While superluminal travel has been regarded as impossible for many years, recent work has suggested ways we might be able to circumvent the light-speed barrier. Unfortunately, all of these mathematical theories require energy and types of matter that we don’t know how to create yet. But [Dr. Chance Glen] believes that by shaping the energy in a specific way through a dielectric, the math can work out so that there’s no exotic negative energy required.
The experiment involves shooting RF energy into an antifreeze container and using a laser interferometer to detect gravity waves. Of course, that will involve some very sensitive measurements to account for other tiny perturbations that might give false readings. As we’ve seen in the past,
that’s a task easier said than done
.
Does this make sense? Beats us. Our physics and math are too out of date to make a good guess about how much of this is real and how much is hype. Of course, if he does detect gravity waves, that will get us as close to warp drive as the invention of the telegraph got us to cell phones. Then again, you have to start somewhere.
If you want to know more about the state of rocket engines, including
the nascent possibility of warp drives
, we’ve discussed that before. Incidentally, if you think the experiment sounds a bit like the the
Laser Interferometer Gravitational-wave Observatory (LIGO)
, you aren’t wrong. | 63 | 18 | [
{
"comment_id": "6594957",
"author": "stabbyabi",
"timestamp": "2023-02-08T12:17:26",
"content": "For the love of space animals, can we please switch to propylene glycol?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6595066",
"author": "Teslaspecte... | 1,760,372,404.305153 | ||
https://hackaday.com/2023/02/08/model-train-delivers-fresh-coffee/ | Model Train Delivers Fresh Coffee | Lewin Day | [
"home hacks",
"Toy Hacks"
] | [
"coffee",
"coffee delivery",
"model train",
"train"
] | Model trains are good fun, though few of them serve any purpose beyond amusement or authentic railway simulation. [ProjectAir] decided to put his model train to practical use
by having it deliver fresh espresso
, and faced plenty of difficult challenges along the way.
It sounds simple, but the practicalities of the task proved difficult. After all, even a slight wobble is enough to tip a coffee cup off a small train. Automating everything from the railway itself to the kitchen coffee machine was no mean feat either. Plus, the aim was to deliver coffee from a downstairs kitchen up to an upstairs office. This meant finding a way to get the train to climb a steep staircase and to carry the coffee over a 20-meter journey without losing the caffeinated beverage in the process. That required the construction of a fancy train elevator to do the job — an impressive accomplishment on its own.
The final system is a joy to watch. Having a train roll into the upstairs workshop with a fresh brew certainly beats having to go all the way downstairs for a cup. Just don’t think about the fact that
moving the coffee machine upstairs might have been a quicker solution. | 26 | 16 | [
{
"comment_id": "6594909",
"author": "Jeff",
"timestamp": "2023-02-08T09:36:14",
"content": "What fun, and definitely an achievement doing it 00. Reminds me of the old model railway that used to be at the bottom end of Interlarken West Station. That had a fabulous 0m gauge model railway, and a cafe ... | 1,760,372,404.550506 | ||
https://hackaday.com/2023/02/09/does-programming-a-robot-with-chatgpt-work-at-all/ | Does Programming A Robot With ChatGPT Work At All? | Lewin Day | [
"Artificial Intelligence",
"Robots Hacks"
] | [
"ai",
"ChatGPT",
"lawn edger",
"robot"
] | ChatGPT has been put to all manner of silly uses since it first became available online. [Engineering After Hours] decided to see if its coding skills were any chop,
and put it to work programming a circular saw
. Pun intended.
The aim was to build a line following robot armed with a circular saw to handle lawn edging tasks. The circular saw itself consists of a motor with a blade on it, and precisely no safety features. It’s mounted on the front of a small RC car with a rack and pinion to control its position. [Engineering After Hours] has some sage advice in this area: don’t try this at home.
ChatGPT was not only able to give advice on what parts to use, it was able to tell [Engineering After Hours] on how to hook everything up to an Arduino and even write the code. The AI language model even recommended a PID loop to control the position of the circular saw. Initial tests were messy, but some refinement got things impressively functional.
As a line following robot, the performance is pretty crummy. However, as a robot programmed by an AI, it does pretty okay. Obviously, it’s hard to say how much help the AI had, and how many corrections [Engineering After Hours] had to make to the code to get everything working. But the fact that this kind of project is even possible shows us
just how far AI has really come
. | 41 | 17 | [
{
"comment_id": "6596163",
"author": "Ian",
"timestamp": "2023-02-09T16:51:54",
"content": "No one seems to be talking about how these chat “AI” are just repeating what they learned.Nothing new or novel is coming out of this. It is just a lazier way to search for stuff.Granted, it is “searching” a h... | 1,760,372,404.638601 | ||
https://hackaday.com/2023/02/09/ask-hackaday-incidental-earthquake-detection/ | Ask Hackaday: Incidental Earthquake Detection | Dan Maloney | [
"Current Events",
"Featured",
"Interest",
"News",
"Slider"
] | [
"citizen science",
"clock",
"detection",
"earthquake",
"seismometer"
] | It never seems to fail: at the very moment that human society seems to reach a new pinnacle of pettiness, selfishness, violence, and self-absorption, Mother Nature comes along and reminds us all who’s really in charge. The obvious case in point here is the massive earthquakes near the border of Turkey and Syria, the appalling loss of life from which is only now becoming evident, and will certainly climb as survivors trapped since the Monday quakes start to succumb to cold and starvation.
Whatever power over nature we think we can wield pales by comparison with the energy released in this quake alone, which was
something like 32 petajoules
. How much destruction such a release causes depends on many factors, including the type of quake and its depth, plus the soil conditions at the epicenter. But whatever the local effects on the surface, quakes like these have a tendency to set the entire planet ringing like a bell, with seismic waves transmitted across the world that set the needles of professionally maintained seismometers wiggling.
For as valuable as these seismic networks are, though, there’s a looser, ad hoc network of detection instruments that are capable of picking up quakes as large as these from half a planet away. Some are specifically built to detect Earth changes, while some are instruments that only incidentally respond to the shockwaves traveling through the planet. And we want to know if this quake showed up in the data from anyone’s instruments.
Shock and Awe
My first thought on hearing the news about this quake early Monday was a flashback to
the Hunga Tonga volcanic eruption back in 2022
. I recalled being mesmerized by the satellite images captured after the initial blast that showed the pressure wave it produced traveling around the world. There was also a wealth of barometric data, captured by the vast network of public and private weather stations scattered around the globe. These clearly showed a brief but strong spike in atmospheric pressure as the shockwave passed a given location, and often showed the returning reflected impulse as the pressure wave made it all the way around the world.
But those incidental detections were relatively easy, so to speak, being as they were mainly an atmospheric phenomenon. (Yes, the volcanic eruption is obviously a seismic event, but most incidental detections of that event were atmospheric.) Hunga Tonga was also very much an impulse event — an explosion. The initial Turkey-Syria quake lasted something like seven or eight minutes, which is more drawn-out and less likely to leave behind an atmospheric signature, at least intuitively. So we expect that most of the incidental detections for this event will likely be due to picking up ground waves.
One striking example of ground waves traveling across the planet is
this Ground Motion Visualization
(GMV). The animation shows a network of North American seismometers lighting up as the ground waves from the quake pass over the continent — red means the station is moving up, blue means downward movement. It’s fascinating to watch the rapid progress of the waves across the continent, and the way the density of seismometers in California really stands out at the end.
Watch the waves from the M7.8 earthquake in Turkey roll across seismic stations in North America.
pic.twitter.com/vfbecEwsR1
— EarthScope Consortium (@EarthScope_sci)
February 6, 2023
Clocks That Shake
Another incidental detection we got word of soon after the quake was from our friend Daniel Valuch at CERN in Geneva. We recently covered
his amazing atomic pendulum clock build
that disciplines an old pendulum clock with a cesium timebase in his lab via a simple but clever chain-drive mechanism. The mechanism uses a PLL to drive a stepper motor to pay out or retract a length of chain into a tray attached to the pendulum arm, which changes the effective length of the pendulum and subtly adjusts its period. When he got into the office on Monday morning and reviewed
the PLL data
, he found that the clock was really struggling for a bit at one point. And that’s how Daniel learned that there was an earthquake 1,700 km away.
PLL data from Daniel Valuch’s pendulum clock at CERN, struggling to adjust its period during the quake. Source:
Daniel Valuch
.
Ionospheric Changes
Another fascinating Earth change resulting from this quake was the detection of ionospheric changes. We’ve covered
Alex Schwarz and his “RF Seismometer” before
, which seems to be pretty good at finding the atmospheric effects of large earthquakes via their impact on RF propagation. Alex uses custom SDR software and a special down-converter tapped into the IF stage of a shortwave receiver or ham transceiver to continually monitor wideband HF noise. When an earthquake occurs, he sees a spike in the noise floor as triboelectric effects in the quake zone couple with the ionosphere and change its refractive index.
RF-Seismograph trace from the time of the Turkey-Syria quake. Not the changes to propagation right around the time of the quake, as well as its major aftershock. Source:
Alex Schwarz
.
Your Turn
With an event this powerful, there are bound to be tons of incidental detections. Our society is massively instrumented, so this quake is likely to have shown up in somebody’s data. Perhaps you run your own personal seismograph and saw the signal. Or maybe someone actually did manage to get a barometric signal — probably someone close to Ground Zero, if anyone. What about oddball effects? We’d wonder what a CT scan or an MRI taken during the quake would look like. How about someone with a 3D printing run going — that could yield some interesting artifacts in the print.
We understand that this is all microscopically trivial stuff compared to the enormity of the loss and suffering going on now over in Turkey and Syria. Please keep that in mind as you sound off in the comments and we attempt to at least take something positive away from this tragedy.
Header Image: Seismograph data from
EarthScope Consortium | 13 | 6 | [
{
"comment_id": "6596087",
"author": "Phate191",
"timestamp": "2023-02-09T15:04:29",
"content": "Maybe will be cool to aggregate all data with gps position and precision reference in time",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6596828",
"auth... | 1,760,372,404.695128 | ||
https://hackaday.com/2023/02/09/five-years-on-where-is-starman-and-where-will-he-go/ | Five Years On, Where Is Starman And Where Will He Go? | Maya Posch | [
"Space"
] | [
"space debris",
"starman"
] | On 6 February 2018, a Tesla Roadster was launched as the mass simulator on the first ever Falcon Heavy launch — putting for the first time ever a car on a Mars-crossing orbit. While undoubtedly a bit of a stunt, the onboard cameras provided an amazing view of our planet Earth as the Starman dummy in the Roadster slowly drifted away from that blue marble, presumably never to be seen again.
This “never” is the point that researchers at the University of Toronto would like to clarify in a
paper published after the launch
titled
The Random Walk of Cars and Their Collision Probabilities with Planets
. Using N-body simulations, they come to the conclusion that there’s a 22%, 12%, and 12% chance of the Roadster impacting the Earth, Venus, and the Sun, respectively. But don’t get too excited, it’s not due to happen for a few million years, so it isn’t something any of us will be around to see.
As the
Where Is Starman?
website shows, the Roadster never reached escape velocity from the Sun’s gravity, meaning that it’s still zipping around in an orbit around our day star. Exposed to the harsh UV and other radiation, it’s likely that very little is left at this point of the Tesla, or Starman himself. Even so,
scientists to this day
are feeling less than amused by what they see as essentially littering, adding to the discarded rocket stages, dead satellites and other debris that occasionally makes it into the news when it smashes into the Moon, or threatens the ISS. | 55 | 15 | [
{
"comment_id": "6595950",
"author": "jwn",
"timestamp": "2023-02-09T12:12:18",
"content": "“If very little” will remain of the Tesla, what is the big deal? “Space” is called “Space” because it is mostly empty!Did the Aries flight to the moon left no debris on earth, the moon, in space, earth orbi... | 1,760,372,404.789851 | ||
https://hackaday.com/2023/02/09/utility-mat-turns-waste-epoxy-into-useful-tools/ | Utility Mat Turns Waste Epoxy Into Useful Tools | Lewin Day | [
"Tool Hacks"
] | [
"epoxy",
"recycling"
] | Epoxy is a great and useful material typically prepared by mixing two components together. But often we find ourselves mixing too much epoxy for the job at hand, and we end up with some waste left behind.
[Keith Decent’s] utility mat aims to make good use of what is otherwise waste material.
The concept is simple yet ingenious. It’s a flexible mat that serves as a mold for all kinds of simple little plastic workshop tools. The idea is that when you have some epoxy left over from pouring a finish on a table or laying up some composites, you can then pour the excess into various sections of the utility mat. The epoxy can then be left to harden, producing all manner of useful little tools.
It may seem silly, but it could save your workshop plenty of nickels and dimes. Why keep buying box after box of stir sticks when you can simply make a few with zero effort from the epoxy left from your last job? The utility mat also makes other useful nicknacks like glue spreaders, scrapers, wedges, and painter’s pyramids.
We’ve seen other great recycling hacks over the years too.
Video after the break. | 46 | 17 | [
{
"comment_id": "6595811",
"author": "ono",
"timestamp": "2023-02-09T09:08:39",
"content": "I was hoping it was a trick to recycle polymerized epoxy…",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6598594",
"author": "Fireking",
"timestamp": ... | 1,760,372,404.97467 | ||
https://hackaday.com/2023/02/08/the-arpanet-of-things-and-cmus-history-of-networked-soda-machines/ | The ARPANET Of Things And CMU’s History Of Networked Soda Machines | Maya Posch | [
"internet hacks"
] | [
"IoT"
] | When the computer science department of Carnegie Mellon University expanded in the 1970s, this created a massive issue for certain individuals who now found that they had to walk quite a distance to the one single Coke machine. To their dismay, they’d now find that after braving a few flights of stairs, they’d find that the Coke machine (refilled randomly by grad students) was empty, or worse, had still warm Coke bottles inside. What happened next is
detailed by the Coke machine itself
, straight from the CMU’s servers.
A
follow-up by the IBM Industrious blog
adds more feedback from those responsible for we now refer to as an IoT device, though technically it was an AoT at the time, being a pre-Internet era. For the bottle-based, 1970s machine, microswitches were installed by students in the machine to keep track of the fill state of each column and for how long the bottles had been inside. After about 3 hours newly added bottles were registered as being ‘COLD’, which could be queried from the PDP-10’s mainframe (CMUA) or via
ARPANET
using the finger command on the special ‘coke’ user account with
finger coke@cmua
.
As time moved on and the coke machine was replaced in the early 90s with a newer (and very much non-IoT) model, students would once again attempt to modify it, much to the chagrin of the Coke company’s maintenance people, resulting in the students reverting modifications prior to a maintenance appointment. This tracking system used the empty column lights on the machine, leading to a similar tracking system as on the 1970s machine, except now running on a PC-XT class computer that also tracked the status of the M&M snack machine nearby.
Whether CMU CS students can still query such highly relevant information today is not mentioned, but we presume it is an issue of paramount importance that has been addressed in an expedient fashion over the intervening years.
(Thanks to [Daniel T Erickson] for the tip) | 10 | 6 | [
{
"comment_id": "6595691",
"author": "Deon van Schalkwyk",
"timestamp": "2023-02-09T06:39:15",
"content": "Afaik the first (one of the first?) potentially apocryphal uses of a webcam was also a university based system that showed the level of the brewed pot of filter coffee, for similar reasons.",
... | 1,760,372,405.019481 | ||
https://hackaday.com/2023/02/08/understanding-ai-chat-bots-with-stanford-online/ | Understanding AI Chat Bots With Stanford Online | Al Williams | [
"Artificial Intelligence"
] | [
"chatbot",
"GPT-3",
"stanford"
] | The news is full of speculation about chatbots like GPT-3, and even if you don’t care, you are probably the kind of person that people will ask about it. The problem is, the popular press has no idea what’s going on with these things. They aren’t sentient or alive,
despite some claims to the contrary
. So where do you go to learn what’s really going on? How about Stanford? Professor [Christopher Potts] knows a lot about how these things work and he shares some of it in a recent video you can watch below.
One of the interesting things is that he shows some questions that one chatbot will answer reasonably and another one will not. As a demo or a gimmick, that’s not a problem. But if you are using it as, say, your search engine, getting the wrong answer won’t amuse you. Sure, you can do a conventional search and find wrong things, but it will be embedded in a lot of context that might help you decide it is wrong and, hopefully, some other things that are not wrong. You have to decide.
If you’ve ever used a product like Grammarly or even a simple spell checker, it is much the same. It tells you corrections, but you must ensure they aren’t incorrect. It doesn’t happen often, but it is possible to get a wrong suggestion.
On the technical side, the internal structure of all of these programs uses something called “the transformer” that looks at input words and their positions. The idea came
mostly out of Google in a 2017
paper and has — no pun intended — transformed language processing resulting in the things like GPT-3 that we are seeing today.
According to [Potts], the seemingly complex algorithm is a composition of simple parts, but no one really understands why it works as well as it does. There’s more in the hour-long lecture, but it is an hour well-spent if you are interested in this trending technology.
Of course, like all high technology, you don’t necessarily have to completely understand it
to use it
. Getting things wrong is one problem. Copying things
you shouldn’t is another
. We can’t predict where all this is going, but it is definitely going somewhere. Until then, it might be true that we don’t completely understand chat bots. But it is also true that they don’t completely understand us.
https://www.youtube.com/watch?v=-lnHHWRCDGk | 8 | 5 | [
{
"comment_id": "6595475",
"author": "Dan (No, the OTHER one)",
"timestamp": "2023-02-09T03:24:47",
"content": "Surprisingly, Grammarly is often incorrect to the point that it irks me. It does do a decent job of fixing *ahem* grammatical errors, but it introduces more errors than it fixes.",
"pa... | 1,760,372,405.075943 | ||
https://hackaday.com/2023/02/08/simple-wood-fired-water-heater-is-surprisingly-effective/ | Simple Wood-Fired Water Heater Is Surprisingly Effective | Lewin Day | [
"home hacks"
] | [
"water heater",
"wood fired stove",
"wood stove"
] | These days, humans have gotten all fancy-schmancy with their gas and electric water heaters. Heck, some are even using heat pumps to do the work as efficiently as possible. [HowToLou] got back to basics instead,
with his simple wood-fired water heater design.
The design is straightforward, featuring 100ft of quarter-inch copper tubing wrapped directly around a steel barrel. Room-temperature water is fed into the tubing via a garden hose, and comes out much hotter, thanks to a fire burning away
in the barrel stove of [Lou’s] own construction
.
For an input water temperature of 41 F, the output reaches 105 F at a flow rate of 0.67 gallons per minute. By [Lou]’s calculations, that’s a heat transfer to the water of roughly 21,000 BTU per hour. [Lou] achieved this with just $55 worth of copper tubing, and he notes that simply doubling up the tubing would increase the heat transfer to the water even further.
If you’re looking for a hot shower from your outdoor wood stove, a build like this might be just the ticket. With the stove burning hot and your hose as a water supply, you could experience the joy of the hot water while you’re standing in the snow outside.
We’ve seen [Lou]’s work before, too
. Video after the break. | 55 | 18 | [
{
"comment_id": "6595394",
"author": "Col. Panek",
"timestamp": "2023-02-09T01:59:53",
"content": "I tried that with a couple wraps of 1/2 inch tubing around a steel drum full of solar heated water, and it only lasted ten years until it rotted pinholes in the copper. It was OK while it lasted, becau... | 1,760,372,405.550154 | ||
https://hackaday.com/2023/02/07/count-leading-zeros-for-efficient-logarithms/ | Count Leading Zeros For Efficient Logarithms | Chris Lott | [
"digital audio hacks",
"Software Development"
] | [
"algorithms",
"count leading zeros",
"dsp",
"logarithms"
] | [Ihsan Kehribar] points out a clever trick you can use to
quickly and efficiently compute the logarithm of a 32-bit integer
. The technique relies on the CLZ instruction which counts the number of leading zeros in a machine word and is available in many modern processors. Typical algorithms used to compute logarithms are not quick and have a variable execution time depending on the input value. The technique [Ihsan] is using is both fast and has a constant run time.
The above equation summarized the math behind the algorithm. We get the first term easily using the CLZ instruction. Using the remainder and a pre-computed lookup table, it is possible to get the second term to various degrees of accuracy, depending on how big you make the table and whether or not you take the performance hit of interpolation or not — those of a certain age will no likely groan at the memory of doing interpolation by hand from logarithm tables in high school math class. [Ihsan] has posted an MIT-licensed implementation of this technique in his GitHub repository, which includes both the C-language algorithm and Python tools to generate the lookup table and evaluate the errors.
Why would you do this? Our first thought was real-time streaming DSP operations, where you want fast and deterministic calculations, and [Ihsan]’s specifically calls out embedded audio processing as one class of such applications. And he should know, after all, since he developed a MIDI capable polyphonic FM synthesizer on a Cortex M0 that
we covered way back in 2015
. | 14 | 8 | [
{
"comment_id": "6594446",
"author": "alialiali",
"timestamp": "2023-02-07T16:50:36",
"content": "CLZ is very interesting. I can think of a few algorithms where your result is a 1-hot word with position of the bit being what you’re interested in.I doubt if many compilers emit a CLZ for the various w... | 1,760,372,405.135002 | ||
https://hackaday.com/2023/02/07/all-about-usb-c-manufacturer-sins/ | All About USB-C: Manufacturer Sins | Arya Voronova | [
"Engineering",
"Featured",
"Interest",
"Rants",
"Slider"
] | [
"Type-C",
"USB C",
"USB Type-C",
"USB-C PD"
] | People experience a variety of problems with USB-C. I’ve asked people online about their negative experiences with USB-C, and got a wide variety of responses, both
on Twitter
and
on Mastodon.
In addition to that, communities like
r/UsbCHardware
keep a lore of things that make some people’s experience with USB-C subpar.
In engineering and hacking, there’s unspoken things we used to quietly consider as unviable. Having bidirectional power and high-speed data on a single port with thousands of peripherals, using nothing but a single data pin – if you’ve ever looked at a schematic for a proprietary docking connector attempting such a feat, you know that you’d find horrors beyond comprehension. For instance, MicroUSB’s ID pin quickly grew into a trove of incompatible resistor values for anything beyond “power or be powered”. Laptop makers had to routinely resort to resistor and one-wire schemes to make sure their chargers aren’t overloaded by a laptop assuming more juice than the charger can give, which introduced a ton of failure modes on its own.
When USB-C was being designed, the group looked through chargers, OTG adapters, display outputs, docking stations, docking stations with charging functions, and display outputs, and united them into a specification that can account for basically everything – over a single cable. What could go wrong?
Of course, device manufacturers found a number of ways to take everything that USB-C provides, and wipe the floor with it. Some of the USB-C sins are noticeable trends. Most of them, I’ve found, are manufacturers’ faults, whether by inattention or by malice; things like cable labelling are squarely in the USB-C standard domain, and there’s plenty of random wear and tear failures.
I don’t know if the USB-C standard could’ve been simpler. I can tell for sure that plenty of mistakes are due to device and cable manufacturers not paying attention. Let’s go through the notorious sins of USB-C, and see what we can learn.
Omitting The Resistors, One Cent At A Time
No USB-C resistors in sight, and the pins aren’t even soldered
Yep, you got it. The first, honorary entry is omitting 5.1 kΩ pulldowns on a USB-C port intended for charging your device. “Why does my device charge with a USB-A to USB-C cable, but doesn’t charge with a USB-C to USB-C cable”, asks the user? The answer is simple – because your device’s designer decided to save one cent while building your device, and didn’t care about testing the device before selling it to you. In other words, your device is supposed to have two resistors connected to the USB-C plug, yet it does not, and USB-C power supplies are unable to detect that they ought to provide power. Remember, the resistor detection is fundamentally a safety mechanism, and by now, information about this problem is omnipresent.
Omitting these resistors is one of the most infuriating Type-C mistakes for users, and often results in people debugging the problem for hours on end. Here’s just an example of a developer who was working with a WCH RISC-V board using a USB-C connector for power, and spent a good few hours due to WCH not bothering to add these resistors. If you buy an USB-C-equipped Arduino Pro Micro or TP4056 board on Aliexpress, it is likely to be resistor-less. Everywhere you look, you’ll find a resistor-less device or two.
The sheer volume of this problem
is, honestly, ridiculous.
Murderous “USB-C” PSUs At Your Local Lidl
Remember
the power article
, specifically, how you get to higher voltages? Let’s recap: you get 5 V first, and then only after resistor detection. Higher voltages require negotiations over a digital protocol. This is a safety rule – it’s how you can use the same USB-C charger for your laptop, your phone, your wireless headphones, your devboards and whatever else.
Picture
by Stephanie Lahs
Now, what happens when someone builds a power supply with a fixed higher-than-5 V output, say, 12 V, and puts a USB-C plug on it? The answer is – seriously bad things happen. Such a power supply isn’t safe to be used on actual USB-C devices – it’s likely to destroy your phone or laptop, and it’s at a glance indistinguishable from an adapter that follows the USB-C rules laid out for everyone else. If you must use such an adapter for something every now and then, you ought to mark its cable with red tape in a way that covers the connector plug, so that you (or your loved one) don’t grab it to charge something else. Seriously, it’s easy to make a mistake, and the more you get comfortable with USB-C, the more likely you are to make it.
Who does this? Well, many no-name manufacturers do, but also
Lidl Parkside tools,
for one. CrowPi
does this too,
in their recently released CrowPi L laptop. Both of these come with dumb “USB-C” 12 V power supplies, and neither of them should be sold to consumers, especially given that the CrowPi laptop is designed for kids and educational purposes, and Parkside tools are designed for non-tech-savvy people. When your kid burns a $500 smartphone or your granddad burns his laptop due to a $2 power supply, that’s when the gravity of this standard violation really sets in.
Blaming Companies? It’s Not That Simple
The resistor omission is by now a thorn in consumers’ sides, and the murderous PSU designs are unforgivable. Designers should not do these things. There is, however, an area where I can forgive mistakes happening, and that’s the USB-PD protocol – specifically, the compatibility mistakes, especially in early USB-C tech.
The PD specification is 800 pages – this is, no doubt, intimidating. If you’re getting paid to implement USB-C, however, it’s your job to be familiar with it. On the other hand, when you’re an early adopter implementing a complex specification, it’s quite likely you’re going to screw it up through no fault of your own. You don’t have as many implementations to work with, you’re going to work with (and around) similarly early adopter low-level hardware like ICs, and other devices around you are going to be similarly crooked in subtle ways. The gist is – early adoption of is more of a tricky engineering problem than we might recognize.
In addition to that, there’s two early adopter routes for a wide-reaching interfacing technology like this. One route is – you build a device that is engineered to be specifically compatible with the pricey peripherals that you manufacture, despite being based an open standard being aimed at intercompatibility, and don’t really test the device with other things. I call this the Nintendo Switch route,
for no particular reason.
The other early adopter route is – you design a device, then test it with other devices. It’s the early adoption stage, so other devices are often similarly broken, and you end up adding a slew of workarounds and bugfixes piled up on top of each other. New devices keep getting released, and for a while each of them brings a slightly more broken implementation. At best, you spend plenty of time testing when hardly anyone else around does, ensuring tip-top compatibility – provided you can throw developers at the problem. At worst, your fixes create a whole new kind of buggy device.
With this “blaming companies” disclaimer in mind, let’s move to the next point, where I will spend time blaming companies.
Not Testing PD Implementations Enough
Nowadays, there’s no excuse to release a poorly tested USB-C product. If an open-source project can have an array of power supplies to test a USB-C PSU with, large companies have no excuse. If you bought a hefty powerbank that doesn’t put enough effort into figuring out power roles and ends up getting charged from the laptop when you need the opposite, that means it’s not been tested on laptops like yours, and chances are, yours isn’t special. Let’s face it – a company developing powerbanks can afford to buy a few laptops with different OSes and test the behaviour until it works well.
The PD compatibility problems are out there, and you might stumble upon them eventually, especially when it comes to charging. There’s laptops that don’t work with specific chargers, for instance – my Framework laptop doesn’t work with a Xiaomi laptop 65 W charger, in a way where the battery keeps cycling from 10% to 30%, and the charger keeps doing connect/disconnect cycles. I also have a dock where charger passthrough works only for half of laptops. Of course, there’s ways to mis-manage specifications, but let’s face it – there’s gotta be a more fundamental cause for this.
Part of the problem is lack of information sharing. When a large open-source project solves a tricky compatibility problem and adds a workaround, it goes onto GitHub for everyone to see and make use of, with a searchable description of the problem in the commit message.
When a commercial entity fixes the same bug, it is thrown into
/dev/null
for all other informational intents and purposes, except for the binary blob they push as a firmware update – if even. In this case, each company implementing PD-talking stuff, has their own database of PD quirks, working around peculiarities of devices they tested with. Those PD quirks ought to be openly available information, but they’re not.
Proprietary solution developers aren’t paid to share things, whereas in open-source project, the sharing happens naturally, through no extra effort, once again exposing the fundamental inferiority of proprietary processes. Large part of the reason you have buggy USB-C devices, is that companies would rather make you overpay and suffer incompatibilities, than put effort into sharing information between themselves. Whether it’s security vulnerability information or designing standards together, large corporations are slowly learning to do things the right way, domain by domain, but the general concept never really seems to stick – the fundamental blinders of profit motives and greed are just that strong.
Microcontrollers with PD peripherals are often tough to work with, too. Again, this is a lack of effort put into making those peripherals friendly for developers, whether through better design or better documentation – often, more open code, as you might be able to guess, sadly. This factor alone makes it more likely that the end-user will encounter mistakes, purely because a peripheral that is harder to work with will be harder to write reasonable code for.
Don’t Add, Don’t Tell
You can buy a $1000 laptop, and find out that its USB-C port only does USB3 – no charging or DisplayPort. Or, you can buy a mid-tier $500 smartphone, and find out that it can’t charge and do OTG at the same time, despite USB-C making it so that devices can easily do precisely that in a standardized manner, killing off all those MicroUSB splitter adapters with weird resistors on the ID pin.
By Ilya Plekhanov,
CC A-SA 4.0
In laptop space, Asus is one of the worst offenders, having had a long streak of devices with only USB3 output on USB-C – no DisplayPort, no charging, not to even mention Thunderbolt. What’s worse – when looking at documentation, you might not find any mention of what the USB-C port is capable of, no matter if it’s capable of something or not. And of course, lack of clear labeling of ports makes it worse.
The cherry on top is a single USB-C port on a laptop – and nothing else — you might have seen Macbooks like this. You’re basically required to carry a dongle with PD passthrough around, there’s nowhere to plug your wireless mouse receiver in, and the USB-C port becomes the living definition of the word “bottleneck”. When it comes to right to repair, having a single USB-C port for absolutely everything means adding a giant failure point that will leave you laptop-less if you accidentally use too cheap of a charger and end up melting the only port’s plastic. If it’s not a Macbook, good luck finding a replacement port; custom-made small-batch USB-C ports can be quite literally impossible to find for a hobbyist.
Still, Workarounds Exist
Remember: if your USB-C cable is broken or wonky, you should stop using it and buy a replacement. Mark devices that misbehave, and talk online about them; name and shame liberally. Read online reviews if compatibility is what you worry about, scroll down on Aliexpress, or search the product name to see if the device you’re buying has the resistors it needs. When buying a USB-C power supply or an expensiveish dock, it can be good to test it with your device and make sure you can return it or exchange it for a different one. With time, the sharp edges will smooth out, and whenever it is that USB-D visits our households, you will find a lot of people feeling nostalgic about just how simple USB-C was. | 85 | 25 | [
{
"comment_id": "6594388",
"author": "BobH",
"timestamp": "2023-02-07T15:29:12",
"content": "In the early days of the PD spec, it was very much a moving target. I was working at a semiconductor company developing USB-PD chips, and there would be monthly changes that necessitated ripping up large amo... | 1,760,372,405.458801 | ||
https://hackaday.com/2023/02/07/micropython-esp32-ide-makes-life-simpler/ | MicroPython ESP32 IDE Makes Life Simpler | Al Williams | [
"Microcontrollers",
"Software Development"
] | [
"ESP32",
"micropython"
] | In theory, using MicroPython on the ESP32 is easy — just flash an image and connect using a serial port. But that leaves a lot of things you still have to do. You need to move files between the two platforms. You’ll want to manage network configurations. You might want better editing and assistance, too. So there are a number of IDEs made to help you and one we recently noticed was
MPY-Jama
.
The IDE provides source code editing, of course. But it also allows you to do things like pull information about the network using a dashboard or connect to a WiFi network easily. You can even create your own AP with a simple interface.
Although the front part of the README mentions it is for Windows or Mac, if you scroll down you’ll find instructions for installing under Linux. The IDE is extensible using “Jama Funcs” and can handle the flashing operation from inside the IDE.
Of course, there is an
IDE from Arduino
(but not the Arduino IDE) that handles MicroPython. You can also find a rundown of several
similar alternatives online
. If you need some inspiration for a MicroPython project, perhaps
you’d like to play a game
? | 49 | 14 | [
{
"comment_id": "6594304",
"author": "Murray",
"timestamp": "2023-02-07T12:58:13",
"content": "I’m sorry but Python is just wrong.We have Circuit diagrams and layouts. They are related, but circuit diagrams prioritize, readability, understanding. While layout is about structure.So too we have prese... | 1,760,372,405.958569 | ||
https://hackaday.com/2023/02/07/og-doom-shows-off-the-origins-of-multi-monitor/ | OGDOOMShows Off The Origins Of Multi-Monitor | Jonathan Bennett | [
"classic hacks",
"Games"
] | [
"doom",
"multi monitor",
"retro gaming"
] | We have a thing for
DOOM
, and we admit it. The source was released, and clever hackers have ported the engine to every system imaginable. It’s a right of passage, when hacking a machine, to run
DOOM
on it — be it a VoIP phone, or tractor. But the original 1993 release does have a few notable tricks, and there’s something to be said for recreating that experience on period hardware. And that’s what we’re covering today: [Tech Tangents] discovered
DOOM’s
multi-monitor support, and
built a 4-computer cluster to show it off
.
There is a catch, of course.
DOOM
1.1 has the multi-monitor support, and under-the-hood, it works by running a copy of the game on individual computers, and controlling the drones over the network. As the game’s network code was updated for version 1.2, the multi-monitor feature was axed to make the network code easier to maintain. So, find a 1.1 shareware release, install it on a DOS machine with IPX drivers, and start each iteration with a
-net
flag. Use
-left
and
-right
to set the drones to the appropriate view. And that view is ninety degrees left and right.
Maybe not ideal, but at the time it was one of the first games to have any sort of multi-monitor support at all. Likely
inspired by a commercial flight simulator setup
. Either way, it’s a neat feature, and kudos to [Tech Tangents] for showing off this obscure feature of a beloved classic! | 13 | 8 | [
{
"comment_id": "6594191",
"author": "ono",
"timestamp": "2023-02-07T09:52:07",
"content": "“Doom for monkeys” or the unfortunate spread of social networks into the physical privacy of every person. Sometimes I miss the print era, where text serves as a medium for suggestion, and images are parsimon... | 1,760,372,405.234319 | ||
https://hackaday.com/2023/02/06/spy-drone-propeller-makes-for-a-quite-pc/ | Spy Drone Propeller Makes For A Quiet PC | Al Williams | [
"3d Printer hacks"
] | [
"fan",
"PC cooling"
] | MIT recently announced its research on toroidal propellers to create quieter drones. That got [Major Hardware] thinking about noisy PC fans. The obvious solution was to
adapt the toroidal shape for a PC fan
. He was familiar with the idea from similar screws on boats that are commercially available. You can see his tests in the video below.
The shape of the blades on the MIT drones is visible in video and pictures, but there were no available 3D models. [Major] did a design and 3D printed the blades. Watching the comparison with a conventional fan using smoke was pretty impressive.
The fan appeared to work pretty well, but the stock fan worked better. Oddly, the stock fan was also a little quieter overall, but the MIT-inspired blade was quieter at high frequencies. Static pressures were a good bit less for the new design.
Of course, this was a first attempt so there could be improvements that would help. And, as [Major] points out, flying a drone is a different job than cooling a PC, so these tests don’t really negate the idea that the design may lead to quieter drones.
We looked at the
MIT drones
earlier. If you don’t want to spin a blade, maybe you could move PC cooling air
with a flapping wing
. | 45 | 17 | [
{
"comment_id": "6594069",
"author": "CityZen",
"timestamp": "2023-02-07T06:12:55",
"content": "I think the design space is quite different when you’ve got a housing surrounding the fan blade vs. when you don’t. It’s not likely that a blade optimized for one situation works well in the other.",
... | 1,760,372,405.320307 | ||
https://hackaday.com/2023/02/06/researchers-find-inert-components-in-batteries-lead-to-cell-self-discharge/ | Researchers Find “Inert” Components In Batteries Lead To Cell Self-Discharge | Donald Papp | [
"Battery Hacks",
"chemistry hacks",
"News"
] | [
"battery",
"Chemistry",
"Li-ion",
"lithium",
"pet",
"self-discharge"
] | When it comes to portable power, lithium-ion batteries are where it’s at. Unsurprisingly, there’s a lot of work being done to better understand how to maximize battery life and usable capacity.
Red electrolytic solution, which should normally be clear.
While engaged in such work, [Dr. Michael Metzger] and his colleagues at Dalhousie University opened up a number of lithium-ion cells that had been subjected to a variety of temperatures and found something surprising: the electrolytic solution within was a bright red when it was expected to be clear.
It turns out that PET — commonly used as an inert polymer in cell assembly —
releases a molecule that leads to self-discharge of the cells
when it breaks down, and this molecule was responsible for the color change. The molecule is called a redox shuttle, because it travels back and forth between the cathode and the anode. This is how an electrochemical cell works, but the problem is this happens all the time, even when the battery isn’t connected to anything, causing self-discharge.
As [Dr. Metzger] points out, this came as a surprise in part because no one was paying much attention to “inert” components like PET. PET is present in the plastic foils and tapes that make up a battery’s internals, and while it is indeed inert at the time of cell manufacture, it can degrade within the battery and release the redox shuttle molecule. Elevated temperatures worsen this condition.
There are two papers (
Identification of Redox Shuttle in Cells
, and
Self-discharge Originating from Redox Shuttle Generation
) on the subject, and if you’d like to learn a bit more about lithium-ion batteries in general, our own Arya Voronova
has you covered
. | 11 | 5 | [
{
"comment_id": "6593993",
"author": "Gravis",
"timestamp": "2023-02-07T03:22:56",
"content": "More specifically, they were looking at LiFePO4 batteries. This is an important discovery but it becomes less relevant as we get closer to using solid state batteries which have no liquid electrolyte.",
... | 1,760,372,406.425111 | ||
https://hackaday.com/2023/02/06/custom-enclosure-for-3d-printer/ | Custom Enclosure For 3D Printer | Maya Posch | [
"3d Printer hacks"
] | [
"3d printer enclosure",
"perspex",
"wood"
] | Having an enclosure around an FDM 3D printer is generally a good idea, even when printing only with PLA, as it keeps the noise in, and the heat (and smell, with ABS) inside. With all the available options for enclosures out there, however, [David McDaid] figured that it should be possible to
make an enclosure
that does not look like a grow tent and is not overly expensive. He also shared the
design files
on GitHub.
The essential idea is very simple and straightforward: the structural part is cut out of pine beams that are cut to size and joined into a cube by (3D-printed) corner brackets, with acrylic (Perspex) sheets filling in the space between the wooden beams. A door is formed using (also 3D-printed) hinges and door handles. The whole enclosure is rounded off with a lick of paint on the wooden elements, and a diffused set of LED lights for internal illumination.
It definitely has to be admitted that it makes for a very stylish enclosure, with a lot of modding potential. It can also easily be adapted to differently sized printers and filament material demands. | 19 | 10 | [
{
"comment_id": "6594141",
"author": "70sjukebox",
"timestamp": "2023-02-07T07:51:19",
"content": "On my ‘to do’ list now",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6594179",
"author": "Secaderolate",
"timestamp": "2023-02-07T09:34:43",
"conten... | 1,760,372,405.607976 | ||
https://hackaday.com/2023/02/05/sundial-collection-is-2d-printed/ | Sundial Collection Is 2D Printed | Al Williams | [
"clock hacks"
] | [
"2d print",
"folding",
"kids",
"orgami",
"paper",
"sundial"
] | We see a lot of clocks, and many of the better ones have some 3D printed elements to them. But [Carl Sabanski] shows us his
kits for making sundials
for either hemisphere using a conventional printer (you know, one that puts ink on paper), some styrofoam, and possibly some other materials like wire coat hangers, threaded rods, thumbtacks, glue, and different papers like transparencies or card stock.
In all, there are 21 different kinds of sundials. Some are pretty standard-looking fare, but there are others, like the pinwheel equatorial sundial or the cycloid polar sundial, which might be surprising. One even uses a CD as a kind of indicator.
These are great alternatives to paper airplanes and would probably form the basis of a pretty nice science project for a kid. Some of them are simple, and others, like the globe kit, might take a bit of work. All of them would be very amenable to modifications since the materials are readily available and inexpensive. We couldn’t help but think that some of the sundials could use a few 3D-printed helper pieces, but if you are handy with a CAD program, you can probably work that out yourself.
If you are interested in sundials, [Carl] has a
website with more information
. He is clearly very excited about sundials. We’ve seen some
unusual ones
before. We’ve even seen some that
position themselves
. | 3 | 3 | [
{
"comment_id": "6592617",
"author": "Jan",
"timestamp": "2023-02-05T11:40:30",
"content": "“These are great alternatives to paper airplanes” really made me smile. In my silly mind I can see people throwing paper sundials out of the window and through the classroom. Which is always better then throw... | 1,760,372,405.645828 | ||
https://hackaday.com/2023/02/04/3-ways-to-diy-custom-cnc-dust-covers/ | 3 Ways To DIY Custom CNC Dust Covers | Donald Papp | [
"cnc hacks",
"how-to"
] | [
"bellows",
"dust cover",
"dust shield"
] | Home shop machinists know dust shields are important for keeping swarf out of expensive linear rails and ball screws. [Petteri Aimonen]
demonstrates three inexpensive ways to DIY some bellows-style dust covers
. Such things can of course be purchased, but they’re priced at a premium and not always available in the size one needs.
A bellows-style dust cover ideally maximizes extension length while minimizing side wall distortion. It should hold its shape without external support.
The first method is to fold a suitable flat plastic or paper sheet into a bellows pattern. This method is all about the fold pattern, and thankfully, there’s no need to reinvent the wheel. [Petteri] used a fellow enthusiast’s
bellows folding pattern generator
which is, believe it or not, itself inspired by a remarkably comprehensive
US Patent Number 6,054,194
.
The downside to this method is the thickness of the bellows when it is fully collapsed. The corners always contain the most material, because it is there that the material is folded upon itself, and this limits how close to the end of travel the CNC carriage can move with the bellows attached.
The second method is to cut a large number of C-shaped sections from fabric and sew them together to make bellows. This method collapses down well and holds its shape well, but the cutting and sewing it requires can be a barrier.
The final method — and the one [Petteri] found most useful — was to hack some IKEA window blinds. IKEA
Schottis
pleated blinds are inexpensive, with a slick finish on one side and polyester fabric. The polyester is perfect for gluing. By cutting the material at a 45-degree angle into three sections and gluing them into a U-shape, one can create a serviceable bellows-style cover for a minimum of work.
Any of the explored methods can do the job, but [Petteri] has formulas to determine the maximum extensions and folded thicknesses of each method just in case one would like to see for themselves before choosing. And if a bellows-style cover isn’t your cup of tea, check out
this method for turning a plastic strip into a spring-like tube that does the same job
. | 7 | 4 | [
{
"comment_id": "6592530",
"author": "macsimski",
"timestamp": "2023-02-05T08:58:10",
"content": "Here in the netherlands you can buy rolls of a polyethylene and cardboard mixture also used for milk cartons at the hardware shop. Sold as covering for floors during plastering and painting. It is very ... | 1,760,372,405.698393 | ||
https://hackaday.com/2023/02/04/reliving-a-bitmapped-past-with-a-veritable-hoard-of-bitmap-fonts/ | Reliving A Bitmapped Past With A Veritable Hoard Of Bitmap Fonts | Maya Posch | [
"Retrocomputing"
] | [
"8-bit fonts",
"bitmap",
"bitmap fonts",
"lcd",
"retro fonts"
] | The fonts seen with old computer systems such as those from Apple and Commodore, as well as Microsoft Windows 3.1 and older, form an integral part of our interaction with these systems. These days such bitmap fonts are a rarity, with scalable vector-based fonts having taken their place on modern-day systems. This unfortunately also means that these fonts are at major risk of being lost to the sands of time. This is where [Rob Hagemans] seeks to
maintain an archive
of such bitmap fonts, ranging from Acorn to MSX to Windows.
Many of these fonts are extracted from character ROMs, with a preview of some of these fonts available via the
Monobit viewer
. The fonts themselves are made available in
YAFF format
, which is a text-based format that can be converted back to a binary format using the
Monobit
tool. If you ever wanted to use one of these old bitmap fonts in a project, this would seem to offer a treasure trove of options. The hoard of bitmap fonts might be the perfect fit for your next graphic LCD project.
(Via [SuperIlu] on
Mastodon
) | 12 | 5 | [
{
"comment_id": "6592567",
"author": "Daid",
"timestamp": "2023-02-05T10:02:47",
"content": "There you go.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6592568",
"author": "Daid",
"timestamp": "2023-02-05T10:03:14",
"content": "https://int10h.org... | 1,760,372,405.847629 | ||
https://hackaday.com/2023/02/04/mcm-70-replica-embodies-proud-canadian-heritage/ | MCM/70 Replica Embodies Proud Canadian Heritage | Chris Wilkinson | [
"Retrocomputing"
] | [
"MCM/70",
"retrocomputing",
"vintage computer"
] | When a vintage computer is all but unobtanium, software emulation is often all that remains. Unless you are [Michael Gardi], who saw an opportunity to
reproduce Canada’s home-grown MCM/70 microcomputer
using a combination of software emulation and modern hardware.
Short of building a brand new MCM/70 from the original schematics, this faithful facsimile of the MCM/70 does everything it can to pay homage to the original machine. The foundations of this project can be attributed to the York University Computer Museum (YUCoM)
MCM/70E emulator
, highly regarded for its “historical accuracy”. The MCM/70 used dual cassette tapes for storage and a funky 32-character dot matrix plasma display, which is all reproduced in software (other versions dropped one of the cassette drives for a modem, bleeding edge innovation for 1974 microcomputing).
From here, [Michael] set off to assemble the various physical components of the original computer. The chassis itself was built from scratch using a mixture of 3D printing and traditional woodwork. The high-voltage plasma display was recreated using four HCMS-2972 dot matrix modules, which minor compromises. The original computer used display memory as extra storage when executing instructions, which created a sporadic blinkenlights effect on the original display. This new display unfortunately won’t reproduce this ‘thinking’ pattern, but it’s a small sacrifice.
Similarly, the original keyboard was going to be challenging to replicate with 100% accuracy, so a brand-new recreation of an Ohio Scientific computer keyboard was used instead. The layouts are extremely similar, and anyone except your most committed Canadian retro computing enthusiasts probably wouldn’t notice the difference. Being a modern recreation of a vintage keyboard, this was relatively easy to source. A set of custom-made keycaps with APL legends really helped sell the replica.
And while working dual cassette drives would have brought this project home, it’s commendable that [Michael] has created ‘working’ cassette drives using 3D printed cassettes and some magnetic magic using hall effect sensors to identify the loaded cassette. The emulator incorporates three virtual cassette tapes which made this solution possible.
If this all sounds familiar, it might be because this project was based on a
superb Hackaday writeup of the MCM/70
. A truly innovative computer for its time, the story behind Micro Computer Machines (not to be confused with the toy cars) is a fascinating tale, and the write-up is worth a read if you haven’t seen it already. | 17 | 5 | [
{
"comment_id": "6592263",
"author": "George",
"timestamp": "2023-02-05T00:46:41",
"content": "Texas Instruments had a similar terminal in the late 1970s. We used it to work with code to programming microprocessors. Left tale was input and was read into memory, We made edits. Then wrote source fi... | 1,760,372,406.011771 | ||
https://hackaday.com/2023/02/04/the-wic64-brings-classic-commodores-online-google-maps-included/ | The WiC64 Brings Classic Commodores Online, Google Maps Included | Robin Kearey | [
"classic hacks",
"Retrocomputing"
] | [
"bbs",
"commodore 64",
"ESP32",
"wifi"
] | A computing platform is never really dead unless people stop developing new software for it. By that measure, the Commodore 64 is alive and well: new games, demos, and utilities are still being released on a regular basis. Getting those new programs onto an old computer was always a bit of a hassle though, requiring either an SD card adapter for the Commodore or a direct cable connection from an internet-connected PC. Luckily, there’s now a simpler way to get your latest software updates thanks to a WiFi adapter called WiC64. This adapter plugs into the expansion port of a classic Commodore and lets you download programs directly into memory. [Tommy Ovesen] over at [Arctic Retro] bought one and
explored its many features
.
The basic design of
the WiC64
is straightforward: an ESP32 mounted on an adapter board that connects its data bus to that of the Commodore 64, 128 or VIC-20. A simple program, which you still need to transfer the old way, lets you configure the device and connect to a WiFi network. Once that’s done, an interactive BBS-style program is launched that allows you to access a range of online services. The WiC64 developers provide these, but since the system is fully open-source there’s nothing stopping you from running your own servers as well.
Services currently available include an RSS reader, several multiplayer online games, and even a radio station that plays non-stop SID tunes. There’s also a direct link to
CSDB
, an online database of Commodore 64 programs and demos which you can now simply download and run directly on your C64 – in effect, a modern app store for a classic computer.
One feature that really seems to defy the C64’s hardware limitations is a fully functional version of Google Maps. Even with the Commodore’s limited resolution and color depth, it does a pretty decent job of showing maps, satellite photos, and even Street View images.
Using the WiC64 requires no hardware modifications to the Commodore 64, but a custom ROM is available that enables a few convenient features such as
LOAD
ing programs directly from a web address. There have been several attempts at
getting classic Commodores online
, but none so far that managed to get complex apps like Google Maps running. We have seen
YouTube videos being played on a Commodore PET though
. | 29 | 11 | [
{
"comment_id": "6592141",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-02-04T21:29:33",
"content": "“and even a radio station that plays non-stop SID tunes”But is it AM or FM?B^)",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6592204",
... | 1,760,372,406.184534 | ||
https://hackaday.com/2023/02/04/fulcrum-foils-finger-fatigue/ | Fulcrum Foils Finger Fatigue | Jonathan Bennett | [
"Peripherals Hacks"
] | [
"custom keyboard",
"mechanical keyboard",
"split keyboard"
] | It turns out that typing all day just might be bad for your hands and fingers. Repetitive Strain Injury, RSI, was a real problem for [David Schiller], particularly when coding. So, naturally, he started designing his own keyboard. And bless him, he’s
shared the whole project on GitHub
.
The solution is Fulcrum, a chording keyboard with keys that can be pressed with minimal movement. And one more clever trick is a thumb joystick, mounted in the thumb’s opposable orientation. It’s a 5-way switch, making for a bunch of combinations. The base model is a 20-key arrangement, and he’s also designed a larger, 40-key option.
The build is pretty simple, if you have access to a 3D printer. Print the STLs, add key switches, and
wire it all up to a microcontroller
. Use the supplied code, and all that’s left is to learn all the chord combos. And why stop with combos for single characters, when there are plenty of common words and plenty of key combinations. If you decide to build your own take on the Fulcrum, be sure to
let us know about it
! | 10 | 3 | [
{
"comment_id": "6592059",
"author": "Fixed for Formal Faultless Factualization",
"timestamp": "2023-02-04T19:16:13",
"content": "Fulcrum Fights Finger Fatigue",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6592072",
"author": "sampleusername",
"timest... | 1,760,372,406.240433 | ||
https://hackaday.com/2023/02/04/copyright-data-but-do-it-right/ | Copyright Data, But Do It Right | Elliot Williams | [
"Hackaday Columns",
"Rants"
] | [
"creative commons",
"newsletter",
"open data",
"open source",
"Rant"
] | Copyright law is a triple-edged sword. Historically, it has been used to make sure that authors and rock musicians get their due, but it’s also been extended to the breaking point by firms like Disney. Strangely, a concept that protected creative arts got pressed into duty in the 1980s to
protect the writing down of computer instructions
, ironically a comparatively few bytes of BIOS code. But as long as we’re going down this strange road where assembly language is creative art,
copyright law could also be used to protect the openness of software as well
. And doing so has given tremendous legal backbone to the open and free software movements.
So let’s muddy the waters further. Looking at cases like the
CDDB fiasco
, or the most recent sale of
ADSB Exchange
, what I see is a community of people providing data to an open resource, in the belief that they are building something for the greater good. And then someone comes along, closes up the database, and sells it. What prevents this from happening in the open-software world? Copyright law. What is the equivalent of copyright for datasets? Strangely enough,
that same copyright law
.
Data, being facts, can’t be copyrighted. But data
sets
are purposeful collections of data. And just like computer programs, datasets can be licensed with a restrictive copyright or a permissive copyleft. Indeed, they must, because the same presumption of restrictive copyright is the default.
I scoured all over the ADSB Exchange website to find any notice of the copyright / copyleft status of their dataset taken as a whole, and couldn’t find any. My read is that this means that the dataset is the exclusive property of its owner. The folks who were contributing to ADSB Exchange were, as far as I can tell, contributing to a dataset that they couldn’t modify or redistribute. To be a
free and open dataset
, to be shared freely, copied, and remixed, it would need a copyleft license like Creative Commons or
the Open Data Commons license
.
So I’ll admit that I’m surprised to have not seen permissive licenses used around community-based open data projects, especially projects like ADSB Exchange, where all of the software that drives it is open source. Is this just because we don’t know enough about them? Maybe it’s time for that to change, because copyright on datasets
is
the law of the land, no matter how absurd it may sound on the face, and the closed version is the default. If you want your data contributions to be free, make sure that the project has a free data license.
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
! | 33 | 10 | [
{
"comment_id": "6591855",
"author": "Ostracus",
"timestamp": "2023-02-04T15:10:14",
"content": "Of course, one wonders if our patron saint of openness didn’t foresee this problem, otherwise there would have been an inclusion in the GPL.",
"parent_id": null,
"depth": 1,
"replies": []
}... | 1,760,372,406.311124 | ||
https://hackaday.com/2023/02/05/equipping-rats-with-backpacks-to-find-victims-under-rubble/ | Equipping Rats With Backpacks To Find Victims Under Rubble | Maya Posch | [
"Misc Hacks",
"News"
] | [
"animal",
"disaster response",
"rats",
"rescue",
"rubble"
] | When it comes to demining or finding victims after a disaster, dogs are well-known to aid humans by sniffing out threats and trapped humans with ease. Less well-known, but no less impressive are rats, with the African giant pouched rat being the star of the show. Recently a student at the Dutch Technical University of Eindhoven (TU/e) has demonstrated how these rats can sniff out buried victims,
aided by a high-tech backpack
that gives them a communication link back to their human handler.
All of this is done in association with the Belgian-registered and Tanzania-based NGO APOPO, whose achievements include training gold medal winner
Magawa the rat
, who helped find 71 landmines and dozens more types of UXO over a 5-year career. These landmine-hunting rats are known as HeroRATs and have been helping demine nations since the 1990s. They may be joined by RescueRats in the near future.
Each RescueRat is equipped with a backpack that contains a camera and battery, as well as GPS and altimeter. Each backpack includes a button that the rat is trained to press when they have found a victim — essentially dropping a pin on their human rescuer’s maps.
Figuring out the location of the victim inside the rubble pile is the real challenge. This is where a (LoRa) radio beacon in the backpack is triangulated using receivers placed around the area, allowing the rescuers to determine with reasonable accuracy where to focus their efforts.
(Thanks to [Roel] for the tip!) | 20 | 9 | [
{
"comment_id": "6593285",
"author": "Drone",
"timestamp": "2023-02-06T07:16:57",
"content": "Very timely. I’m sure they can use these RescueRats in Syria and Turkey this morning!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6593315",
"author": "Glaskows... | 1,760,372,406.364536 | ||
https://hackaday.com/2023/02/05/hacking-the-python-for-loop/ | Hacking The Python For Loop | Al Williams | [
"Software Development",
"Software Hacks"
] | [
"python"
] | In the early days of C, you’d occasionally see someone — probably a former Pascal programmer — write something like this:
#define BEGIN {
#define END }
This would usually initiate complaints about abusing the preprocessor and generally being anti-C. Surely no modern language would permit such things, right? Perhaps not. Consider [Tushar Sadhwani] who wanted to create a classic
C-style for loop inside of Python
. He did it, and the journey is perhaps more interesting than the result.
First, you can’t just transport straight C for loops into Python. There has to be some concession to Python syntax. The initial attempt was clever but not clever enough. However, the disassembly of the Python code was telling. The second attempt, however, was particularly interesting.
That attempt used an odd feature to examine the interpreter’s tree structure for the code and then modify it. This is sort of like a very painful C preprocessor but more powerful. That version works although it is pretty convoluted.
Ironically, [Tushar] then set up a third attempt after seeing code that tries to replace Python indentation with braces using a codec. In Python-speak, a codec lets you convert different text encodings. However, you can do other things than text encoding conversion. This is closest in spirit to the C preprocessor method. You can wade through the source code ahead of processing and make whichever changes you see fit.
Is any of this really useful? Probably not as it is. But you never know when you might need to do something exotic and one of these techniques could save the day. You probably couldn’t get away with some of this on
MicroPython
, of course. Your mileage may vary depending on where you find your Python running — like
the Web
. | 33 | 11 | [
{
"comment_id": "6593527",
"author": "John the Programmer",
"timestamp": "2023-02-06T14:25:18",
"content": "Thanks for confirming my decision to avoid Python.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6593536",
"author": "Eugeny (@eugeeeeny)",
... | 1,760,372,406.64386 | ||
https://hackaday.com/2023/02/05/hackaday-links-february-5-2023/ | Hackaday Links: February 5, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"acronym",
"Chinese balloon",
"ev",
"Facebook messenger",
"HAB",
"hackaday links",
"high altitude balloon",
"hybrid",
"lithium",
"meta",
"negative testing",
"sensory deprivation",
"smartphone battery",
"toyota"
] | Well, this week’s Links article is likely to prove a bit on the spicy side, thanks in no small part to
the Chinese balloon that spent the better part of the week meandering across the United States
. Putting aside the politics of the whole thing — which we’ll admit is hard to do, given the state of the world today — there are some interesting technical aspects to this story, which the popular press has predictably ignored. Like the size of this thing — it’s enormous. This is not even remotely on the same scale as the hundreds of radiosonde-carrying balloons sent aloft every day, at least if the back-of-the-envelope math thoughtfully sent to us by [Dr_T] holds up. If the “the size of three buses” description given in most media reports is accurate, that means a diameter of about 40 meters, for a volume of 33,500 cubic meters. If it’s filled with helium — a pretty safe bet — that makes its lifting capacity something like three metric tons. So maybe it was a good idea
to wait until it was off the Carolinas to shoot it down
.
In other potentially spicy news, we stumbled upon
an article
this week that provides details on Toyota’s seeming foot-dragging when it comes to electric vehicles. Toyota has staked out a pretty staunch “hybrids-only” approach to its vehicle lineup, and although it’s working on a battery-only platform, it’s pretty safe to say that the Japanese carmaker has not been favorably disposed to converting to an all-electric lineup. The numbers they use to defend that position are interesting, too, when taken with the appropriate amount of salt. They claim their position is based on the limits to lithium production, which of course is essential to building batteries. Given a fixed supply of the metal, they feel it’s smarter to build many smaller batteries and put them in hybrid vehicles, rather than commit to building just a limited number of giant batteries for a smaller fleet of EVs. Again, this has to be tempered with the knowledge that Toyota just happens to have a lot of its production capacity devoted to hybrid cars, so it may be a little self-serving. But it still makes sense, at least until we can lasso a lithium-rich asteroid and tow it back to Earth.
Have you ever felt like your phone battery is running down far quicker than it should? If so, you’re not alone, and it may be due to something called “negative testing” on Facebook Messenger. This is according to
whistleblower and now ex-Facebook engineer George Hayward
, who claims he was fired for refusing to partake in such testing. He claims Meta can run code that runs the battery down on a specific phone, apparently because that’s how data science is done. We agree with George that this is unethical and dangerous — imagine needing to dial emergency services because you’re having chest pain only to find out your phone battery has been depleted by a random test you didn’t know you had signed up for when you signed off on the EULA.
If you’ve ever had to scan through a modern scientific paper, one of the hardest bits is coming up against acronyms that you’re not familiar with. This usually means you have to go back in the text to find where the acronym was instantiated to get a translation, or perhaps even Google it in the worst case. But with so many forced and cutesy acronyms — looking at you, NASA; SHERLOC, and WATSON? — the signal-to-noise ratio on a search can make meaningful results difficult to obtain. To look into the prevalence of acronyms in scientific literature and how they might be impacting understanding, a bunch of Danish scientists came up with a paper entitled
“SearCh for humourIstic and Extravagant acroNyms and Thoroughly Inappropriate names For Important Clinical trials (SCIENTIFIC): qualitative and quantitative systematic study.”
It’s actually a pretty good read, and has some funny bits, like the two criteria they define for acronym quality: a positive factor, known as BEAUTY (Boosting Elegant Acronyms Using a Tally Yardstick), and negative factors, denoted CHEATING (obsCure and awkHward usE of lettArs Trying to spell somethING). Extra points for misspelling “awkward” and making the extra letter the only one from the word to make it into the acronym.
And finally, if you’ve been having trouble concentrating at work lately as much as I have, then you might want to hop in the WABAC machine and check out
“The Isolator.”
It dates from the 1920s and was the brainchild of none other than Hugo Gernsback, the father of science fiction (or at least science fiction publishing) — as well as magazines like Radio Electronics. Old Hugo apparently has a hard time staying on track at the office thanks to both audible and visible stimulation, so he came up with something that looks like a cross between a pith helmet and an old-timey diving helmet. The thing was substantial, made of layers of wood, cork, and felt, presumably for their sound-absorbing qualities, and also limited visual distractions with just a tiny pair of portholes, which would have exactly zero chance of lining up with your axis of view at any given moment. To prevent suffocation, and possibly as a quick hangover remedy, Hugo thoughtfully included an inlet for an oxygen supply, which appears to blow directly at the wearer’s nose. We can’t imagine how stifling it would have gotten inside that thing. | 33 | 15 | [
{
"comment_id": "6593060",
"author": "GotNoTime",
"timestamp": "2023-02-06T00:11:42",
"content": "The Isolator looks like Dark Helmet’s pith helmet from Spaceballs.The portholes are even worse. One of the diagrams in the article shows that they’re mostly painted black with only a tiny slit that is c... | 1,760,372,406.514858 | ||
https://hackaday.com/2023/02/05/behold-a-microscope-that-sees-by-squashing-things-into-it/ | Behold A Microscope That Sees By Squashing Things Into It | Donald Papp | [
"Science",
"Tool Hacks"
] | [
"gel",
"Imaging",
"lab tools",
"microscope"
] | “Look with your eyes, not your hands” is something many of us have heard while growing up, but that doesn’t apply
to the touch-sensitive microscope [Steve Mould] got to play with
.
Gel pad removed, exposing lens and multi-directional lighting.
The wand-like device is made by Gelsight, and instead of an optical lens like a normal microscope, it sports a gel pad on the sensing end. By squashing an object into the gel, the device is able to carefully illuminate and image the impression created. By taking multiple images lit from different angles, a lot of information can be extracted.
The result is a high-resolution magnification — albeit a monochromatic one — that conveys depth extremely well. It’s pretty neat clearly seeing tiny specks of dust or lint present on surfaces when [Steve] demonstrates imaging things like coin cells.
Many a hacker knows that the devil is in the details when it comes to executing an idea. Even so, the basic principles of the Gelsight seem simple enough and possibly within the realm of inspired DIY in the same way that we saw
a CNC gantry and USB microscope repurposed as an optical comparator
.
Watch the Gelsight in action in the video below, embedded below the page break. | 18 | 8 | [
{
"comment_id": "6592947",
"author": "hartl",
"timestamp": "2023-02-05T21:14:28",
"content": "not sure if publishing a partial fingerprint is a good idea in this modern world…",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6592953",
"author": "Piecut... | 1,760,372,406.574691 | ||
https://hackaday.com/2023/02/05/dishwasher-repair-nightmare-chasing-down-3-faults/ | Dishwasher Repair Nightmare: Chasing Down 3 Faults | Donald Papp | [
"Repair Hacks"
] | [
"Bosch",
"dishwasher",
"logic analyzer",
"nightmare",
"repair"
] | It all started with a vague error code (shown in the image above) on [nophead]’s Bosch SMS88TW01G/01 dishwasher, and it touched off
a months-long repair nightmare
that even involved a logic analyzer. [nophead] is normally able to handily diagnose and repair electronic appliances, but this time he had no idea what he was in for.
Not many dishwashers require breaking out a logic analyzer and 3D-printed custom adapters, but this one did.
Not only were three separate and unrelated faults at play (one of them misrepresented as a communications error that caused a lot of head-scratching) but to top it all off, the machine is just not very repair-friendly. The Bosch device utilized components which are not easily accessible. In the end [nophead] prevailed, but it truly was a nightmare repair of the highest order. So what went wrong?
One error appears to have been due to a manufacturing problem. While reverse-engineering the electronics in the appliance, [nophead] noticed a surface-mounted transistor that looked crooked. It was loose to the touch and fell into pieces when he attempted to desolder it. This part was responsible for switching an optical sensor, so that was one problem solved.
Another issue was a “communications error”. This actually came down to ground leakage due to a corroded and faulty heater, and to say that it was a pain to access is an understatement. Accessing this part requires the machine to be turned upside down, because the only way to get to it is by removing the base of the dishwasher, which itself requires a bizarre series of awkward and unintuitive steps to remove. Oh, and prior to turning the machine upside down, one has to purge the sump pump, which required a 3D-printed adapter… and the list goes on.
And the E02 error code, the thing that started it all? This was solved early in troubleshooting by changing a resistor value by a tiny amount. [nophead] is perfectly aware that this fix makes no sense, but perhaps it was in fact related to the ground leakage problem caused by the corroded heater. It may return to haunt the future, but in the meantime, the machine seems happy.
It goes to show that even though every fault has a cause and a reason, sometimes they are far from clear or accessible, and the road to repair is just a long slog. Heck,
even phones these days can be bricked by accidentally swapping a 1.3 mm screw for a 1.2 mm screw
. | 42 | 18 | [
{
"comment_id": "6592825",
"author": "some guy",
"timestamp": "2023-02-05T18:05:16",
"content": "Just a word of caution: Before messing around with scopes, logic analyzers and stuff like this make sure your device has proper separation from mains and that GND is really GND/PE!!! Some appliances migh... | 1,760,372,406.781615 | ||
https://hackaday.com/2023/02/05/need-to-dump-a-protected-stm32f0x-use-your-pico/ | Need To Dump A Protected STM32F0x? Use Your Pico! | Arya Voronova | [
"Reverse Engineering",
"Security Hacks"
] | [
"fuzzing",
"hardware hacking",
"jtag",
"reverse engineering",
"rp2040",
"stm32"
] | Sometimes, security mechanisms can be bypassed if you just do things slightly out of the ordinary. For instance, readout protection on microcontrollers is a given nowadays, to the point where it’s intentionally enabled and relied upon as a major technical measure to protect intellectual property. The gist is — when you connect to a microcontroller over its debug interface and then ask to read its flash memory, it will politely refuse. However, [Racerxdl] shows us that in practice, it’s not flawless protection – for certain chips, you just
need to be a little quicker than usual.
Usually, flashing and debugging software will chat with the microcontroller for a bit, and probe parameters before going for any direct requests. However, if you skip the courtesy and bluntly get to the point immediately right after power is applied to the microcontroller, you can intimidate them just enough to give you one byte of its memory before it refuses to cooperate further. Since that can be any byte you wish, you can read the entire flash — one byte at a time.
You need to power cycle the chip before you can progress, so the hardware does involve a bit more than just an SWD interface, and it will take a fair bit more time than reading out a non-protected chip the usual way; plus, of course, the debugging interface needs to be active for this in the first place, which isn’t always the case. However, it still beats paying a few thousand dollars for a factory in China to decap your chip and read it out using a fancy machine.
[Racerxdl] didn’t just write a proof-of-concept for this attack – they implemented it for one of our favourite chips, the RP2040. As such, you no longer need an unobtainium STM32 to dump an unobtainium STM32.
To be clear, [Racerxdl] didn’t design this attack — it’s been around for some time now. Credit for that goes to
Johanes Obermaier.
All in all, this is a wonderful reminder that seemingly reliable security mechanisms can be foiled by the simplest tricks. For instance, if your chip erases the flash when you unlock its protection, you can
just tell it not to. | 21 | 10 | [
{
"comment_id": "6592808",
"author": "Gravis",
"timestamp": "2023-02-05T17:27:40",
"content": "Umm… why?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6593500",
"author": "Arya Voronova",
"timestamp": "2023-02-06T13:31:53",
"content"... | 1,760,372,406.697346 | ||
https://hackaday.com/2023/02/05/the-effect-of-filament-color-on-print-strength-and-more/ | The Effect Of Filament Color On Print Strength And More | Maya Posch | [
"3d Printer hacks"
] | [
"3d printer filament",
"anneal",
"FDM",
"strength"
] | What is an FDM filament coloring’s purpose but to be an aesthetic choice? As it turns out, the additives that create these changes in coloring and transparency also affect the base properties of the polymer, whether it’s PLA, PETG, or another material. This is where a
recent video
by [CNC Kitchen] is rather illustrative, using a collection of colored PLA filaments from a single filament manufacturer.
[CNC Kitchen] ran a range of tests including tensile strength, ductility, layer adhesion, impact resistance, and annealing performance. The results showed no clear overall winner between plain PLA polymer and any specific color. Perhaps most fascinating was just how much these color additives change the material’s response to annealing. Baking the PLA at 100°C for 30 minutes generally improves material properties, but also can cause warping and shrinking. The effective warping and shrinking differed wildly between the filament.
The general conclusion would seem to be that the natural polymer isn’t necessarily the optimal choice, but that you should test and pick the filament from a specific manufacturer to fit your project’s needs. | 16 | 8 | [
{
"comment_id": "6592725",
"author": "vaewyn",
"timestamp": "2023-02-05T14:42:29",
"content": "I know that across the board red PLA has the most bed adhesion issues no matter the manufacturer. Blue seems to be the best. Took a ton of failed prints before I learned to add every trick when printing wi... | 1,760,372,406.834103 | ||
https://hackaday.com/2023/02/06/sdr-scanner-listens-to-everything/ | SDR Scanner Listens To Everything | Al Williams | [
"Radio Hacks"
] | [
"RTL-SDR",
"scanner",
"sdr"
] | In the old days, scanners would listen to a bunch of channels in a round-robin fashion. If a signal breaks the squelch, the scanner stops and scanning continues scanning after a few seconds of inactivity. But with modern SDRs, you don’t have to listen to one channel at a time. You can listen to all of them. [Tech Minds]
shows RTL-SDR Scanner on Linux
to record up to 20 MHz of the band simultaneously. It records all the channels in the band of interest. The actual project is on
GitHub
.
Once recorded, you can use a web interface to listen to the channels and see some statistics about them. [Tech Minds] tried recording aircraft traffic. It worked, but the program doesn’t know how to demodulate AM yet so if you want to record the entire shortwave band, aircraft, or other AM sources, you’ll have to wait a bit before this software is ready for your use case.
If you need to run the program under Windows like [Tech Minds] did, you can use VMWare Workstation Player to get a free copy of Linux on Windows. We wondered if WSL version two might work, too, but we don’t know. Once you have Linux running, Docker makes the installation straightforward. Since the interface is a web interface, you could probably run this on a small computer on the network and then access it at your leisure from another computer.
Of course, old-fashioned scanners were often used to listen to police and fire radios. Those have all gone
trunked
these days. This isn’t
a new idea
, but it did seem like a well-packaged solution. | 39 | 12 | [
{
"comment_id": "6593787",
"author": "Michael Black",
"timestamp": "2023-02-06T21:23:08",
"content": "Before there were scanners, you had to tune the band manually. Then somecrystal controlled radios. Then scanning added to those. But yiu needed to buy a crystal for every channel you wanted to li... | 1,760,372,406.948179 | ||
https://hackaday.com/2023/02/06/arduino-does-sdi-video-with-fpga-help/ | Arduino Does SDI Video With FPGA Help | Al Williams | [
"Arduino Hacks",
"FPGA",
"Video Hacks"
] | [
"arduino",
"Arduino MKR Vidor 4000",
"fpga",
"sdi",
"serial digital interface"
] | If you are running video around your home theater, you probably use HDMI. If you are running it in a professional studio, however, you are probably using SDI, Serial Digital Interface. [Chris Brown] looks at SDI and shows
a cheap SDI signal generator for an Arduino
.
On the face of it, SDI isn’t that hard. In fact, [Chris] calls it “dead simple.” The problem is the bit rate which can be as high as 1.485 Gbps for the HD-SDI standard. Even for a super fast processor, this is a bit much, so [Chris] turned to the Arduino MKR Vidor 4000. Why? Because it has an FPGA onboard. Alas, the FPGA can’t do more than about 200 MHz, but that’s fast enough to drive an external Semtech GS296t2 serializer which is made to drive SDI signals.
The resulting project contains the Arduino, the serializer, a custom PCB, and both FPGA and microcontroller code. While the total cost of the project was a little under $200, that’s still better than the $350 to $2000 for a commercial SDI signal generator.
If you want to play along, the files are out on
GitHub
. We used the
Vidor
back in 2018 when it first came out. If you need a quick start on FPGAs, there’s always
our boot camp
. | 12 | 7 | [
{
"comment_id": "6593818",
"author": "Leon",
"timestamp": "2023-02-06T21:56:18",
"content": "99.999% of job is done by FPGA but “Arduino does video”",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6595489",
"author": "bebop",
"timestamp": "202... | 1,760,372,408.950978 | ||
https://hackaday.com/2023/02/06/jupiters-moon-io-could-play-host-to-life/ | Jupiter’s Moon Io Could Play Host To Life | Lewin Day | [
"Hackaday Columns",
"Slider",
"Space"
] | [
"I/O",
"Jupiter",
"life",
"search for life"
] | It was many years ago now when David Bowie asked if there was life on Mars. Since then, we’ve concluded there isn’t, much to everyone’s disappointment. That left scientists the world over to start looking elsewhere for new lifeforms for us to talk to, conquer, or play bridge with. Or perhaps more likely, look at under a microscope.
The latest candidate for hosting nearby life is Jupiter’s moon, Io. Let’s take a look at what makes Io special, and what we might hope to find there.
The Pizza Moon
When it comes to places to search for life, Io hasn’t really been at the top of the list. Other moons of Jupiter, like Europa and Ganymede, have been considered far more likely candidates. That’s largely down to the fact that those moons play host to subsurface oceans. Given that we know life and water are so closely intertwined here on Earth, that has guided our search elsewhere. Saturn’s moon
Enceladus
has also been considered a strong contender, for a plume of methane erupting from its surface. It too plays host to subsurface oceans which could theoretically host life.
Io’s volcanic eruptions can be huge in scale, as seen by Galileo in 1997.
Io, in comparison, is a hot and volcanic place. New data collected by NASA’s Juno spacecraft suggests that despite this rugged, unhospitable exterior, Io could still host living things. On a recent flyby, Juno got within 80,000 km of the so-called “pizza moon,” and a future pass will get as close as 1,500 km. That’s set to update our knowledge of the moon significantly. Before Juno, our last visit to Io was with the Galileo spacecraft, over 20 years ago.
In size, Io is roughly comparable to the Earth’s moon, also known as “The Moon”. Io is wracked by volcanic activity though, with active lava flows on the surface, with mountain ranges and plains interspersed with calderas left over from volcanic eruptions. Being so distant from the Sun, Io can be very cold, at up to -130 °C in places. It’s nevertheless is an energetic place, with eruptions capable of shooting lava hundreds of kilometers from the surface.
In fact, near areas of volcanic activity, temperatures can reach up to 1,600 °C. The lava is kept hot and flowing thanks to the tidal forces experienced by Io, thanks to Jupiter itself and nearby moons Europa and Ganymede. It’s possible that the small moon may have once held water, like Europa or Ganymede, as ice was once common in its part of the solar system. However, a combination of radiation from Jupiter and the unrelenting tidal heating have likely long since driven away most of the water on Io, if any was once present.
Theories about life on Io center around the materials present and its unique environment. It’s believed that geothermal heat on the moon, combined with sulfur compounds, could serve as an energy source for simple microbial life. However, it’s unlikely these microbes would live on the surface, where temperatures are often well below freezing and radiation abounds. Instead, they could lurk within lava tubes beneath the surface. In fact, lava tubes commonly play host to microbes on Earth, all around the globe, so it’s conceivable that the same thing could happen on a distant rock far away in the solar system.
The difficulty for life on Io hinges on whether or not there is
any
water left on the desolate moon. Water serves as a solvent, and is involved in all manner of basic life processes for organisms on Earth. It’s abundant here, and the absence of water in an environment here largely coincides with an absence of life.
Lava tubes are conduits underground through which lava once flowed. It’s possible that lava tubes on Io could host life in much the same way they do on Earth. Credit:
Frank Schulenburg, CC-BY-SA-3.0
If water isn’t present, though, alternatives could exist. Hydrogen sulfide (H
2
S) is one possibility, with some similarities to the chemical behavior of water. It exists in a liquid form from -86 °C to -60 °C. Given the temperature profile on Io, liquid H
2
S could form in areas beneath the surface, particularly if subsurface channels were warmed by lava flows. Life could potentially exist in a spore-like form, where it springs to life when at the right temperature and in the right solvent environment, and going dormant when conditions aren’t so suitable. Bacteria on Earth can behave in such ways, so it’s not inconceivable for life to develop in this way elsewhere.
Of course, it’s all speculation at this point. The primary focus is on theories as to whether life
could
be on Io, rather than investigating if it currently is there or not. Proving the latter is a difficult task, and one that would likely require new space missions with a focus on doing the hard science necessary. Perhaps, though, a future generation will be the first to discover life teeming just beneath the scorched surface of the distant Pizza Moon.
Featured image: “
Full Disk Views of Io
” by NASA. | 26 | 11 | [
{
"comment_id": "6593680",
"author": "Michael Black",
"timestamp": "2023-02-06T18:13:53",
"content": "Robert Heinlein wrote about it in 1950, Farmer in the Sky.Atmosphere machines, gravity fields, and acomplicated process to turn lava into dirt for farming.",
"parent_id": null,
"depth": 1,
... | 1,760,372,409.313253 | ||
https://hackaday.com/2023/02/06/create-your-rtl-simulations-with-kicad/ | Create Your RTL Simulations With KiCAD | Dave Rowntree | [
"Software Hacks"
] | [
"icestudio",
"KiCAD",
"RTL",
"simulation",
"verilog"
] | [Bob Alexander] is in the process of designing a homebrew discrete TTL CPU, and wanted a way to enter schematics for digital simulations via a Verilog RTL flow. Since KiCAD is pretty good at handling hierarchical schematics, why not use that? [Bob] created a KiCAD plugin,
KiCadVerilog
allowing one to instantiate and wire up the circuits under consideration, and then throw the resulting Verilog file at your logic simulator of choice.
KiCadVerilog doesn’t do all the hard work though, as it only provides the structure and the wiring of the circuit. The actual guts of each TTL instance needs to be provided, and a reference to it is manually added to the schematic object fields. That’s a one-time deal, as you can re-use the component library once generated. Since TTL logic has been around for a little while, locating a suitable Verilog library for this is easy. Here’s
ice-chips-verilog
by [TimRudy] on GitHub for starters. It’s intended as a
collection
for
Icestudio
(which is also worth a look). Still, the Verilog code for many TTL series devices is presented ready for the taking, complete with individual test benches in case you need them.
Check out the
project GitHub page
for the module source code, and some more documentation about the design process.
We’ve seen many RTL hacks over the years,
here’s an interesting way to generate a PCB layout with discrete logic, direct from the RTL
. | 4 | 2 | [
{
"comment_id": "6593752",
"author": "Leandro Heck (@leoheck)",
"timestamp": "2023-02-06T20:25:12",
"content": "Any visual example for us?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6593889",
"author": "Bob",
"timestamp": "2023-02-06T23:5... | 1,760,372,409.466725 | ||
https://hackaday.com/2023/02/06/ask-hackaday-the-ten-dollar-digital-mixing-desk/ | Ask Hackaday: The Ten Dollar Digital Mixing Desk? | Jenny List | [
"Ask Hackaday",
"digital audio hacks",
"Featured",
"Interest",
"Slider"
] | [
"alsa",
"linux",
"mixing desk",
"OSS",
"Pipewire",
"sound card"
] | There comes a point in every engineer’s life at which they need a mixing desk, and for me that point is now. But the marketplace for a cheap small mixer just ain’t what it used to be. Where once there were bedroom musicians with a four-track cassette recorder if they were lucky, now everything’s on the computer. Lay down as many tracks as you like, edit and post-process them digitally without much need for a physical mixer, isn’t it great to be living in the future!
This means that those bedroom musicians no longer need cheap mixers, so the models I was looking for have disappeared. In their place are models aimed at podcasters and DJs. If I want a bunch of silly digital effects or a two-channel desk with a crossfader I can fill my boots, but for a conventional mixer I have to look somewhat upmarket. Around the three figure mark are several models, but I am both a cheapskate and an engineer. Surely I can come up with an alternative.
Cheap And Nasty Sound Cards To The Rescue!
An analogue mixer is an extremely simple device at heart, it simply sums a series of audio signals each of which has its own volume control fader. It’s so simple that one can be made with passive components only, and indeed there are extremely affordable mixers that do just that.
They claim this thing has a TI PCM2902 chip inside, and who am I to dispute that!
Most small mixers however use straightforward op-amp gain stages and buffers, with adjustable ones for each channel. It’s possible to make one without too much bother, and indeed I considered exactly that. The problem was that the budget climbs with each successive channel towards the point at which I’d be better off spending a bit more and buying one. I’m not pricing for the most expensive faders on the market, but a reasonable quality linear potentiometer adds quite a bit per channel to the BoM.
At this point it occurred to me, can I use the PC as a live mixer with multiple sound cards? I can order a heap of very cheap and nasty USB sound cards for under ten dollars, so it won’t cost me much to try. I placed the order, and when they arrived I plugged them in and instantly had a computer with five audio jacks.
Unfortunately I can’t just fire up Audacity expecting an awesome multi-channel experience. I have a load of sound cards to choose from, but I can only record from one of them at any one time. It’s time for a dive into Linux audio, to a level I’ve never needed to do before because, well, it’s always just
worked
, hasn’t it?
Who Knew There Was So Much To Linux Audio!
So near and yet so far, I can see them but not touch them!
In the beginning, there was the Open Sound System, or OSS. My Linux in the 1990s was all about setting up web servers, so the first Linux sound subsystem passed me by. Instead like probably most of you, I’m used to ALSA, the Advanced Linux Sound System. This sits at kernel level and provides an interface to the disparate pieces of sound hardware there may be connected to the system. On top of that lie sound servers providing a further interface layer such as PulseAudio or Jack, and in many distributions the whole lot has been replaced by PipeWire.
All these promise mixing and multiple card support as their killer feature, so somewhere in that lot it should be possible to find what I want, right? Unfortunately not, because while they can all see a load of soundcards, none of the various machine configurations I tried could make applications see more than one of them at once. Perhaps a solution
could be found in binding several cards together as a virtual ALSA card
. But here yet again there’s no reward, because as the instructions point out, the real hardware will drift out of sync over time. I wonder whether my live mixer application would find this less problematic than a simultaneous multi-track recorder, but something tells me if it did, everybody would be doing it.
So I’ve conspicuously failed to make a cheap live mixing desk out of a thousand-dollar laptop and ten dollars’ worth of cheap sound cards. Plenty of you will be no doubt be queueing up to berate me for my less-than-1337 level of Linux wizardry, but the truth is I’ve never really concerned myself with the multimedia features before. I’m still curious though, can this be done? Answer me below in the comments! | 110 | 46 | [
{
"comment_id": "6593558",
"author": "Dude",
"timestamp": "2023-02-06T15:21:58",
"content": ">it’s always just worked, hasn’t it?No. You’ve just never really done anything with it. Basic stereo with no EQ is “fine”. Anything beyond that goes hairy really quickly.",
"parent_id": null,
"depth"... | 1,760,372,409.244596 | ||
https://hackaday.com/2023/02/06/surfing-the-web-like-its-1978-carbonyl/ | Surfing The Web Like It’s 1978 — Carbonyl | Jonathan Bennett | [
"computer hacks"
] | [
"ascii art",
"browser",
"Carbonyl",
"text-based"
] | [Fathy] gets a kick out of doing odd things with Chromium, and
Carbonyl
is a clever byproduct of that hobby. In this case, it’s what you get when you connect chrome’s renderer to an SVG output module and then convert that SVG to colored characters on a terminal. See,
html2svg
is an earlier project, taking Chromium’s Skia engine and plugging it into an SVG back-end. And once you have SVG, why not render it to the terminal?
And the results are actually pretty impressive. Imagery is rendered using Unicode 2584, a half-block character. The background and foreground color can be set per character, giving us two controllable pixels per character. Text is handled a bit differently, rendering using the normal text fonts, making for readable pages.
The
source is very much a work in progress
, but there are some neat ideas already coalescing around the project, like using sixels for better rendering. There’s already decent mouse support and audio output, making for an impressive terminal experience. This might be a project to keep an eye on. | 29 | 7 | [
{
"comment_id": "6593442",
"author": "Askarel",
"timestamp": "2023-02-06T12:24:53",
"content": "Finally a wothy replacement for lynx and elinks !",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6593503",
"author": "Feinfinger (super villain in nostalg... | 1,760,372,408.836102 | ||
https://hackaday.com/2023/02/06/ikea-clock-gets-wanderlust/ | Ikea Clock Gets Wanderlust | Al Williams | [
"3d Printer hacks",
"clock hacks"
] | [
"3d print",
"clock",
"Geneva Drive",
"wandering hour"
] | We always enjoy unique clocks, and a recent 3D print from [David Kingsman] caught our eye. It converts an Ikea clock into a very unusual-looking “
wandering hour
” clock that uses a Geneva drive to show a very dynamic view of the current time. The concept is based on an earlier wandering clock, but [David] utilized a different mechanism.
To read the clock, you note which hour numeral is in range of the “minute arc” and read the time directly. So if the 12 hour is over the 20-minute mark, the time is 12:20. Besides the clock, you need a fair number of printed parts, although they all look like relatively simple prints. You’ll also need 13 bearings and some metric hardware. A piece of cardboard used for the face rounds out the build.
Modifying the clock is more than just taking it apart. There is a template file to print, and you’ll need to align it and drill holes as indicated.
If you haven’t seen a Geneva drive before, it translates a continuous rotation into intermittent rotation. This isn’t the first clock we’ve seen use this kind of drive, although the last one we saw
represented time differently
. If you want something even more mechanical, try
a chain-driven clock
. | 29 | 10 | [
{
"comment_id": "6593356",
"author": "Chuck",
"timestamp": "2023-02-06T09:40:25",
"content": "Why? There could be just one drive wheel (bigger in the center) with three driven in geneva mechanism and no internal gears.",
"parent_id": null,
"depth": 1,
"replies": [
{
"commen... | 1,760,372,408.901643 | ||
https://hackaday.com/2023/02/04/experimenting-with-20-meters-of-outlet-adapters/ | Experimenting With 20 Meters Of Outlet Adapters | Chris Lott | [
"Parts"
] | [
"crazy",
"power adapter",
"power meter"
] | You may have seen some of the
EEVblog
dumpster dive videos, where [Dave Jones] occasionally finds perfectly good equipment that’s been tossed out. But this time, rather than a large screen monitor, desktop computer, or a photocopier, he features a
stash of 283 electrical outlet double adapters
that he found last year. He decided to perform a test in the parking lot, connecting all 283 adapters in series.
Using a pair of power meters and a 2 kW electric heater as a test load, [Dave] and his son [Sagan] measure the loss through this wild setup. It works out to about about 300 W, or roughly 1 W per adapter. He did a follow-up experiment using a FLIR thermal camera, and confirmed that the power loss is reasonably uniform, and that no single rogue adapter consuming all the lost power. After a back of the envelope calculation, we estimate this chain of adapters is about 20 meters long, making this whole thing entirely pointless but interesting nonetheless. Stick around until the end of the video for a teardown — they’re not as cheaply made as you might think.
[Dave]’s crazy experiment aside, we do wonder why someone had so many adapters to throw away in the first place. What would you have done with 283 adapters — left them in the dumpster or rescued them? | 100 | 27 | [
{
"comment_id": "6591729",
"author": "Andy Pugh",
"timestamp": "2023-02-04T12:11:50",
"content": "“we do wonder why someone had so many adapters to throw away in the first place. What would you have done with 283 adapters ”To run 24 devices from a single outlet, obviously.(If I am right that the geo... | 1,760,372,409.089957 | ||
https://hackaday.com/2023/02/04/mechanical-keyboard-is-also-a-mouse/ | Mechanical Keyboard Is Also A Mouse | Bryan Cockfield | [
"Peripherals Hacks"
] | [
"3d printer",
"arduino",
"cad",
"design",
"keyboard",
"mouse",
"split",
"wireless"
] | The mechanical keyboard community is a vibrant, if not fanatical, group of enthusiasts determined to find as many possible ways of assembling, building, and using as many high-quality keyboards as possible. With so many dedicated participants, most things that can be done with a keyboard already have been done. So when something as unique as
this split keyboard that also doubles as a mouse
pops up, we take notice.
The keyboard is a custom build from [Taliyah Huang] which uses a pair of Arduinos, one in each half of the keyboard, to communicate key and mouse information to a third Arduino which is plugged in to her laptop. The right-hand half of the keyboard also includes the circuitry from an optical mouse, which gets powered up when the caps lock button is held down. When activated, this allows the keyboard to be used as a mouse directly. It also includes support for most Mac gestures as well, making it just as useful as a trackpad.
While there were some problems with the design, including being slightly too tall to be ergonomic and taking nearly 24 hours of soldering to complete, the prototype device is an interesting one especially since it allows for full control of a computer without needing a dedicated mouse. For other unique mechanical keyboard concepts,
we recently featured this build
which takes design and functionality cues from the Commodore 64. | 15 | 9 | [
{
"comment_id": "6591800",
"author": "Justin",
"timestamp": "2023-02-04T14:01:36",
"content": "Had this idea a while back, and couldn’t resolve some of the problems. Looks like she ran into the same problems. Like the keyboard being too thick. And I also couldn’t work out how to keep it light eno... | 1,760,372,409.364718 | ||
https://hackaday.com/2023/02/03/candy-blaster-lets-you-shoot-pez-at-your-friends/ | Candy Blaster Lets You Shoot PEZ At Your Friends | Lewin Day | [
"3d Printer hacks"
] | [
"candy",
"Pez",
"pez blaster"
] | Nerf Blasters are great fun to play with, but you really shouldn’t eat the foam darts. Conversely, Pez dispensers are fussy and kind of boring, but the candy is a tasty treat. [Soloprototype] has presented us the best of both worlds, in the form of
a 3D-printed Pez blaster,
with a firm note that this toy is for grown-ups only.
Overall, the design is very similar to the Pez Shooter, a long-discontinued Pez dispenser design. It uses a basic pistol form factor, and accepts a magazine of Pez pellets loaded into the grip. The magazine itself is cut out of a regular Pez dispenser, to avoid reinventing the wheel. Pulling the trigger fires the Pez pellets with spring power, launching candy into the air.
We all love candy propelled at speed, though [Soloprototype] notes that some safety precautions should be observed. To avoid choking risks, it’s not recommended to allow children to play with the toy. Nor should it be fired at the face or mouth. The full list of safety measures is available on the project’s
Cults3D page.
The Pez blaster is cool, but we’d love to see more work in this space. The world needs a Twinkie Trebuchet, or a Cadbury Catapult, to say nothing of the Butterfingers Balista. If you can think of other Age of Empires siege weapons that would be ideal for candy delivery, drop them in the comments below. Alternatively,
consider the M&M launcher we’ve shared previously
! | 16 | 11 | [
{
"comment_id": "6591522",
"author": "Gilliam Vespa",
"timestamp": "2023-02-04T06:23:53",
"content": "how about the Rolo Wololo",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6591548",
"author": "ewitch",
"timestamp": "2023-02-04T07:09:19",
"conten... | 1,760,372,408.641449 | ||
https://hackaday.com/2023/02/03/scratch-your-itch-to-program-a-microcontroller/ | Scratch Your Itch To Program A Microcontroller | Al Williams | [
"Microcontrollers"
] | [
"block programming",
"scratch"
] | One of the fun things about “old school” computers is that it was fairly easy to get kids into programming them. The old Basic interpreters were pretty forgiving, and you could do some clever things easily with very little theory or setup. These days, you are more likely to sneak kids into programming via Scratch — a system for setting up programs via blocks in a GUI. Again, you can get simple results simply. With Scratch or Basic, complex things have a way of turning out complex, but that’s to be expected. If you want to try a Scratch-inspired take on microcontroller programming, check out
MicroBlocks
. It will work with several common boards, including the micro:bit and the Raspberry Pi Pico. You can use it in a browser or download versions for Linux, Windows, Mac, or even Chromebooks.
You can see a video below about the micro:bit version from a year ago. The tool is advancing, so you’ll find many new features compared to the video, but it will still give you an idea of what’s happening.
We were impressed with the range of blocks and libraries including like I2C, SPI, and NeoPixel. You can graph data easily. We were unable, sadly, to make the browser version work with an ESP32 S3 module we had sitting on the desk. The tutorials have videos and snippets of graphical “code” you can drag directly into the IDE.
We aren’t sure if it was a configuration issue or if the S3 isn’t supported. Or it could have been simple operator error. The web page says it can be “tricky” to get the initial firmware on the ESP32, and — for us — it was apparently too tricky. We even grabbed some firmware images from GitHub and flashed them. We also tried building the smallvm component from scratch, but getting it to build for the S3 took some modifications and uncovered some typos in the code base. It did work in the end and it worked as advertised for a “stock” ESP32 development board.
We get it. You don’t want to shower kids with cryptic error messages. However, there didn’t seem to be many options for troubleshooting or for a teacher or coach to just flash the image in some regular way. There was a GUI — we think — to flash the base firmware on
GitHub
but with little documentation.
But if you have a supported board, it looks great. We know that block programming isn’t the language of choice for most Hackaday readers. But if you are looking for a gateway drug for a friend or a child, this could well be it.
You shouldn’t write kernel modules in Scratch, either, but
people have
. If you’d rather stick with
Python
, you can do that, too. | 19 | 9 | [
{
"comment_id": "6591450",
"author": "0xDEADBEEF",
"timestamp": "2023-02-04T04:18:56",
"content": "Scratch has some Arduino extensions to begin with.And mblock.cc which is clone of Scratch in addition to their robots support, has a ton of microcontroller extensions.",
"parent_id": null,
"dep... | 1,760,372,409.426564 | ||
https://hackaday.com/2023/02/03/levitating-banana-is-an-excellent-conversation-starter/ | Levitating Banana Is An Excellent Conversation Starter | Lewin Day | [
"Art"
] | [
"banana",
"electromagnet",
"hall effect sensor",
"levitating banana",
"levitation"
] | “I really like your floating banana.” If that’s something you’ve always wanted your guests to say when visiting your living room,
this levitating banana project from [ElectroBing] is for you.
The design is simple. It relies on a electromagnet to lift the banana into the air. As bananas aren’t usually ferromagnetic, a simple bar magnet is fitted to the banana to allow it to be attracted to the electromagnet. One could insert the magnets more stealthily inside the banana, though this would come with the risk that someone may accidentally consume them, which can be deadly.
Of course, typically, the magnet would either be too weak to lift the banana, or so strong that it simply attracted the banana until it made contact. To get the non-contact levitating effect, some circuitry is required. A hall effect sensor is installed directly under the electromagnet. As the banana’s magnet gets closer to the electromagnet, the hall effect sensor’s output voltage goes down. Once it drops below a certain threshold, a control circuit cuts power to the electromagnet. As the banana falls away, power is restored, pulling the banana back up. By carefully controlling the power to the electromagnet on a continuous basis, the banana can be made to float a short distance away in mid-air.
It’s a fun build, and one that teaches many useful lessons in both physics and electronics. Other levitation techniques exist, too,
such as through the use of ultrasound
. Video after the break. | 6 | 3 | [
{
"comment_id": "6591310",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-02-04T00:19:13",
"content": "Banana for scale.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6591332",
"author": "Hirudinea",
"timestamp": "2023-0... | 1,760,372,409.510773 | ||
https://hackaday.com/2023/02/03/dad-builds-frickin-tank-for-his-son/ | Dad Builds Frickin’ Tank For His Son | Anool Mahidharia | [
"Tech Hacks",
"Toy Hacks"
] | [
"internal combustion engine",
"main battle tank",
"paintball",
"paintball gun",
"Tank Tracks",
"toy"
] | We gotta love hacker Dads and Moms for being so awesome. Sooner or later, their kids get to play with some amazing toy that every other kid on the block is jealous of. [Meanwhile in the Garage aka MWiG] is one of those super hacker Dads who
built a frickin’ Tank for his son
(video, embedded below.). But it’s so much fun driving that beast around that we suspect Dad is going to be piloting it a lot more than the kid. The tank features metal tracks, differential steering, a rotating turret, periscopes and a functional paintball gun with camera targeting.
Building a tank, even if it’s a mini replica, needs an engine with a decent amount of torque. [MWiG] first tried reviving an old ATV engine, but it did nothing more than sputter and die. It went to the scrap heap after donating its rear transmission and axle. [MWiG] managed to get an old Piaggio scooter with a 250cc / 22 hp engine. The scooter gave up its engine, electricals and the instrument cluster before being scrapped. Looking at the final build, and the amount of metal used, we are left wondering how the puny 22 hp engine manages to drive the tank. We guess it’s the right amount of gearing for the win.
[MWiG] has a lot of experience, and a well equipped workshop with all the right kind of tools to pull off this project. Even so, the build is not without a few hiccups along the way, such as broken drills and bent axle shafts that required rework. The tank chassis is progressively built up by welding a series of square section steel pipe frames. The scooter engine connects to the rear differential via a chain drive. He added a pair of clutches on each wheel to allow differential steering, as well as a pair of disk brakes. The two clutches are actuated using left and right foot pedals and an elaborate system of rigid levers and flexible rod ends. Each of the twelve non-drive wheels, six on each side, have independent spring suspension. The track drive wheel assembly and tensioning system is nothing short of artwork. He fabricated the drive wheel sprockets from bar stock.
Next part of his build focuses on the rotating turret, mounting and articulation of the paintball gun and attaching the camera and LCD screen for targeting. We have to envy a hacker who has a battle tank scrapyard in his neighborhood. Unfortunately, a visit there does not yield any periscopes as he anticipated, so [MWiG] custom fabricates six periscopes using polycarbonate sheets and glass mirror pieces. The tracks are painstakingly fabricated using steel C-channel pieces, lengths of bar stock, and steel cable rubber conveyor belting pieces, all bolted together. It’s amazing to see the amount of hard work he puts in to fabricate the tracks.
He had to replace a misplaced immobilizer and a faulty injector before the tank could be rolled out for its first test drive. He also swapped the soft, short suspension springs with stiffer, longer ones to prevent the tank from bottoming out due to its weight. Finally, he added a couple of idler support wheels to prevent the tank tracks from sagging. He then disassembled the whole vehicle for cleaning, degreasing, painting and pop riveted the aluminum chequer plate paneling. His idea of using a projector to trace out the logo on the side of the tank turret is pretty brilliant. Finally, it was time to tweak the camera for precise targeting of the paintball gun and the tank was ready to roll.
As a bonus side project, he modified a flatbed trailer to transport the mini tank, building some ramps and a nice manual winch to load and unload the tank. After some target practise in the backyard, father and son set off to put the tank through its paces in an isolated field. We have to admit – this is one seriously epic project and it would be fun to be in the drivers seat.
[Meanwhile in the Garage] is a pretty prolific hacker churning out some great projects over the years. Check out this
Rotary Valve Engine That Smokes the Competition
and this
DIY Enclosed Motorcycle To Keep You Dry In The Rain
. | 25 | 15 | [
{
"comment_id": "6591170",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-02-03T21:10:16",
"content": "Nomination for Father of the Year!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6591268",
"author": "Thinkerer",
"timestamp": ... | 1,760,372,410.690129 | ||
https://hackaday.com/2023/02/03/building-a-fake-printer-to-grab-screenshots-off-the-parallel-port/ | Building A Fake Printer To Grab Screenshots Off The Parallel Port | Dave Rowntree | [
"Peripherals Hacks"
] | [
"Advantest",
"bench instruments",
"IEEE-1284",
"KiCAD",
"parallel",
"printer",
"Raspberry Pi Pico",
"rp2040"
] | [Tom Verbeure] recently found himself lamenting the need to take screen grabs from an Advantest R3273 spectrum analyzer with a phone camera, as the older gear requires you to either grab tables of data over an expensive GPIB interface card, or print them to paper. Then he realized, why not
make a simple printer port add-on that looks like a printer
, but sends the data over USB as a serial stream?
On the hardware side, the custom PCB (
KiCAD project
) is based on the Raspberry Pi Pico. Obvious form factor issues aside ([Tom] did revise the PCB to make it smaller) this is a shrewd move, as this is not a critical-path gadget so using the Pico as a USB-to-thing solution is a cost-effective way to get something working with minimal risk. One interesting design point was the use of the
74LVC161284 special function bus interface
that handles the 5 V tolerance that the RP2040 lacks, whilst making the project compliant with IEEE-1284 — useful for the fussier instruments.
Using the
service manual of the Sharp AP-PK11 copier/printer
as a reference, [Tom] again, shows how to correctly use the chip, minimizing the design effort and scope for error. The complete project, with preliminary firmware and everything needed to build this thing, can be found on the
project GitHub page
. [Tom] does add a warning however that this project is still being worked on so adopters might wish to bear that in mind.
If you don’t own such fancy bench instrumentation, but grabbing screenshots from devices that don’t normally support it, is more your thing, then how about a tool to
grab Game Boy screenshots
? | 36 | 15 | [
{
"comment_id": "6591099",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-02-03T19:51:01",
"content": "A great idea.As it is a USB device, does it write to a USB drive?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6591225",
"au... | 1,760,372,410.060765 | ||
https://hackaday.com/2023/02/03/smart-ovens-are-doing-dumb-checks-for-internet-connectivity/ | Smart Ovens Are Doing Dumb Checks For Internet Connectivity | Lewin Day | [
"Current Events",
"Featured",
"Interest",
"News",
"Slider"
] | [
"internet of things",
"IoT",
"iot security",
"smart devices",
"smart oven"
] | If you’ve ever worked in IT support, you’ll be familiar with users calling in to check if the Internet is up every few hours or so. Often a quick refresh of the browser is enough to see if a machine is actually online. Alternatively, a simple ping or browsing to a known-working website will tell you what you need to know. The one I use is
koi.com
, incidentally.
When it comes to engineers coding firmware for smart devices, you would assume they have more straightforward and rigorous ways of determining connectivity. In the case of certain smart ovens,
it turns out they’re making the same dumb checks as everyone else.
“Just Go To Google, Dude”
As reported by
The Register
,
software architect Stephan van Rooij was recently astounded by the behavior of his new AEG home devices. Van Rooij had purchased the AEG Built In Combination Microwave and AEG Oven, which both hilariously feature Wi-Fi in devices that traditionally have no need for connectivity. He had no need for their Wi-Fi features, and purchased them unaware they were even available.
Upon hooking up the devices to his home network, Van Rooij found some curious behaviour. The devices were regularly querying various popular websites to determine whether an internet connection was available or not. The AEG devices were routinely checking
google.com
every five minutes. As a further surprise though, the devices would also send repeat queries to
baidu.cn
and
yandex.ru
on the same timetable. If you’re unfamiliar with these websites, they are popular search engines in China and Russia respectively. Van Rooij was able to capture this activity as he had
a Pi-Hole setup
blocking ads on his home network.
While a quick ping is a perfectly cromulent way of testing your connectivity, it’s a little lazy for manufacturers to rely on such a check. It’s fundamentally a dereliction of responsibility to expect Google to handle your connectivity checks for you. Companies like Microsoft, Google, and Apple maintain their own endpoints for checking internet connectivity. They don’t simply ping some random website that has been deemed popular enough to never go offline. Worse, the appliances already have a cloud API for talking to AEG’s servers. Van Rooij contends that the company should run its own connectivity check through this method, rather than sending data to search firms overseas.
It’s unlikely Baidu and Google would go offline at the same time, or change their domain names.
The odd pings are not the only issue that Van Rooij draws with the oven’s cloud connectivity, either. The whole purpose of the internet connectivity is to provide the devices with some form of remote control, via an app. On the surface of it, this appears highly useful. For example, it could be used to set the oven to begin pre-heating while you’re driving home from the grocery store. It could also provide phone notifications when a timer is up and your meal is done cooking.
However, the oven’s overbearing security measures are set up in a way that makes the remote control feature largely useless. Van Rooij explains that every time the oven door is closed, the user is asked whether they would like to enable remote control. A button must be pressed to enable remote control
every time
the oven is closed. There is no way to permanently enable remote control. Thus, if one forgets to press the button, there is simply no way to remotely activate the oven at all, as the app will refuse to turn the oven on. On the surface of it, this may seem like a wise security measure. However, as Van Rooij points out, even if a malicious actor could turn your oven on remotely, there shouldn’t be any real consequences beyond some wasted energy. If it’s dangerous to run the oven too long, a simple timeout feature would be enough protection. He also points out that a PIN entry through the app would be enough security to prevent children accidentally turning on the oven from their parents phone, if that’s a real concern the company has.
Overall, the story paints a familiar picture: poorly thought-out “smart” features that work poorly and are implemented with odd shortcuts. We’ve written more stories about IoT security issues than you can
shake
a
stick
at
. There’s obviously some value in having an oven you can turn on over the Internet. Whether it’s enough to justify the curious internet traffic and the janky user experience is another question entirely. | 85 | 23 | [
{
"comment_id": "6591048",
"author": "Andrew Taylor",
"timestamp": "2023-02-03T18:37:02",
"content": "Traffic to Russian and china servers from their home address would cause some people in the UK and the USA a lot of problems and to have this traffic from a smart device which could possibly have ... | 1,760,372,410.277319 | ||
https://hackaday.com/2023/02/03/hackaday-podcast-204-cesium-colorful-cast-buttons-and-cnc-pizza/ | Hackaday Podcast 204: Cesium, Colorful Cast Buttons, And CNC Pizza | Kristina Panos | [
"Hackaday Columns",
"Podcasts"
] | [
"Hackaday Podcast"
] | This week, Editor-in-Chief Elliot Williams and Assignments Editor Kristina Panos met up over thousands of miles to discuss the hottest hacks of the past seven days. There’s a whole lot of news this week, and the really good part is the the small radioactive source that went missing in Australia has been found. Phew!
Kristina is still striking out on What’s That Sound, but we’re sure you’ll fare better. If you think you know what it is, fill out the form and you’ll be entered to win a coveted Hackaday Podcast t-shirt!
Finally, we get on to the hacks with an atomic pendulum clock that’s accurate enough for CERN, safecracking the rough-and-ready way, and plenty of hacks that are non-destructive to nice, old things. We’ll gush over a tiny DIY adjustable wrench, drool over CNC pizza, and rock out to the sounds of a LEGO guitar/synthesizer thing.
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!
And/or
download it and listen offline
.
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 204 Show Notes:
News:
ADS-B Exchange Sells Up, Contributors Unhappy
The Radioactive Source Missing In Australian Desert Has Been Found
Wizards Get Creative, Maybe Save The World
What’s that Sound?
If you can figure out this week’s sound,
fill out this form
and maybe you’ll win a Hackaday Podcast t-shirt!
Interesting Hacks of the Week:
RF Spectrometer Sees Inside
Casting Custom Resin Buttons For The Steam Deck
An Atomic Pendulum Clock Accurate Enough For CERN
Hacking Grandfather Clock Accuracy While It’s Still Ticking
Self-Watering Planters Reuse Household Jars
Opening A Safe With A Stepper Motor And DIY Auto-Dialer
Retro Computer Enclosure Without The Sacrifice
Quick Hacks:
Elliot’s Picks:
KiCanvas Helps Teach And Share KiCad Projects In Browsers
Find SWD Points Quickly, No Extra Hardware Needed
Surgery On An LED To Preserve Vintage Aesthetics
Kristina’s Picks:
DIY Adjustable Wrench? Nuts!
Pizza-Making CNC Machine Is The Only Tool We’ve Ever Dreamed Of
Lego Guitar Is Really An Ultrasonically-Controlled Synth
Can’t-Miss Articles:
Detecting Machine-Generated Content: An Easier Task For Machine Or Human?
New AI classifier for indicating AI-written text
What Losing Everything Taught Me About Backing Up | 2 | 1 | [
{
"comment_id": "6591008",
"author": "Info",
"timestamp": "2023-02-03T17:37:31",
"content": "Info: the download link is referring to episode 202.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6591092",
"author": "Tom Nardi",
"timestamp": "20... | 1,760,372,409.910384 | ||
https://hackaday.com/2023/02/03/mcp23017-went-through-shortage-hell-lost-two-inputs/ | MCP23017 Went Through Shortage Hell, Lost Two Inputs | Arya Voronova | [
"News",
"Parts"
] | [
"debugging hell",
"gpio expander",
"gpio extender",
"I have to redesign a product now",
"MCP23017",
"screaming"
] | The
MCP23017
, a 16-bit I2C GPIO expander, has always been a tasty chip. With 16 GPIOs addressable over I2C, proper push/pull outputs, software-enabled pull-ups, eight addresses, maskable interrupts for all pins, and reasonably low price, there’s a reason it’s so popular. No doubt due in part to that popularity, it’s been consistently out of stock during the past year and a half, as those of us unlucky enough to rely on it in our projects will testify.
Now, the chip is back in stock, with 23,000 of them to go around on Mouser alone, but there’s a catch. Apparently, the lengthy out-of-stock period has taken a heavy toll on the IC. Whether it’s the recession or perhaps the gas shortages, the gist is — the MCP23017 now a 14/16-bit expander, with two of the pins (GPA7 and GPB7)
losing their input capabilities
. The chips look the same, are called the same, and act mostly the same — if you don’t download the latest version of the datasheet (Revision D), you’d never know that there’s been a change. This kind of update is bound to cause a special kind of a debugging evening for a hobbyist, and makes the chip way less suitable for quite a few applications.
It’s baffling to think about such a change happening nearly 20 years after the chip was initially released, and we wonder what could have caused it. This applies to the I2C version specifically — the SPI counterpart, MCP23S17, stays unaffected. Perhaps,
using a microcontroller
or
shift registers
for your GPIO expansion isn’t as unattractive of an option after all. Microcontroller GPIO errata are at least expected to happen, and shift registers seem to have stayed the same since the dawn of time.
The reasons for MCP23017 silicon getting cut in such a way, we might never know. At least now, hopefully, this change will be less of a bitter surprise to those of us happy to just see the chip back in stock — and for hackers who have already restocked their MCP23017 hoards, may your shelved boards magically turn out to have a compatible pinout. | 68 | 26 | [
{
"comment_id": "6590916",
"author": "daveboltman",
"timestamp": "2023-02-03T16:09:24",
"content": "Eish! Why not give it a slightly different part number to distinguish it 🤦🏽♀️",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6590924",
"author": "W... | 1,760,372,410.393783 | ||
https://hackaday.com/2023/02/03/this-week-in-security-github-google-and-realtek/ | This Week In Security: Github, Google, And Realtek | Jonathan Bennett | [
"Hackaday Columns",
"News",
"Security Hacks"
] | [
"Chaotic Good",
"ipod",
"This Week in Security"
] | GitHub Desktop may have stopped working for you yesterday, Febuary 2nd. The reason was
an unauthorized access to some decidedly non-public repositories.
The most serious bit of information that escaped was code signing certificates, notably used for GitHub Desktop and Atom. Those certificates were password protected, so it’s unlikely they’ve been abused yet. Even so, Github is taking the proper steps of revoking those certificates.
The only active certificate that was revoked was used for signing the Mac releases of GitHub Desktop, so quite a few older versions of that software is no longer easily installed. If nothing else, it’s a reminder that even a project with a well run security team can have problems.
Sh1mmer-ing Chromebooks
There’s a new, clever attack on the Chromebook, specifically with the goal of
unenrolling the device from an educational organization
. And the “vulnerability” is a documented feature, the
RMA Shim
. That’s a special boot loader target that contains a valid signature, but allows the booting of other code, intended for troubleshooting and fixing devices in a repair center. Quite a few of those images have leaked, and Sh1mmer combines the appropriate image with a boot menu with some interesting options.
The first is unenrolling, so the device will act like a privately owned computer. This gets rid of content blocks and allows removing extensions. But wait, there’s more. Like rooting the device, a raw Bash terminal, and re-enabling developer mode. Now, as far as we can tell, this doesn’t *directly* break device encryption, but it’s likely that the RMA shim could be abused to tamper with the device’s filesystem. Meaning that the leak of a bunch of signed shims is a big problem for device security. If you use a Chromebook, it might be time to do some research on whether that model’s shim has been leaked.
Google Fi Fouled
Google Fi
customers have received notice of a breach
, in which some bits of customer data was leaked. The timing suggests that it could be related to the T-mobile breach about the same time. There’s more worrying element of this, at least one user seems to have been
the victim of a SIM swap attack
, pulled off as a result of the breach. Just a reminder, that SMS as a two factor authentication method is a terrible idea.
Realtek
There’s a big
ongoing campaign against Realtek-based devices
, and it’s because of CVE-2021-35394, a vulnerability in the Realtek Jungle SDK. Buckle up, this one has been known to lead to double-facepalms.
Back in 2015, a handful of
vulnerabilities were found and disclosed in D-Link and TRENDnet devices
. One of those was the UDPServer process, which seems to be a debugging interface. It listens on UDP port 9034, and just executes whatever commands are received. Totally unauthenticated. And on some devices, this process starts automatically. Oof.
This was reported in 2015, and
Realtek fixed it
. Observe:
if(!memcmp(buf, "orf", 3)){
strcat(buf, " > /tmp/MP.txt");
system(buf);
}
Yes, this is the solution they went with. Make sure the command string starts with
orf
, then redirect the output to a temp file. So secure. And now, someone is spamming port 9034 all across the internet, with
orf;malicious_command
. Shodan shows 80 different models on the Internet with this port open, and it’s possible even more won’t normally start the vulnerable service, but can be launched via an unauthenticated web endpoint, reachable if the device is configured to allow remote management. It speaks badly of Realtek to fumble a fix this badly, and even worse of vendors to have left this service in place. Patches are available for many of the affected devices.
Hacking your Ipod With wInd3x
[Serge Bazanski] found a new hobby to ride out Covid, and he’s finally ready to
share it with the world
. Hacking ancient iPods. The goal here is to crack open the platform, get a Linux kernel booting, and then finally engaging in that most noble of pursuits, running Doom on unexpected hardware.
But even in 2008, the iPod Nano 4G was doing a sort of secure boot, and was designed to not load arbitrary boot images. The bootloader will only load properly signed images, and the signing key never leaked. But that’s only a foolproof system so long as there’s not a big bug in the boot sequence that bypasses the security.
One of the tricks the iPod has under its metaphorical hat is to boot off USB for recovery, using Device Firmware Update (DFU). The implication is that the bootloader has to have a USB stack to pull this trick off, and that’s a good place to look for a vulnerability. And there’s a pretty nifty one, where data provided in the USB setup packet is used to index another array, without any sanity checks.
This just happens to be a function pointer lookup, and code execution jumps to the lookup result. Send something bogus, and it crashes the device. Massage the program state correctly, and execution jumps to a bit of code that works as a “trampoline”, bouncing execution back to … *wait-for-it* … The beginning of the USB packet that triggered the vulnerability.
[Serge] is proud of this part, and rightfully so. His exploit is a polyglot — it’s both a valid USB packet, and valid ARM code. It works on the Nano 4G, but he really wanted to take a crack at the 5G, which doesn’t even have boot ROM dumps available. The vulnerability worked, but the memory layout was different enough that the exploit would need re-engineered. The first task was trying to find that trampoline code, and brute-forcing the possible locations led to an interesting finding. One memory location resulted in a device restart when triggered. Time to throw the polyglot packet at it and see what happened. It worked, and he had code execution, but blind execution with no map. He would need the rest of the memory layout to do something useful.
He could make the device do something, at least. Jumping code execution to memory location 0 did a reboot. And triggering an infinite loop made it hang. So, just manually leak memory layout information one bit at a time. That’s a lot of dedication just to run Doom on an iPod. And the work is still in progress, but it looks like the iPod nano Gen5 finally has a booting Linux kernel. Bravo!
PlugX
USB malware still lives
. It’s thankfully not as bad as the old days, when Windows would actually autorun a binary as soon as the USB drive was plugged in to the computer. But some new tricks make for a pretty effective trap for the insufficiently wary.
The core trick is that folder names using the Unicode
00A0
character, non-breaking space, don’t render correctly in Windows Explorer, and the folders are not displayed at all as a result. An infected USB drive contains one of these invisible folders, as well as a shortcut bearing the same name as the drive. That shortcut points to a legitimate copy of the
x32dbg.exe
debugger binary, in the hidden directory, but also lurking there is a malicious
x32bridge.dll
file.
A quirk of the Windows library loading procedure is that the local directory will be checked first, even if the DLL exists in a system directory. And since DLLs aren’t signed like executables are, this DLL side loading has become a popular technique for running malware without any warning prompts. In the case of PlugX, it runs the payload, and then opens another hidden folder that serves as the fake root of the drive. All your expected files are there. And if you’re not paying attention, the extra step of launching the shortcut would be easy enough to overlook.
Bits and Bytes
The new Meta Account Center
had no rate limiting for SMS verification codes
, until [Gtm Mänôz] discovered and reported the issue. This allowed an interesting attack, where you could add a phone number belonging to another account, and by brute-forcing the six digit code, the number would be unlinked from the legitimate Facebook or Instagram account. If it was being used for 2FA, that security feature would simply be turned off on that account. The issue was fixed, and he earned a nice $27,200 for the find.
An international effort managed to
take down the infrastructure behind Hive Ransomware
. Law enforcement was able to compromise Hive servers several months ago, and ran a scam on the scammers, quietly handing out decryption keys to victims. In time, physical servers were located, in Los Angeles of all places, and the scheme shut down. Unfortunately there have yet to be any arrests announced as part of the operation.
Grey Hat really doesn’t do [Shashwat Kumar] justice.
This hack is definitely a Chaotic Good action
. After learning about a scammy free points offer, he discovered a malicious app that collected credit card information, and copied incoming SMS messages to a remote server. On that server, he found a dashboard with a SQL injection flaw. Upon confirming that this was indeed a malicious scam, the natural course of action was to abuse another SQL injection flaw to wipe the database of data. And then, change the app’s welcome message to warn users that it was malicious. Technically illegal, but obviously for the greater good. Huzzah! | 4 | 3 | [
{
"comment_id": "6590973",
"author": "Jay",
"timestamp": "2023-02-03T16:59:35",
"content": "> The most serious bit of information that escaped was code signing certificatesPlease don’t do this. Certificates, be they code signing certificates or otherwise, are not secret. There’s no harm in them ge... | 1,760,372,409.988569 | ||
https://hackaday.com/2023/02/03/end-of-an-automation-era-as-twitter-closes-its-doors-to-free-api-access/ | End Of An Automation Era As Twitter Closes Its Doors To Free API Access | Jenny List | [
"internet hacks",
"News"
] | [
"api",
"bot",
"mastodon",
"twitter"
] | Over the last few months since Elon Musk bought Twitter there has been a lot of comment and reaction, but not much with relevance to Hackaday readers. Today though that has changed, with an announcement from the company that
as of February 9th they will end their free API tier
. It’s of relevance here because Twitter has become one of those glue items for connected projects and has appeared in many featured works on this site. A week’s notice of a service termination is exceptionally short, so expect to see a lot of the Twitter bots you follow disappearing.
Twitter bot owners have the option of paying to continue with Twitter, or rebuilding their service to use a Mastodon instance such as
botsin.space
. If the fediverse is new to you, then
the web is not short of tutorials on how to do this
.
We feel that Twitter will be a poorer place without some of the creative, funny, or interesting bots which have enriched our lives over the years, and we hope that the spam bots don’t remain by paying for API access. We can’t help feeling that this is a misguided step though, because when content is the hook to bring in the users who are the product, throwing out an entire category of content seems short-sighted. We’re not so sure about it as a move towards profitability either, because the payback from a successful social media company is never profit but influence. In short: social media companies don’t make money but the conversation itself, and that can sometimes be worth more than money if you can avoid making a mess of it.
If the bots from our field depart for Mastodon, we look forward to seeing whether the new platform offers any new possibilities. Meanwhile if your projects don’t Toot yet,
find out how an ESP32 can do it
.
Header: D J Shin,
CC BY-SA 3.0
. | 40 | 14 | [
{
"comment_id": "6590734",
"author": "BT",
"timestamp": "2023-02-03T12:04:10",
"content": "“we hope that the spam bots don’t remain by paying for API access”Oh, they will.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6590737",
"author": "jpa",
... | 1,760,372,410.47118 | ||
https://hackaday.com/2023/02/03/the-struggle-of-keeping-a-1950s-candlepin-bowling-system-working/ | The Struggle Of Keeping A 1950s Candlepin Bowling System Working | Maya Posch | [
"News"
] | [
"bowling",
"candlepin bowling"
] | When we hear the term ‘bowling’, most of us think of what is known as ten-pin bowling, yet this is only one of the many variations. Candlepin bowling — so called because of the distinctive pin shape — has been around since 1880, yet is mostly played within the US New England and Canadian Maritime provinces. Because of how relatively uncommon it is, candlepin bowling alleys such as the one that [Autumn Mowery]’s family runs is
struggling to keep the system working
, much of it due to a lack of spare parts.
On
[Autumn]’s YouTube
channel she goes through many of the behind the scene details at the Ellsworth, Maine-based
bowling alley
, the repairs and the scavenging of spare parts from the sacrificial bowling lanes that are used to keep the other lanes going for as long as possible. With the mechanics of the installed
candlepin bowling
system dating back to the 1940s and having been use constantly since the 1950s, it’s an every day struggle to keep the system from breaking down, with no spare parts available for sale.
Although the financially responsible approach might be to give up on the system and have a readily available tenpin bowling system installed instead, there’s a
lot more to this form of bowling
than the difference in pin shape. Differences include the much stricter rules, the use of a smaller ball without finger holes, lower chance of hitting a pin, and so on. This, along with the historical significance of the sport and this particular system would make it appear to be something that’s right up the (bowling) alley of our audience.
How’d you keep a 1950s-era bowling system up and running?
Thanks to [Tara Calishain] for the tip! | 45 | 19 | [
{
"comment_id": "6590659",
"author": "Andrew",
"timestamp": "2023-02-03T09:53:46",
"content": "3D printing and desktop CNC. Every part that breaks can be examined, measured, documented, and re-made on a small scale, now that the original factory is gone. I assert.They could be remanufactured by hand... | 1,760,372,410.633616 | ||
https://hackaday.com/2023/02/02/a-disposable-dumper-for-rom-chips-with-a-pi-pico/ | A Disposable Dumper For ROM Chips With A Pi Pico | Arya Voronova | [
"Raspberry Pi",
"Tool Hacks"
] | [
"Raspberry Pi Pico",
"ROM dump",
"rom dumping",
"rp2040"
] | ROM dumping is vital for preserving old hardware, and we’ve seen many hacks dedicated to letting someone dump a ROM and send its contents to some hacker stuck with a piece of technology that lost its firmware. However, that requires ROM dumping tools of some kind, and it’s often that the lucky ROM-equipped hacker doesn’t own such tools. Now, you could mail the chip to someone else, but postal services in many countries are known to be UDP-like — lossy and without delivery guarantees. The risk of leaving both hackers without a ROM chip is quite real, so, instead of mailing ROM chips or expensive devices around, [Amen] proposes
a cheap and disposable flash dumping tool
that you could mail instead.
The ROMs in question are 24-pin 2332 and 2364 chips, which run at 5 V and can easily be read with any microcontroller. Thus, his concept is a very simple board, with a Pi Pico and flash chip socket on it, as well as some resistors. Those are used to provide rudimentary GPIO over-voltage protection, since the RP2040 runs its GPIOs at 3.3 V. All the magic is in the software – the tool can both write the chip contents in the RP2040’s internal memory, as well as dump it over USB to the computer.
Everything is open-source
– if you ever need to dump a rare chip on the other side of the world, modify the design to your liking, order a few copies and then mail them to the hacker involved – losing such a package is way less significant than losing a ROM chip with last-of-its-kind firmware on it.
Old ROM chips are dying out, causing whole generations of hardware, like
synths,
to fade away – with tools like this one, you can lend a hand in
preserving the legacy
of many an industry and hobby, and many hackers do. Looking to learn about the basics of parallel flash dumping?
This post from 2012
will be a good start, and then check out
a more recent venture
to learn how things are done with more recent parts. | 26 | 6 | [
{
"comment_id": "6590649",
"author": "TinWhisker",
"timestamp": "2023-02-03T09:43:44",
"content": "I appreciate the ‘disposable’ nature being in relation to the mailing systems worldwide and potential for loss, rather than use-it-bin-it.",
"parent_id": null,
"depth": 1,
"replies": []
}... | 1,760,372,410.532482 | ||
https://hackaday.com/2023/02/02/brass-hardware-makes-for-pretty-potentiometer-knobs/ | Brass Hardware Makes For Pretty Potentiometer Knobs | Lewin Day | [
"Parts"
] | [
"3d printing",
"knobs",
"potentiometer"
] | Knobs and switches can make or break the aesthetic and tactile appeal of a project. Fine hi-fi hardware goes hard on these details, while cheap knock-off guitar pedals often go the other way. If you’re looking for a unique, cheap, and compelling solution for potentiometer knobs, you might like to consider
using converted brass hardware for the job.
Gorgeous, no?
The idea comes from [Kevin Jordan], who realized that some simple 3D printed parts would enable him to repurpose brass hardware for use with common split-shaft potentiometers. He grabbed a bunch of brass flare caps intended for use with gas piping, and got to work.
The result is the simple 3D printed cap converter. It has a threaded outer portion, which screws neatly inside a brass flare cap. Inside, it features a hole to mate to the potentiometer shaft. While this could be done with a spline, it also works with a simple hole since the plastic is soft enough to simply push the potentiometer shaft into.
The flare caps look great when pressed into service as knobs. [Kevin] uses them on a tennis racket guitar he built, and the brass knobs beautifully set off against the natural wood finishes of the build. If you’re looking for some unique adornments for your own projects, you might like to experiment with this concept yourself! Alternatively,
you can try making your own knobs from scratch
. | 18 | 12 | [
{
"comment_id": "6590463",
"author": "SayWhat?",
"timestamp": "2023-02-03T04:17:33",
"content": "They look like someone found some junk and pressed them into service instead of getting nice knobs.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6591741",
... | 1,760,372,410.748656 | ||
https://hackaday.com/2023/02/02/building-an-all-in-one-desktop-out-of-framework-parts/ | Building An All-in-One Desktop Out Of Framework Parts | Arya Voronova | [
"laptops hacks"
] | [
"framework",
"Framework laptop"
] | The Framework laptop prides itself on having reusable parts, and hackers all around routinely challenge the claims by building projects reusing them. Yet again, [whatthefilament] puts the Framework hardware to the test, by taking all the laptop internals
and building an AiO
(All-in-One) desktop computer with it. Hot on the heels of
his Framework tablet project
we covered a few months ago, this desktop reuses as much as possible – the mainboard, the display and the expansion cards in particular, and even one of the hinges is reused for adjusting the monitor’s angle.
Of course,
this build
required a custom case – and [whatthefilament]’s design is fully 3D-printed, with
STLs
and
assembly instructions
available for anyone interested. Parts of the desktop are held by magnets for ease of assembly and maintenance, with a few parts requiring screws held in by heat-set inserts. Complete with a webcam, speakers and even a WiFi card, all it needs for completeness is an external keyboard&mouse combo, making for a sleek desktop that anyone in possession of a few Framework parts can build.
Laptop-to-desktop builds are nice – take
the X-PC project,
starting with a pile of school laptops and rebuilding them into colourful and sturdy desktops for classroom use. We’ve seen
quite a few fancy Framework projects
already, and that’s because they
provided motherboards to hackers
for specifically project purposes, kickstarting a fair few creations to grace our pages. Other hacker-friendly laptops didn’t lag behind, either – for instance, here’s the hacker favourite, Novena,
getting the desktop treatment. | 10 | 4 | [
{
"comment_id": "6590430",
"author": "pictographer",
"timestamp": "2023-02-03T03:37:40",
"content": "Very slick! Great work and pictures.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6590599",
"author": "sampleusername",
"timestamp": "2023-02-03T08:2... | 1,760,372,410.799218 | ||
https://hackaday.com/2023/02/02/build-a-circuit-sculpture-style-vu-meter-for-music/ | Build A Circuit Sculpture-Style VU Meter For Music | Lewin Day | [
"LED Hacks",
"Musical Hacks"
] | [
"led",
"level meter",
"visualization",
"VU meter"
] | One of the coolest things any sound system can have is some kind of musical visualization. Thumping level meters that pump with the volume are a great example, and were particularly popular in the 1980s. Now, you can build a rainbow set with great response,
thanks to this guide from [Invexlab World].
The build relies on a very simple circuit that relies entirely on analog electronics in lieu of the usual digital signal analysis usually employed for the job. It’s a barebones design that’s assembled using a jig to create the attractive circuit sculpture structure. It uses simple colored LEDs, assembled in a line with red at the bottom, stepping through yellow and green, to blue and white at the top. A series of diodes is placed in series, with the sound level having to exceed the voltage drop of successive diodes to light the higher LEDs. It’s intended to be directly connected to a speaker’s audio input, and thus likely does load down the amplifier output slightly.
The result is an attractive rainbow VU meter display that would look great as a part of any old-school stereo setup. We can imagine it would look even better if it was
cast in clear resin.
Video after the break. | 19 | 8 | [
{
"comment_id": "6590177",
"author": "mike jones",
"timestamp": "2023-02-02T22:21:45",
"content": "Would the scaling change with volume level? Good encouragement to turn it up to 11 if so.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6591150",
"aut... | 1,760,372,410.854444 | ||
https://hackaday.com/2023/02/02/audio-playback-toy-for-dsp-adventures/ | Audio Playback Toy For DSP Adventures | Bryan Cockfield | [
"Microcontrollers"
] | [
"adc",
"audio",
"AVR",
"AVR128DA28",
"dac",
"interrupt",
"memory",
"microcontroller",
"op-amp",
"speed"
] | The declining costs of single-board computers has made serious computing power available for even the most trivial of tasks. It’s easy enough to slap a Raspberry Pi onto almost anything for nearly the same cost as a powerful 32-bit microcontroller platform, but this takes some of the fun out of projects for a few of us. Looking to get into the weeds can be a challenge as well, as [Michal Zalewski] demonstrates in
this audio playback device he built from a simple 8-bit microcontroller
.
The small toy takes audio input from a microphone through an op-amp and feeds this signal to an ADC within the
AVR128DA28
microcontroller. The data is then stored on a separate memory chip ready to be played back through another op-amp paired with a speaker. This is where being familiar with the inner workings of the microcontroller comes in handy. By manipulating the interrupt routines in specific ways, the audio stored in memory can be played back at various speeds.
[Michal] intended this build to be a toy for one of his younger relatives, and for the price of a few ICs and buttons it does a pretty good job of turning a regular voice into a chipmunk voice like some
commercial children’s toys
some of us might remember. If the design aesthetics of this gadget look familiar, you may be thinking of his
minimalist gaming device which we recently featured
. | 1 | 1 | [
{
"comment_id": "6590063",
"author": "Stephanie Seven",
"timestamp": "2023-02-02T19:48:01",
"content": "Very clever indeed, thank you for sharing this with us.👍",
"parent_id": null,
"depth": 1,
"replies": []
}
] | 1,760,372,410.891371 | ||
https://hackaday.com/2023/02/02/now-chatgpt-can-make-breakfast-for-me/ | Now ChatGPT Can Make Breakfast For Me | Jenny List | [
"Artificial Intelligence",
"Current Events",
"Featured",
"home hacks",
"Rants",
"Slider"
] | [
"ai",
"ChatGPT",
"openscad"
] | The world is abuzz with tales of the ChatGPT AI chatbot, and how it can do everything, except perhaps make the tea. It seems it can write code, which is pretty cool, so if it can’t make the tea as such, can it make the things I need to make some tea? I woke up this morning, and after lying in bed checking Hackaday I wandered downstairs to find some breakfast. But disaster! Some burglars had broken in and stolen all my kitchen utensils! All I have is my 3D printer and laptop, which curiously have little value to thieves compared to a set of slightly chipped crockery. What am I to do!
Never Come Between A Hackaday Writer And Her Breakfast!
OK Jenny, think rationally. They’ve taken the kettle, but I’ve got OpenSCAD and ChatGPT. Those dastardly miscreants won’t come between me and my breakfast, I’m made of sterner stuff! Into the prompt goes the following query:
My shiny new mug, kettle, and teaspoon.
The result was promising, it wrote
an OpenSCAD module
right in front of me. It looks valid, so into OpenSCAD it went. A nice tall cylindrical kettle, with a … er… lid. That should print no with problems, and I’ll be boiling the water for my morning cuppa in no time!
But I need a teaspoon and a mug too, I’d better do the same for those. On with the same queries, and duly code for a
mug
and a
teaspoon
were created. Fortunately the robbers haven’t taken the coffee, the sink, or the cooker, so I’m soon enjoying a reviving cup of morning coffee. This new technique for generating utensils automatically as I need them is straight out of
Star Trek
, I think I’ll never buy a piece of kitchenware again!
Having a bit of caffeine in my system, I felt it was time for a spot of Proper English Breakfast. Bacon and eggs are still in the fridge and the bread is on the shelf, so here goes, back to ChatGPT. I need a frying pan, a spatula, a plate, a knife, and a fork. This is going to be
such
a good breakfast!
Out come OpenSCAD models for a
frying pan
and
spatula
. The pan is maybe more of a griddle than a pan, but no AI coding chatbot is perfect, is it. The spatula is a two-piece affair with a chunky handle, very modern and contemporary styling. I like it. The
plate
boldly eschews a bottom and instead corrals the food with an angular edge, while the
knife and fork
follow the same chunky styling as the spatula.
I’m soon tucking into a fine breakfast thanks to my AI-generated utensils, ready for my day.
Perhaps Breakfasts In The Future Won’t Be Quite Like This
Of course, some of you may have noticed something a little
avant-garde
about my ChatGPT creations. Some might say they prioritise form over function to the extent of losing the latter, and I’d say yes, but it’s made a good joke pursuing them for the last few paragraphs.
I’ve put all the stuff in a GitHub repository
for you to look at if you want, and it’s soon pretty obvious that while ChatGPT has mastered a few basic OpenSCAD features such as union, translate, and difference of cylinders, it’s got no idea what a kitchen utensil looks like.
Of course, ChatGPT isn’t an image-trained AI in the way that Dall-E is, so one might argue that it shouldn’t be expected to have any idea what a mug looks like. Perhaps I should ask it, with the query “Tell me what a mug looks like”.
A mug is typically a cylindrical shaped container with a handle, used for drinking hot or cold beverages such as tea, coffee, hot chocolate, etc. The top of the mug usually has a slightly flared or rounded shape to make it easier to drink from, and the bottom of the mug is flat so that it can be placed on a surface. The handle is attached to the side of the mug, usually near the top, and is used to hold the mug securely while drinking. The material of the mug can vary, but mugs are commonly made from ceramic, glass, metal, or plastic. Some mugs have designs or patterns on them, and some have logos or images printed on them. Mugs can come in various sizes, from small espresso cups to large travel mugs, and the design and features of mugs can also vary widely.
So much for the “ignorance of mugs” defence, from that reply it seems to have a pretty good handle on muggishness. But we’re told an AI is only as good as its training, so perhaps the real point here is that it has several descriptions of mugs in its makeup, but no tutorials on how to generate a model from a text description. At last, something that requires a bit of meat-based intelligence!
We’re in the middle of an AI hype storm, and it’s right to push the boundaries of all these tools because they have within them some remarkable capabilities. Next time you meet someone who’s drunk just a little too much of the Kool-Aid though, ask them this question. Can it help you make breakfast with no utensils?
Header image: Joadl,
CC BY-SA 3.0 AT. | 62 | 19 | [
{
"comment_id": "6590008",
"author": "Kaaaaaaaaaaaaaaaaang",
"timestamp": "2023-02-02T18:25:42",
"content": "Be glad about ChatGPT trying to generate a model; with my luck I bet If I request an openscad model of a mug, the only answer I would get is “DON’T MUG ME!”",
"parent_id": null,
"dept... | 1,760,372,411.952805 | ||
https://hackaday.com/2023/02/02/lets-make-scpi-more-helpful/ | Let’s Make SCPI More Helpful | Arya Voronova | [
"Software Hacks",
"Tool Hacks"
] | [
"libscpi",
"scpi",
"self-documenting interface",
"Technical documentation"
] | The SCPI (Standards Command for Programmable Instruments) protocol is exceptionally popular in lab and workspace tools, letting you configure and fetch data from oscilloscopes and lab scales alike in a standardized way. However, when interfacing with a SCPI device, you need to use a programming guide document if you want to know the commands for any of the inevitably extended features; essentially, SCPI isn’t as human-friendly as you might want. [MisterHW] argues that SCPI could use more discoverability by
proposing a HELP? command.
This proposal is so intuitive, it makes you wonder why it isn’t in the base spec. It adds a built-in command that provides information on other commands. Internally, the description is just an extra string parameter that you add to your command definition code, and you can use it to describe the parameter types and ranges it takes. The output is both human-readable and machine-parseable, and as it’s stored within your code, it’s way quicker to update the description string than it is to re-release programming guides. Which are themselves prone to being outdated as-is, so decreasing reliance on them is a win-win.
The proposal makes a lot of sense, and [MisterHW] is willing to back it up with
a pull request to the most popular SCPI library
,
libscpi
. Whenever the pull request finally goes through, you will have the option to easily add the HELP? command support to whatever SCPI-connected device you might have brewing.
While the old devices will eventually fade, SCPI is not about to die out – hackers keep building devices with SCPI as the communication protocol, as the spec is quite powerful. For instance, here’s this fancy
temperature logger,
or this
Source Measurement Unit
– both of them use SCPI for hacker-to-device data transfer, and it’s likely to be
libscpi
under the hood. Ever wondered what SCPI is all about?
Check out our overview! | 9 | 3 | [
{
"comment_id": "6589959",
"author": "cliff claven",
"timestamp": "2023-02-02T17:17:34",
"content": "“SCPI is not about to die out – hackers keep building devices with SCPI as..”Huh? Where on earth did this come from? Was there any implication that SCPI is about to die off? In what way is the hacker... | 1,760,372,411.65618 | ||
https://hackaday.com/2023/02/02/chinas-new-100-mph-train-runs-on-hydrogen-and-supercaps/ | China’s New 100 MPH Train Runs On Hydrogen And Supercaps | Lewin Day | [
"green hacks",
"Hackaday Columns",
"Slider",
"Transportation Hacks"
] | [
"fuel cell",
"hydrogen",
"hydrogen fuel cell",
"railway",
"train",
"trains",
"transport"
] | Electric cars are very much
en vogue
right now, as the world tries to clean up on emissions and transition to a more sustainable future. However, these vehicles require huge batteries as it is. For heavier-duty applications like trucks and trains, batteries simply won’t cut the mustard.
Normally, the solution for electrifying railways is to simply string up some wires and call it a day. China is trying an alternative solution, though,
in the form of a hydrogen-powered train full of supercapacitors.
Hydrogen Rides The Rails
CRRC is a Chinese state-owned company in the rolling stock business. It’s at the forefront of rail projects in the country, and has invested heavily in conventional high-speed rail
and even mag-lev technologies.
It’s latest hydrogen-powered project isn’t built for speed, with a cited top speed of just 160 km/h, along with a range of 600 km on a full tank. That might not be quick by modern rail standards, but it’s enough to make it the fastest hydrogen-powered train in the world. It’s also equipped with self-technology for automatic operations without a driver or crew. The train operates as a four-car consist, and is charged with passenger duty.
The train relies on fuel cells to make electricity from its hydrogen fuel.
Fuel cells
are generally considered an emissions-neutral power source, as their sole output is water. Of course, sourcing hydrogen in a clean fashion
can still be difficult
, but fuel cells themselves don’t directly contribute harmful emissions to the atmosphere.
It’s impossible to deliver a fuel cell transport project without plastering it with hydrogen-themed decals.
CRRC
Notably, the train pairs the hydrogen fuel cells with a bank of supercapacitors. Fuel cells on their own are not great at responding to high instantaneous power demands. A design could obviously be built with a larger bank of fuel cells to serve peak power demands, but this would be expensive and inefficient.
Instead, supercapacitors are used as a power bank to cover off any spikes in power demand. The supercapacitors can be charged slowly over time by the fuel cells, and then deliver high power when it is needed most. The other benefit of adding supercapacitors is that they can store energy captured by regenerative braking. This can be particularly beneficial when a train is travelling down a long grade. That gravitational potential energy can be captured and stored as electrical energy for later use.
The CRRC effort compares ably with other hydrogen-powered rail projects overseas. German railways already operate
a fleet of 14 Alstom trains
on hydrogen fuel. The Alstom Coradia iLint passenger trains entered a pre-service trial back in 2018, and have since entered mainstream public service. They have a lower top speed, at just 140 km/h, though this is more than enough for the usual 80-120 km/h travel speeds on the EVB rail network. The German trains do offer longer range, with 64 on-board hydrogen tanks able to propel the trains up to 1,000 km. A single fill of the hydrogen tanks is enough for a full day’s service along typical routes. The new trains replaced a fleet of 15 diesel units, reportedly saving 1.6 million liters of diesel and 4,400 tonnes of CO2 annually. Alstom plans to ship more hydrogen train sets to other German cities, as well as France and Italy in future.
Germany already has 14 Coradia iLint hydrogen fuel cell trains, operating regular passenger services. Alstom
We weren’t kidding about the decals. Alstom.
Research and development is also ongoing in the freight arena.
An Australian project
is exploring whether freight trains in remote mining areas could run on hydrogen instead of diesel. These long routes are unelectrified, and are currently plied by conventional diesel-powered locomotives. Freight trains tend to require much beefier locomotives, and so the challenge is somewhat greater than producing a hydrogen-powered passenger train. However, if this heavy haulage could run on hydrogen, there’s huge scope to cut emissions to a drastic degree.
Hydrogen fuel cells may seem like a curious choice for trains. Spending resources to create hydrogen, only to turn it back into electricity, is obviously less efficient than simply powering trains with electricity directly. The many overhead-wire and third-rail electric railways around the world indicate that this is a solved technology.
However, in certain circumstances, fuel cell trains do make sense. The trains can run on conventional, non-electrified railways in place of diesel trains, but without the usual greenhouse gas or particulate emissions. Employing a fuel-cell train eliminates the need to install overhead wires on many thousands of kilometers of track. This cuts up-front infrastructure expenditure. However, the trains do come with some expenses of their own. Maintenance of fuel cell trains is likely to be higher than that of conventional electric trains. There is also a need to establish hydrogen refuelling infrastructure along the train’s route. With a limited number of stops, it’s less onerous than providing hydrogen stations for road vehicles, but the infrastructure is still far from free. There’s also the need to provide hydrogen to the various refuelling stations throughout the network, whether via tanker trucks, tanker trains, or pipeline networks.
Fuel cell trains do offer a unique opportunity to cut emissions from railway transport. To achieve this properly, several factors must be considered. The trains should serve on routes currently inaccessible to regular electric trains, and must be fueled with hydrogen sourced as cleanly as possible. The entire supply chain of that hydrogen should also be taken into account, so as not to generate excessive emissions hauling it from production facilities to refueling stations. Costs should also be weighed up as to whether it would be cheaper, easier, and cleaner to simply install a caternary electric supply instead. | 83 | 18 | [
{
"comment_id": "6589866",
"author": "M",
"timestamp": "2023-02-02T15:28:58",
"content": "one of the leading ways to make hydrogen is through natural gas steam reforming. don’t automatically assume hydrogen is carbon-free.",
"parent_id": null,
"depth": 1,
"replies": [
{
"co... | 1,760,372,412.078856 | ||
https://hackaday.com/2023/02/01/detecting-machine-generated-content-an-easier-task-for-machine-or-human/ | Detecting Machine-Generated Content: An Easier Task For Machine Or Human? | Maya Posch | [
"Current Events",
"Featured",
"Machine Learning",
"Original Art",
"Science",
"Slider"
] | [
"ai",
"ChatGPT",
"GPT",
"large language model"
] | In today’s world we are surrounded by various sources of written information, information which we generally assume to have been written by other humans. Whether this is in the form of books, blogs, news articles, forum posts, feedback on a product page or the discussions on social media and in comment sections, the assumption is that the text we’re reading has been written by another person. However, over the years this assumption has become ever more likely to be false, most recently due to large language models (LLMs) such as GPT-2 and GPT-3 that can churn out plausible paragraphs on just about any topic when requested.
This raises the question of whether we are we about to reach a point where we can no longer be reasonably certain that an online comment, a news article, or even entire books and film scripts weren’t churned out by an algorithm, or perhaps even where an online chat with a new sizzling match turns out to be just you getting it on with an unfeeling collection of code that was trained and tweaked for maximum engagement with customers. (Editor’s note: no, we’re not playing that game here.)
As such machine-generated content and interactions begin to play an ever bigger role, it raises both the question of how you can detect such generated content, as well as whether it matters that the content was generated by an algorithm instead of by a human being.
Tedium Versus Malice
In George Orwell’s
Nineteen Eighty-Four,
Winston Smith describes a department within the Ministry of Truth called the Fiction Department, where machines are constantly churning out freshly generated novels based around certain themes. Meanwhile in the Music Department, new music is being generated by another system called a versificator.
Yet as dystopian as this fictional world is, this machine-generated content is essentially harmless, as Winston remarks later in the book, when he observes a woman in the prole area of the city singing the latest ditty, adding her own emotional intensity to a love song that was spat out by an unfeeling, unthinking machine. This brings us to the most common use of machine-generated content, which many would argue is merely a form of automation.
The encompassing term here is ‘
automated journalism
‘, and has
been in use
with respected journalistic outlets like Reuters, AP and others for years now. The use cases here are simple and straightforward: these are systems that are configured to take in information on stock performance, on company quarterly reports, on sport match outcomes or those of local elections and churn out an article following a preset pattern. The obvious advantage is that rooms full of journalists tediously copying scores and performance metrics into article templates can be replaced by a computer algorithm.
In these cases, work that involves the journalistic or artistic equivalent of flipping burgers at a fast food joint is replaced by an algorithm that never gets bored or distracted, while the humans can do more intellectually challenging work. Few would argue that there is a problem with this kind of automation, as it basically does exactly what we were promised it would do.
Where things get shady is when it is used for nefarious purposes, such as to draw in search traffic with
machine-generated articles
that try to sell the reader something. Although this has recently led to
considerable outrage
in the case of CNET, the fact of the matter is that this is an incredibly profitable approach, so we may see more of it in the future. After all, a large language model can generate a whole stack of articles in the time it takes a human writer to put down a few paragraphs of text.
More of a grey zone is where it concerns assisting a human writer, which is becoming an issue in the world of scientific publishing, as
recently covered
by
The Guardian
, who themselves pulled a bit of a stunt in September of 2020 when they
published an article
that had been generated by the GPT-3 LLM. The caveat there was that it wasn’t the straight output from the LLM, but what a human editor had puzzled together from multiple outputs generated by GPT-3. This is rather indicative of how LLMs are generally used, and hints at some of their biggest weaknesses.
No Wrong Answers
At its core an LLM like
GPT-3
is a heavily interconnected database of values that was generated from input texts that form the training data set. In the case of GPT-3 this makes for a database (model) that’s about 800 GB in size. In order to search in this database, a query string is provided – generally as a question or leading phrase – which after processing forms the input to a curve fitting algorithm. Essentially this determines the probability of the input query being related to a section of the model.
Once a probable match has been found, output can be generated based on what is the most likely next connection within the model’s database. This allows for an LLM to find specific information within a large dataset and to create theoretically infinitely long texts. What it cannot do, however, is to determine whether the input query makes sense, or whether the output it generates makes logical sense. All the algorithm can determine is whether it follows the most likely course, with possibly some induced variation to mix up the output.
Something which is still regarded as an issue with LLM-generated texts is repetition, though this can be resolved with some tweaks that give the output a ‘memory’ to cut down on the number of times that a specific word is used. What is harder to resolve is the absolute confidence of LLM output, as it has no way to ascertain whether it’s just producing nonsense and will happily keep on babbling.
Yet despite this, when human subjects are subjected to GPT-3- and GPT-2-generated texts as in a
2021 study
by Elizabeth Clark et al., the likelihood of them recognizing texts generated by these LLMs – even after some training – doesn’t exceed 55%, making it roughly akin to pure chance. Just why is it that humans are so terrible at recognizing these LLM-generated texts, and can perhaps computers help us here?
Statistics Versus Intuition
(Credit: Gehrmann et al., 2019)
When a human being is asked whether a given text was created by a human or generated by a machine, they’re likely to essentially guess based on their own experiences, a ‘gut feeling’ and possibly a range of clues. In a
2019 paper
by Sebastian Gehrmann et al., a statistical approach to detecting machine-generated text is proposed, in addition to identifying a range of nefarious instances of auto-generated text. These include fake comments in opposition to US net neutrality and misleading reviews.
The statistical approach detailed by Gehrmann et al. is called
Giant Language model Test Room
(GLTR,
GitHub source
) involves analyzing a given text for its predictability. This is a characteristic that is often described by readers as ‘shallowness’ of a machine-generated text, in that it keeps waffling on for paragraphs without really saying much. With a tool like GLTR such a text would light up mostly green in the visual representation, as it uses a limited and predictable vocabulary.
In
a paper presented by Daphne Ippolito et al.
(PDF) at the 2020 meeting of the Association for Computational Linguistics, the various approaches to detecting machine-generated text are covered, along with the effectiveness of these methods used in isolation versus in a combined fashion. The top-k analysis approach used by GLTR is included in these methods, with the alternate approaches of nucleus sampling (top-p) and others also addressed.
Ultimately, in this study the human subjects scored a median of 74% when classifying GPT-2 texts, with the automated discriminator system generally scoring better. Of note is the study by
Ari Holtzman et al.
that is referenced in the conclusion, in which it is noted that human-written text generally has a cadence that dips in and out of a low probability zone. This not only makes what makes a text interesting to read, but also provides a clue to what makes text seem natural to a human reader.
With modern LLMs like GPT-3, an approach like the nucleus sampling proposed by Holtzman et al. is what provides the more natural cadence that would be expected from a text written by a human. Rather than picking from a top-k list of options, instead one selects from a dynamically resized pool of candidates: the probability mass. The resulting list of options, top-p, then provides a much richer output than with the top-k approach that was used with GPT-2 and kin.
What this also means is that in the automatic analysis of a text, multiple approaches must be considered. For the analysis by a human reader, the distinction between a top-k (GPT-2) and top-p (GPT-3) text would be stark, with the latter type likely to be identified as being written by a human.
Uncertain Times
It would thus seem that the answer to the question of whether a given text was generated by a human or not is a definitive ‘maybe’. Although statistical analysis can provide some hints as to the likelihood of a text having being generated by an LLM, ultimately the final judgement would have to be with a human, who can not only determine whether the text passes muster semantically and contextually, but also check the presumed source of a text for being genuine.
Naturally, there are plenty of situations where it may not matter who wrote a text, as long as the information in it is factually correct. Yet when there’s possibly nefarious intent, or the intent to deceive, it bears to practice due diligence. Even with auto-detecting algorithms in place, and with a trained and cautious user, the onus remains on the reader to cross-reference information and ascertain whether a statement made by a random account on social media might be genuine.
(Editor’s Note:
This post about OpenAI’s attempt to detect its own prose
came out between this article being written and published. Their results aren’t that great, and as with everything from “Open”AI, their methods aren’t publicly disclosed. You can try the classifier out, though.) | 41 | 12 | [
{
"comment_id": "6588979",
"author": "Clovis Fritzen",
"timestamp": "2023-02-01T18:07:18",
"content": "I h*ted automated customer service chat replies, now even more. We are automatizing what shouldn’t be.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "65890... | 1,760,372,411.75078 | ||
https://hackaday.com/2023/02/01/electronic-shoe-explores-alleged-chess-misbehavior/ | Electronic Shoe Explores Alleged Chess Misbehavior | Bryan Cockfield | [
"Games",
"Wearable Hacks"
] | [
"attiny",
"bluetooth",
"CHEATING",
"chess",
"insole",
"shoe",
"sole"
] | A few months ago, a scandal erupted in the chess world which led to some pretty wild speculation around a specific chess player. We won’t go into any of the details except to say that there is virtually no physical evidence of any method this player allegedly used to cheat in a specific in-person chess match. But [Teddy Warner] and partner [Jack Hollingsworth] were interested in at least providing a
proof-of-concept for how this cheating could have been done
, though, and came up with this device which signals a chess player through a shoe.
The compact device is small enough to fit in the sole of one of the player’s shoes, and is powered by an ATtiny412 microcontroller paired with a HC-06 Bluetooth module. The electronics are fitted into a 3D printed case along with a small battery which can then be placed into the sole of a shoe, allowing the wearer to feel the vibrations from a small offset-weight motor. With a second person behind a laptop and armed with a chess engine, the opponent’s moves can be fed into the computer and the appropriate response telegraphed through the shoe to the player.
While [Teddy] and [Jack] considers the prototype a success in demonstrating the ease at which a device like this could be used, and have made everything related to this build open source, this iteration did have a number of issues including that the motor buzzing was noticeable during play, and that his chess engine made some bizarre choices in the end game. It also requires the complicity of a second person,
which is something this other chess cheating machine does away with
. They also note that it’s unlikely that any chess players at the highest levels use devices like these, and that other chess experts have found no evidence of any wrongdoing in this specific scandal. | 20 | 7 | [
{
"comment_id": "6588922",
"author": "mrehorst",
"timestamp": "2023-02-01T17:06:07",
"content": "Thanks for ignoring the stupid vibrating butt plug “theory” that was so popular in the press.I think you’d have to be in the room to use a bluetooth based cheat. Do they allow a people with laptops runni... | 1,760,372,411.319981 | ||
https://hackaday.com/2023/02/01/the-radioactive-source-missing-in-australian-desert-has-been-found/ | The Radioactive Source Missing In Australian Desert Has Been Found | Lewin Day | [
"Current Events",
"Featured",
"News",
"Slider"
] | [
"cesium-137",
"radiation",
"radioactive source"
] | Nuclear material is relatively safe when used, stored, and managed properly. This generally applies to a broad range of situations, from nuclear medicine to nuclear power generation. Some may argue it’s impossible to use nuclear weapons safely. In any case, stringent rules exist to manage nuclear material for good reason.
Sometimes, though, things go wrong, mistakes are made, and that nuclear material ends up going AWOL. That’s the situation that faced authorities in Australia, as they scoured over a thousand kilometers of desert highway for a tiny missing radioactive source with the potential to cause serious harm. Thankfully,
authorities were able to track it down.
A Screw Loose
Authorities had to search a 1,400 km stretch of road between the mine site and Perth. Credit: EmergencyWA, screenshot
The situation concerned a tiny radioactive source, roughly 6 mm in diameter and 8 mm tall. The round silver pellet contains the radioactive isotope Cesium-137, and puts out harmful quantities of both gamma and beta radiation. The pellet was part of a gauge used for measuring the density of iron ore feed running through mining equipment.
The gauge itself had been transported from a Rio Tinto mining site in Western Australia on January 12, and had made a 1,400 km journey, ending up in Perth on January 16. The capsule was first reported as missing on January 25, when the gauge it was a part of was unpacked for inspection. The gauge was found broken, with a mounting bolt missing along with multiple screws. Authorities concluded that vibrations from the truck caused the screws and bolt to loosen, with the radioactive capsule then falling out of the gauge and off of the vehicle.
Government authority
Radiation Services WA
has released a statement on the incident. It notes that typically, radioactive sources of this type are usually protected in secure housings in equipment. They are intended to be safe in regards to corrosion and vibration, as well as being able to withstand drops from nine meters high, and even high temperatures of up to 800 °C for 30 minutes without danger. Transporting such materials also requires strict controls, including the use of trained personnel and meeting certain packaging requirements. The fact that the source was able to literally
fall off the back of a truck
suggests these controls were not met.
The Danger
The loss spawned an urgent hunt for the tiny radioactive source. Despite its diminutive size, the source does pose a significant health risk. According to authorities, the source’s original radioactivity was 18.5 GBq. At this level, a human would receive roughly 1.665 mSv/hr (milliSieverts per hour) standing at a distance of 1 meter from the source. This is equivalent to roughly 17 normal chest x-rays, or a year’s worth of background radiation in Australia. For further perspective, a 2 mSv dose increases cancer risk by 1 in 10,000.
Unfortunately, getting closer to the source greatly increases the harm. Getting within 1 cm of the capsule would deliver a dose rate of 16.65 Sv/hr (Sieverts per hour), a full 10,000 times higher thanks to the inverse square law – note the unit change. Picking up the source would increase the dose rate ever higher, on the order of 1,665 Sv/hr. The device is radioactive enough that holding it would cause serious damage to the tissues of the hand, including burns. (Editor’s note: If you want to learn a lot more about the biological specifics,
check out Dan’s awesome article
.)
Some radioactive sources are labelled with the phrase “Drop And Run,” and that action would certainly apply in this case. This tiny Cesium-137 source is far less radioactive than the Cobalt-60 sources this message usually applies to. However, it’s still radioactive enough that you don’t want to be anywhere near it.
Those numbers indicate the severe risk the source poses. If you spotted the tiny source from a distance, you could remain five meters away as recommended by authorities, and you would be relatively safe. Alternatively, if you picked up the source, or it perhaps became lodged in the tread of your shoe, you could be exposed at close range for a great deal of time. An exposure to a double-digit dose of Sieverts tends to be fatal in most cases, so the risk is extreme if it comes into contact with humans.
On the flipside, if the source remains in an isolated area, far from human contact, its impact may be minimal. The Cesium-137 itself is sealed in the capsule, and thus is unlikely to contaminate ground water sources or the soil itself. With a half-life of roughly 30 years, the source is expected to remain meaningfully radioactive for approximately 300 years or so. As the decades pass, though, it becomes less and less radioactive, posing a lower risk over time.
A Hot Needle in a Haystack
The capsule most likely went missing somewhere between the Gudai-Darri mine site operated by Rio Tinto, and Perth. The capsule is potentially still sitting somewhere along the desolate desert roads of Western Australia.
Credit:
Calistemon
,CC-BY-SA-4.0
Trying to find a tiny capsule smaller than a coin on 1,400 km of highway is a difficult task. It’s akin to trying to find the proverbial needle in the haystack, but much harder. Thankfully, though, tools existed to assist authorities in their search. The radiation output by the capsule can be detected at some range by radiation-detecting equipment. This means authorities didn’t just have to rely on keeping their eyes peeled. If they were able to get in the general vicinity of the object, their radiation detectors would help them track down its precise location.
Authorities used vehicles outfitted with radiation-detecting equipment. The vehicles made making slow passes up and down the highway at a speed of just 50 km/h. Travelling at the prevailing highway speed of 100 km/h would be too fast, as any spike caused by the capsule would probably be missed. Going slow and steady was key to finding the capsule.
Of course, there was a risk that the capsule is no longer directly on the highway route where it was lost. Weather or local animal life could have moved the capsule, potentially carrying it a great distance away. Alternatively, the capsule may have become lodged in another vehicle’s tire and carried away. This would be a particular risk, as it would leave the capsule in regular proximity to people. Worse, it could later be removed from the tire by hand, causing a significant radiation exposure in the process.
Just as we’re writing this, thankfully, the source was found by authorities before any calamity came to pass.
Overall, though, There’s also clearly a need to figure out how the source came to be lost in the first place. It would appear that the gauge containing the source was clearly not transported properly, or not transported in the proper condition, if the source was able to get loose in the first place. There are many questions to be answered to ensure that this never happens again. | 66 | 13 | [
{
"comment_id": "6588799",
"author": "Reluctant Cannibal",
"timestamp": "2023-02-01T15:16:05",
"content": "“It’s akin to trying to find the proverbial needle in the haystack, but much harder.” ….. Just trying to think what equipment would be needed to actually find an actual needle in an actual hays... | 1,760,372,411.425883 | ||
https://hackaday.com/2023/02/01/counterfeit-cisco-hardware-bypasses-security-checks-with-modchips/ | Counterfeit Cisco Hardware Bypasses Security Checks With Modchips | Arya Voronova | [
"Reverse Engineering",
"Security Hacks"
] | [
"cisco",
"counterfeit",
"i2c"
] | Some pictures recently surfaced on social media,
showing a small PCB tapped into four points on Cisco-branded boards
. What is this about? A NSA backdoor so data can be exfiltrated to some third party? Well, that’s theoretically possible, but it’s actually used for bypassing hardware authenticity checks in Cisco hardware being cloned — a sizable industry. Of course, “can’t believe it’s not Cisco” hardware is only valuable insofar that it’s able to run the Cisco software, and that’s where the bodge boards play a major role.
A
2020 report by F-Secure details an investigation,
comparing three switches marked as Cisco 2960X – one known genuine and two known counterfeits. The counterfeits had the aforementioned implants either soldered to the bottom of the PCB or added to the board as a separate component, and the paper goes into why they’re important for successful counterfeiting.
Apparently, these chips emulate or bypass an I2C EEPROM containing part of the code executed during the boot sequence, and Cisco depends on this EEPROM’s contents for authenticity verification. Cisco software reads the EEPROM twice — once for verification, and once again for actually running it. The microcontroller included on the mod board can return a genuine binary with a valid signature on the first read, and a binary with hardware checks patched out for subsequent reads.
The paper will tell you about way more than this — it’s thorough yet captivating. As you’d expect, it devotes quite a bit of time to comparing genuine and counterfeit boards, showing that the cloning process is pretty to-the-T, save for some part substitutions. For instance, check out the PDF page 12 to see how via locations are exactly copied between PCBs in a bizarre way, or the Cisco file format and authenticity check analysis closer to the end of the report. All in all, the 38 pages of the document make for a fun foray into what makes Cisco authentication mechanisms tick, and what helps clone hardware makers bypass them.
Are such chips ever used for adding backdoors and data exfiltration? There’s no evidence of that, as much as that’s not to be excluded — bypassing anti-cloning protections would make other hijinks more viable no doubt, that said, only hardware authentication bypass measures were found so far. This mechanism also breaks during software updates, and absolutely, leaves some to be desired when it comes to its stated functionality. That said, such fun insights can help us, say,
enforce right-to-repair
,
enable hardware reuse,
and
thwart many predatory business practices
in areas
where laws fail us. | 32 | 8 | [
{
"comment_id": "6588684",
"author": "Mojo",
"timestamp": "2023-02-01T13:14:47",
"content": "Blue wires add the “personal” touch!",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6589362",
"author": "Technics",
"timestamp": "2023-02-02T02:11:05... | 1,760,372,411.611352 | ||
https://hackaday.com/2023/02/01/diy-adjustable-wrench-nuts/ | DIY Adjustable Wrench? Nuts! | Al Williams | [
"Tool Hacks"
] | [
"adjustable wrench",
"handtools",
"metalworking"
] | What do you do if you want a tiny little adjustable wrench? If you’re [my mechanics] you
build your own
. Where do you get the stock metal? Well, he started with an M20 nut. A few milling operations, a torch, some pliers, and work with a vice resulted in a nice metal blank just the right size to make each part of the wrench, including a new nut for the adjustment.
Want to do this yourself? If you do, we hope you have a well-equipped machine shop. You should also be comfortable working with red-hot metal. Overall, it is an amazing piece of work, and you can watch the whole process in the video below.
Honestly, precision metalworking is a little out of our comfort zone. Like the recent
wood bending we’ve seen
, we always think, “Yeah, I could so do that!” Then we realize that we really couldn’t. But still fun to watch and maybe a few ideas we might be able to apply next time we have to bend a little metal.
The wrench is a scale model of a larger one, and it looks great. We would have liked to see it in use with a tiny nut, but we imagine it would work just fine. If you get excited about making things from a single piece of metal, may we suggest
a nutcracker
? | 12 | 10 | [
{
"comment_id": "6588546",
"author": "Gershwin",
"timestamp": "2023-02-01T10:08:44",
"content": "A lot of “I built an X out of Y” stuff is pathetic, but this guy is amazing.Most of his videos are restoration, heavily relying on scratch building parts on a lathe and mill, but he also does some neat f... | 1,760,372,411.847511 | ||
https://hackaday.com/2023/01/31/a-new-analog-and-crt-neck-board-for-the-macintosh-se/ | A New Analog And CRT Neck Board For The MacIntosh SE | Maya Posch | [
"Retrocomputing"
] | [
"Macintosh SE",
"Macintosh SE/30"
] | Keeping a 35-year old system like the MacIntosh SE and its successor, the SE/30, up and running requires the occasional replacement parts. As an all-in-one system, the analog board that provides the power for not only the system but also the 9″ (23 cm) built-in CRT is a common failure location, whether it is due to damaged traces, broken parts or worse. For this purpose [Kay Koba]
designed a replacement analog board
, providing it with a BOM of replacement components. This also includes the neck board, which is the part that the CRT itself connects to.
As [Kay] notes in the
project log
, the design was inspired after building [Kai Robinson]’s Classic Reloaded logic board, which we
covered previously
. After a few revisions, [Kay] has now
begun selling
the PCBs for $42. The product page also links to BOMs for both the analog board and the neck board, with most of the parts simple through-hole parts. If the board’s fancy styling and LEDs compared to the original board isn’t your cup of tea, it does look like there exists interest in a more subdued version as well. | 13 | 6 | [
{
"comment_id": "6588387",
"author": "Stephen Walters",
"timestamp": "2023-02-01T06:44:13",
"content": "Need something similar for the fat mac 512k and the 1mb mac plus…",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6588609",
"author": "itomato",
... | 1,760,372,411.795987 | ||
https://hackaday.com/2023/01/31/steamdeck-become-printer/ | SteamDeck: Become Printer | Arya Voronova | [
"Linux Hacks",
"Peripherals Hacks"
] | [
"steam deck",
"USB Gadget",
"usb gadget framework"
] | Wonderful things happen when we read the documentation. For instance, we’ve all seen a Raspberry Pi work as an Ethernet adapter over USB, or a ESP32-S2 presenting as a storage device. Well, [parkerlreed] has
made his Steam Deck work as a USB printer
after reading the Linux kernel docs on the USB gadget configuration, and all it took was some C code and a BIOS setting change.
“Wouldn’t it be cool if our USB tablets exposed a fake printer interface and saved the received documents as PDF?” With a SteamDeck, you can do just that – thanks to
the
g_printer
kernel module.
The C code is fairly straightforward, and even lets you configure some aspects of the printer device.
Of course, there’s gotta be a cherry on the cake, and [parkerlreed]’s shell script hides an addition that makes your PDF printing experience all that more realistic! Not to spoil it too much – you should
watch the video
of the script in action, showcasing both the ease of use and the added realism.
Jokes aside, the usefulness of this script is undeniable, and owners of USB-device-capable portable Linux devices will find this script a must-have. It’s seriously cool when someone dives into documentation and pulls out a clever solution to a “wouldn’t it be cool” idea – fundamentally, it is the same mindset that
gave us the venerable RTL-SDR.
What’s your favourite ‘dig into docs and figure out a clever feature’ hack?
We thank [Myself] for sharing this with us on
the Hackaday Discord! | 9 | 4 | [
{
"comment_id": "6588234",
"author": "parkerlreed",
"timestamp": "2023-02-01T03:25:28",
"content": "Thank you, I’m here all night!Crazy seeing this sent to me and I was like “Hah”I’ve had two other ventures on Hackaday for anyone curioushttps://hackaday.com/2009/09/28/internal-wireless-headphones/ht... | 1,760,372,412.172373 | ||
https://hackaday.com/2023/02/02/cheap-kitchen-scale-learns-to-speak-json-with-esp32/ | Cheap Kitchen Scale Learns To Speak JSON With ESP32 | Jenny List | [
"home hacks",
"Microcontrollers"
] | [
"ESP32",
"IoT",
"kitchen scale",
"load cell",
"smart appliances"
] | Smart kitchen appliances are expensive, and more often than not, your usage data goes to whichever company operates the inevitable cloud service. Meanwhile the cheap ones contain substantially the same components without the smarts, so surely a hardware hacker can add a microcontroller to a cheap appliance for a bit of smart home technology without the privacy issues? It’s something [Liore] has done with an Amazon Basics kitchen scale,
removing the electronics and wiring up an ESP32 to the load cell instead
.
The Wheatstone bridge load cell circuit generates a tiny voltage difference that’s far too small for an ESP32 to measure, so in between the pair is an Avia Semiconductor HX711 strain gauge amplifier module. In addition, there’s a small OLED screen and the two buttons used in the Amazon scale are wired in too, providing the the kitchen scale functionality you’d expect.
Naturally the ESP32 brings along with it WiFi networking capabilities, which [Liore] has taken full advantage of here. By navigating a web browser to its IP address, you’ll receive the scale’s current reading in JSON format. This should make it easy to integrate with other systems, from Home Assistant to OctoPrint. We can see that there is plenty of scope for further enhancements for those prepared to write a little code.
Of course, this isn’t the first enhanced scale we’ve brought you,
here’s one with Bluetooth
. We’ve also seen hackers dispense with the kitchen-safe trappings and
build the load cell directly into their own contraptions
. | 5 | 3 | [
{
"comment_id": "6589730",
"author": "on4tux",
"timestamp": "2023-02-02T12:13:34",
"content": "Instead of writing the code for homeassistant integration yourself, you can piggyback on esphome;– hx711:https://esphome.io/components/sensor/hx711.html– ssd1306:https://esphome.io/components/display/ssd13... | 1,760,372,412.125503 | ||
https://hackaday.com/2023/02/02/copy-and-paste-lithium-battery-protection/ | Copy And Paste Lithium Battery Protection | Bryan Cockfield | [
"Battery Hacks",
"Parts"
] | [
"charger",
"dw01a",
"integrated circuit",
"lithium",
"lithium ion",
"pcb",
"protection",
"TP4056"
] | Lithium batteries have, nearly single-handedly, ushered in the era of the electric car, as well as battery energy storage of grid power and plenty of other technological advances not possible with older battery chemistries. There’s just one major downside: these lithium cells can be extremely finicky. If you’re adding one to your own project you’ll have to be extremely careful to treat them exactly how they are designed to be treated using something like
this boilerplate battery protection circuit
created by [DIY GUY Chris].
The circuit is based around the TP4056 integrated circuit, which handles the charging of a single lithium cell — in this design using supplied power from a USB port. The circuit is able to charge a cell based on the cell’s current charge state, temperature, and a model of the cell. It’s also paired with a DW01A chip which protects the cell from various undesirable conditions such as over-current, overcharge, and over-voltage.
The best thing about this design isn’t the design itself, but that [DIY GUY Chris] built the circuit schematic specifically to be easily copied into PCB designs for other projects, which means that lithium batteries can more easily be integrated directly into his other builds. Be sure to check out
our primer on how to deal with lithium batteries
before trying one of your own designs, though. | 40 | 8 | [
{
"comment_id": "6589609",
"author": "Neolker",
"timestamp": "2023-02-02T09:26:22",
"content": "Missing 5.1k Ohm resistors on CC USB-C pins",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6589734",
"author": "willmore",
"timestamp": "2023-02-0... | 1,760,372,412.31733 | ||
https://hackaday.com/2023/02/01/chipwhisperer-adapter-helps-reverse-engineer-a-controversial-game-cartridge/ | ChipWhisperer Adapter Helps Reverse-Engineer A Controversial Game Cartridge | Arya Voronova | [
"Reverse Engineering"
] | [
"ChipWhisperer",
"game cartridge",
"reverse engineering"
] | The ChipWhisperer has been a breakthrough in hobbyist use of power analysis and glitching attacks on embedded hardware. If you own one, you surely have seen the IDC and SMA sockets on it – usable for connecting custom breakouts housing a chip you’re currently probing. Today, [MAVProxyUser] brings us a
ChipWhisperer adapter for STM32F446ZEJx,
which comes in a UFBGA144 package – and the adapter has quite a backstory to it.
In retro gaming world, a crowdfunding campaign for a game called PAPRIUM has seen a huge success getting funded in 2017. However, the campaign has grossly underdelivered throughout the last five years, and out of those rare cartridges delivered to backers, quite a few have faulty hardware. Getting replacements isn’t realistic at this point, so the repair attempts and game preservation efforts
have been ongoing.
Trouble is – there are protection mechanisms against dumping the cartridges, and one of the protection mechanisms is the built-in flash read protection of the aforementioned STM32 found on the cartridge. This board adapts the chip to a ChipWhisperer interface for protection bypass exploration, and has quite a few configuration jumpers anyone facing a similar chip is able to use –
Eagle files are out there
as well, in case your chip needs a slightly different approach.
With reverse-engineering underway, are we likely to see this cartridge’s defenses fall? Our assessment is ‘yes’ – it’s not like there’s a shortage of mechanisms for bypassing security ; from
modchips
to
EMP attacks
to
blasting the die with a laser,
hardware-reliant security is, still, quite bypassable. All in all, despite the drama around the project, this is one more reference design for
the ChipWhisperer,
and a fun journey to look forward to. | 7 | 2 | [
{
"comment_id": "6589500",
"author": "AC",
"timestamp": "2023-02-02T06:36:01",
"content": "Remember when Hackaday ran a design contest, and in total surprise to many readers awarded the grand prize to a project almost no one cared about instead of a practically useful tool that is directly relevant ... | 1,760,372,412.359867 | ||
https://hackaday.com/2023/02/01/not-a-pot-not-an-encoder-exploring-synchros-for-rotational-sensing/ | Not A Pot, Not An Encoder: Exploring Synchros For Rotational Sensing | Dan Maloney | [
"Misc Hacks"
] | [
"angle",
"avionics",
"cosine",
"encoder",
"sensor",
"synchro",
"transformer",
"transmitter"
] | We’re all familiar with getting feedback from a rotating shaft, for which we usually employ a potentiometer or encoder. But there’s another device that, while less well-known, has some advantages that just might make it worth figuring out
how to include it in hobbyist projects: the synchro
.
If you’ve never heard of a synchro, don’t feel bad; as [Glen Akins] explains, it’s an expensive bit of kit most commonly found in avionics gear. It’s in effect a set of coaxial transformers with a three-phase stator coil and a single-phase rotor. When excited by an AC reference voltage, the voltage induced on the rotor coil is proportional to the cosine of the angle between the rotor and stator. It seems simple enough, but the reality is that synchros present some interfacing challenges.
[Glen] chose a surplus altitude alert indicator for his experiments, a formidable-looking piece of avionics. Also formidable was the bench full of electronics needed to drive and decode the synchro inside it — a 26-volt 400-Hz AC reference voltage generator, an industrial data acquisition module to digitize the synchro output, and an ESP32 dev board with a little OLED display to show the results. And those are impressive; as seen in the video below, the whole setup is capable of detecting tenth-of-a-degree differences in rotation.
The blog post has a wealth of detail on using synchros, as does
this Retrotechtacular piece
from our own [Al Williams]. Are they practical for general hobbyist use? Probably not, but it’s still cool to see them put to use. | 25 | 13 | [
{
"comment_id": "6589414",
"author": "They probably also work with 26-volt 0-Hz DC reference voltage generator.",
"timestamp": "2023-02-02T03:46:45",
"content": "Absolute rotary encoders cannot also be avionic grade?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_... | 1,760,372,412.238831 | ||
https://hackaday.com/2023/02/01/want-better-0402-reflow-consider-these-footprints/ | Want Better 0402 Reflow? Consider These Footprints! | Arya Voronova | [
"Lifehacks",
"PCB Hacks"
] | [
"0201",
"0402",
"footprint",
"footprint creation",
"reflow",
"reflow soldering"
] | Assembling with a stencil is just that much more convenient – it’s a huge timesaver, and your components no longer need to be individually touched with a soldering iron for as many times as they have pads. Plus, it usually goes silky smooth, the process is a joy to witness, and the PCB looks fantastic afterwards! However, sometimes components won’t magically snap into place, and each mis-aligned resistor on a freshly assembled board means extra time spent reflowing the component manually, as well as potential for silent failures later on. In an effort to get the overall failure rate down, you will find yourself tweaking seemingly insignificant parameters, and [Worthington Assembly] proposes that you
reconsider your 0402
and
0201 footprints.
Over the years, they noticed a difference in failure rates between resistor&capacitor footprints on various boards coming in for assembly – the size and positioning of the footprint pads turned out to be quite significant in reducing failure rate, even on a tenth of millimeter scale. Eagle CAD default footprints in particular were a problem, while a particular kind of footprint never gave them grief – and that’s the one they recommend we use. Seeing the blog post become popular, they decided to share their observations on 0201 as well, and
a footprint recommendation
too. Are your 0402 resistors giving you grief? Perhaps, checking the footprints you’re using is a good first step.
The 0402 and 0201 components are in a weird spot, where soldering iron assembly is no longer really viable, but the stencil+reflow approach might not be unilaterally successful when you start off – fortunately, that’s where writeups like these come in. Interested in learning stenciling? Get some solder paste, and read up on
all the different ways
you can put it onto your boards. | 13 | 10 | [
{
"comment_id": "6589275",
"author": "Nick Ames",
"timestamp": "2023-02-02T00:10:02",
"content": "I can vouch for their 402 footprint, at least for prototyping and small-scale production. No tombstoning or other issues so far, across several PCB designs and a range of reflow processes.",
"parent... | 1,760,372,412.411334 | ||
https://hackaday.com/2023/02/01/comparing-cheap-capacitative-soil-moisture-sensors-with-commercial-sensors/ | Comparing Cheap Capacitative Soil Moisture Sensors With Commercial Sensors | Maya Posch | [
"green hacks"
] | [
"capacitive sensor",
"moisture sensor",
"soil moisture sensor"
] | When your residence has soil moisture sensors embedded that were dictated by your friendly neighborhood HoA, you may start asking questions about the system used. That’s what [Modest Maker] did and the resulting findings along with an attempt to beat the commercial system with some cheap capacitive sensors, are covered in a
recent video
that’s also embedded below. Part of the motivation here was that the commercial system in the community was not clearly installed properly.
To make a long story short, the commercial system by Hunter (
Soil-Clik
) appears to be a tensiometer-based system that uses the pressure produced by moisture intrusion into the measurement column. This translates to how easy it is for plant roots to extract water, depending on the soil type. [Modest Maker] had to first dodge the broken-by-design capacitive sensors that are available everywhere, but after that was able to cobble together a measurement system that he hopes will allow him to validate the commercial system’s installation. | 41 | 12 | [
{
"comment_id": "6589175",
"author": "Dude",
"timestamp": "2023-02-01T21:57:54",
"content": "These capacitive sensors are basically useless, since they operate in a low frequency where soil salinity and temperature has a great effect on the measurement outcome. Salinity or other dissolved electrolyt... | 1,760,372,412.603504 | ||
https://hackaday.com/2023/02/01/electron-microscope-conversion-hack/ | Electron Microscope Conversion Hack | Al Williams | [
"Science"
] | [
"electron microscope"
] | Some of you probably know this already, but there’s actually more than one kind of electron microscope. In electronics work, the scanning electron microscope (SEM) is the most common. You hit something with electrons and watch for secondary electron emissions. However, biologists more often use a TEM — a transmissive electron microscope — which passes electrons through a sample to image it. [Breaking Taps] built a small device to convert his
SEM into a TEM
.
One key idea is that in a SEM, the beam’s position on the target is the only thing that matters. Any secondary electron detected is a result of that spot’s composition, no matter where you collect them. Common detectors pick up back-scattered electrons bouncing back toward the electron source. There are also low-energy electrons bouncing off in random directions, depending on the topology of the target.
The slow electrons can be attracted by a single detector that has a strong positive charge. TEM doesn’t detect secondary electron emissions. Instead, it passes electrons through a target and collects the ones that pass through a very thin sample using a screen that glows when electrons hit it.
The idea, then, is to create a STEM-SEM device. There’s a sample holder and an angled reflector that shoots electrons passing toward the SEM’s detector. The back-scatter detector is not used, and a shield prevents the detector from seeing secondary emissions from the target itself.
You can buy these, but they are well over $1,000, so in true hacker fashion, [Breaking Taps] made his own. You could, too, but you’d need a pretty good machine shop and — oh yeah — a scanning electron microscope.
While we have seen some home labs
with electron microscopes
, you need some high-tech vacuum and high-voltage gear, so it isn’t too common. Armed with a STEM, you can even see the
shadows of atoms
. | 7 | 4 | [
{
"comment_id": "6589336",
"author": "Ben C",
"timestamp": "2023-02-02T03:26:24",
"content": "A highly related topic that I’d love to see on hackaday is making your own direct electron diode detector (and necessary electronics).FWIW, here is a link to the paper on conversion detectors by Reimer:http... | 1,760,372,412.943951 | ||
https://hackaday.com/2023/01/31/let-this-minimal-desktop-weather-display-point-the-way/ | Let This Minimal Desktop Weather Display Point The Way | Abe Connelly | [
"home hacks"
] | [
"3D printable",
"9G servo",
"openweathermap",
"Raspberry Pi Zero 2 W",
"sg90",
"weather"
] | Much of the Northern Hemisphere is currently in the middle of winter, so what better way to brighten a potentially gloomy day than to put this charming,
minimalist weather display on your desk
.
[Joe] has created a weather gauge that uses two servo motors to position mechanical pointers to indicate weather symbols and time ranges. The electronics consists of a push button and two SG90 servos driven by a Raspberry Pi Zero W 2. The case is 3D printed including the pointers attached to the servos and the button brim of the switch. The Raspberry Pi Zero W 2 is programmed to automatically connect to the OpenWeather API to retrieve the latest weather conditions, with the latitude and longitude being configured into the update script during the configuration and assembly stages.
[Joe] has provided extensive documentation about the build and software setup, in addition to releasing the source code and STL files for anyone wanting to make their own.
[Joe] even offers kits
for those who don’t want to go through the trouble of putting one together themselves — not that we imagine many in this particular audience would fall into that category.
We love to see these delightful weather builds and we’ve featured others in the past, like a converted
weather house for weather prediction
or a
weather reporting diorama
. | 7 | 5 | [
{
"comment_id": "6587315",
"author": "Bob",
"timestamp": "2023-01-31T11:10:40",
"content": "This is pretty impressive. Beautiful work, great design. Also surprised by how cheap the kit is, for people without a 3D printer.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comme... | 1,760,372,412.664299 | ||
https://hackaday.com/2023/01/30/classic-calculators-emulated-in-browser/ | Classic Calculators Emulated In Browser | Bryan Cockfield | [
"computer hacks"
] | [
"browser",
"calculator",
"emulator",
"HP",
"retro",
"ti"
] | The Multiple Arcade Machine Emulator, now known simply as MAME, started off as a project to emulate various arcade games. The project is still adding new games to its library, but the framework around MAME makes it capable of emulating pretty much any older computer. The computer doesn’t even need to be a gaming-specific machine as the latest batch of retro hardware
they’ve added support for is a number of calculators from the 90s and early 00s
including a few classics from Texas Instruments.
Since no one is likely to build an arcade cabinet version of a TI-89, all of these retro calculators are instead emulated entirely within a browser. This includes working buttons and functions on an overlay of each of these calculators but also pixel-accurate screen outputs for each of these. The graphing calculators have more of what we would consider a standard computer screen, but even the unique LCDs of some of the more esoteric calculators are accurately replicated as well thanks to the MAME artwork system.
There are a number of calculators implemented under this project with
a full list found at this page
, and the MAME team has plans to implement more in the future. If you’re looking for something fun to do on a more modern calculator, though, take a look at
this build which implements ray tracing on a TI-84 Plus CE
.
Thanks to [J. Peterson] for the tip! | 24 | 11 | [
{
"comment_id": "6587150",
"author": "Gareth",
"timestamp": "2023-01-31T08:31:59",
"content": "There’s only one for me…https://quartic-software.co.uk/mobile/screenshots.htmlEmulating a calculator on a PC? I really don’t understand",
"parent_id": null,
"depth": 1,
"replies": [
{
... | 1,760,372,412.815598 | ||
https://hackaday.com/2023/01/30/rf-spectrometer-sees-inside/ | RF Spectrometer Sees Inside | Al Williams | [
"Science"
] | [
"nanovna",
"RF",
"spectroscopy"
] | Spectrometry is a well-known technique or, more correctly, a set of techniques. We usually think of it as the analysis of light to determine what chemicals are producing it. For example, you can tell what elements are in a star or an incandescent based on the spectrum of light they emit. But you can also do spectroscopy with other ranges of electromagnetic radiation. [Applied Science] shows how to make an
RF spectroscope
. You can see the video below.
An oscilloscope-resident function generator creates a signal that he feeds to an amplifier because you need a fair amount of power going out. However, you also need to sense a very tiny amount of power coming back, and that requires a special circuit that will block high-power signals while passing low-level signals.
Because of the low level of signals involved, you do need some special RF techniques. You also need a way to read back the spectrum. Turns out a NanoVNA works fine for this application. The actual science behind this is the same idea as what happens with nuclear resonance imaging. The end of the video has a detailed explanation of what makes it work.
Of course, this machine doesn’t do the image part. But we’ve seen
an attempt to do just that
, too. There are many different kinds of spectroscopes. There are ones that use
a laser and Raman scattering
, and some that just
light things up with a laser
. | 7 | 4 | [
{
"comment_id": "6587090",
"author": "peptoid",
"timestamp": "2023-01-31T07:16:24",
"content": "Preempting the semantic argument re: spectrometry vs. spectroscopy…But in any case, it’s a very crude but functional NMR. It’s quite impressive that you can assemble something like one on a benchtop with ... | 1,760,372,412.742775 | ||
https://hackaday.com/2023/01/30/retro-computer-enclosure-without-the-sacrifice/ | Retro Computer Enclosure Without The Sacrifice | Tom Nardi | [
"classic hacks",
"Parts"
] | [
"3D printed enclosure",
"classic computer",
"cyberdeck",
"recreation",
"retro"
] | The unique look of early desktop computer systems remains popular with a certain segment of geekdom, so it’s no great surprise when we occasionally see a modern hacker or maker unceremoniously chuck 40+ year old electronics from a vintage machine just to reuse its plastic carcass. We try not to pass judgement, but it does sting to see literal museum pieces turned into glorified Raspberry Pi enclosures.
But with a little luck, perhaps the
Retro Wedge Computer case designed by [AndyMt]
will be able to save a few of those veteran computers from an unnecessary lobotomy. As the name implies, this 3D printable model is designed to resemble “wedge” desktop computers such as the Atari ST, TI-994A, and Commodore 128. But don’t be put off by its considerable size — the model has been chopped up so no piece is larger than what can fit on a fairly standard 230 x 230 mm print bed.
The case is designed around a modern USB mechanical keyboard.
Rather than tailor the design to one specific set of internals, [AndyMt] has wisely left that up to the end-user. There are no dedicated mounting points inside, nor is there a rear-panel.
Once you figure out which single-board computer
you want to put into this faux-retro box, designing those last parts will be up to you.
That said, the keyboard section is more specific, with the design focusing on a
XTRFY K4 TKL RGB RETRO
. While it’s not the cheapest mechanical keyboard we’ve ever seen, it does feature an era-appropriate color scheme which makes it uniquely well suited to this project.
Like
attempts to recreate other forms of classic computers
, it will obviously take more time and effort to print this case out than it would to look around on eBay for a donor Commodore C64 C. But given that those classic machines are only becoming
more rare and valuable as time goes on
, building it yourself will almost certainly be the cheaper option. | 29 | 10 | [
{
"comment_id": "6586651",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-01-31T00:35:06",
"content": "Good idea!Now if I can put my TS1000 in one.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6587493",
"author": "Sketch",
... | 1,760,372,412.892733 | ||
https://hackaday.com/2023/01/30/converting-a-sink-to-an-ultrasonic-cleaner/ | Converting A Sink To An Ultrasonic Cleaner | Bryan Cockfield | [
"home hacks"
] | [
"audio",
"cleaner",
"driver board",
"transducer",
"ultrasonic",
"wash"
] | While ultrasonic cleaning might sound a bit like the “sonic shower” from Star Trek, this is actually one case where the futuristic-sounding technology predates its use in Sci-Fi. Ultrasonic cleaners have been around since the 50s and are used to clean all sorts of oddly-shaped or specialty objects by creating cavitation within a liquid that allows the surface of the object to be scoured.
With the right equipment, these cleaning devices are fairly straightforward to build as well
.
This ultrasonic cleaner by [Branchus Creations] started off as a standard stainless steel laundry sink, but with the addition of a few transducers it really turns up the volume. They are attached to the underside of the sink with a combination of a bolt and hard epoxy so that the sound is efficiently transmitted to the sink, but they’re not much use without driver boards to power them. These drivers take AC power and convert it to the DC required to generate the ultrasonic frequencies, and this build uses a driver for each of the transducers all wired up to a common control board for ease-of-use.
The results speak for themselves; a test is performed on a sheet of aluminum foil which quickly turns takes on a Swiss cheese appearance after just a couple minutes in the cleaner. It’s also shown cleaning rusty nails and a few other things as well. For other nontraditional cleaning methods, be sure to check out
this wet media blast cabinet
built from a 55-gallon drum.
Thanks to [Zane] for the tip! | 42 | 16 | [
{
"comment_id": "6586579",
"author": "Rudely Awakened",
"timestamp": "2023-01-30T22:02:39",
"content": "Wanted to do the same and purchased a transducer and driver board from my favorite Asian vendor of cheap parts. Shocked the ^*)*& out of me. Measure to ground before touching.",
"parent_id": n... | 1,760,372,413.028292 | ||
https://hackaday.com/2023/01/30/1000-aluminium-cans-cast-into-a-guitar/ | 1000 Aluminium Cans Cast Into A Guitar | Lewin Day | [
"Musical Hacks"
] | [
"aluminium",
"aluminium casting",
"casting",
"guitar"
] | Aluminium cans are all around us, and are one of readily recyclable. While you can turn them into more cans, [Burls Art] had other ideas.
Instead, he turned roughly 1000 cans into a custom aluminium guitar.
Both the body and neck of the electric guitar are made out of aluminium. It’s an impressive effort, as manufacturing a usable neck requires care to end up with something actually playable when you’re done with it.
Producing the guitar started with a big propane furnace to melt all the cans down so they could be cast into parts for the guitar. 38 lbs of cans went into the project, and were first dried out before being placed into the furnace
for safety reasons.
Aluminium cans aren’t made of the best alloy for casting, but you can use them in a pinch. The cans were first melted down and formed into ingots to be later used for producing the neck and body.
[Burls Art] then built sand casting molds for his parts with a material called Petrobond. Wood plugs were used to form the sand into the desired shape. The neck casting came out remarkably well, and was finished with a grinder, hacksaw, and sandpaper to get it to the right shape and install the frets. The body proved more difficult, with its multiple cavities, but it came together after a second attempt at casting.
Fully kitted out with pickups and hardware, the finished product looks great, and weighs 12.3 pounds. It sounds remarkably like a regular electric guitar, too. It does pick up fingerprints easily, and does have some voids in the casting, but overall, it’s a solid effort for an all-cast guitar.
We’ve seen some other great casting projects over the years before, too
. Video after the break. | 31 | 12 | [
{
"comment_id": "6586550",
"author": "TG",
"timestamp": "2023-01-30T20:03:58",
"content": "The little imperfections and cavities and inclusions look really cool",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6586566",
"author": "Hirudinea",
"timestamp"... | 1,760,372,413.192993 | ||
https://hackaday.com/2023/01/30/retro-gadgets-the-cb-cell-phone/ | Retro Gadgets: The CB Cell Phone | Al Williams | [
"Hackaday Columns",
"Radio Hacks",
"Slider"
] | [
"cb radio",
"cell phone",
"retrotech"
] | There was a time when one of the perks of having a ham radio in your car (or on your belt) was you could make phone calls using a “phone patch.” In the 1970s, calling someone from inside your parked car turned heads. Now, of course, it is an everyday occurrence thanks to cell phones. But in 1977, cell phones were nowhere to be found. Joseph Sugarman, the well-known founder of JS&A, saw a need and wanted to fill it. So he offered the “PocketCom CB” which was billed as the “world’s smallest citizens band transceiver.” You can see the full-page ad from 1977 below.
Remember that this is from an era when ICs that could operate at 30 MHz were not the norm, so you have to temper your expectations. The little unit was 5.5 in by 1.5 in and less than an inch thick. That’s actually not bad, but you had — optimistically — 100 mW of output power. They claimed the N cell batteries would last two weeks with average use, but we imagine a lot less as soon as you start transmitting. The weight was 5 oz, but we suspect that is without the batteries.
The device had a crystal for channel 14, and you could buy another crystal to get a second channel. Given that the unit was selling for about $40 to $20, it was telling that the extra crystal cost $8. We heard that over 250,000 of these were sold. The ad copy mentions they were used on the TV show Charlie’s Angels, but we can’t picture how that happened. It also mentioned it can be used as a pager, an intercom, a telephone, or a security device.
In operation, the devices were pretty simple. The 40″ antenna, when pulled out, would make the unit a bit more cumbersome. We found a
relatively recent review
on the CB Gazette from someone who picked up two of these on the used market. Seemed like they did work, although they were probably no better than a kid’s walkie-talkie.
Many hams convert CBs to the 10-meter band or
even the 6-meter band
, and we wonder if a crystal would pull these to 10 meters. Before cell phones, people thought we needed bigger towers, more power, and more channels. Turns out, it is
just the opposite
. | 45 | 19 | [
{
"comment_id": "6586502",
"author": "Ken",
"timestamp": "2023-01-30T18:15:21",
"content": "Back in the day, Radio Shack sold CB & scanner crystals for $5 IIRC, so $8 from JS&A was probably reasonable.There were also “credit card” Ham handhelds that were a little wider/thinner around the same time."... | 1,760,372,413.119034 | ||
https://hackaday.com/2023/01/31/handmade-gps-tracker-keeps-an-eye-on-adventurous-cats/ | Handmade GPS Tracker Keeps An Eye On Adventurous Cats | Robin Kearey | [
"gps hacks",
"News"
] | [
"gps tracker",
"gsm",
"pet tracking",
"traccar"
] | One of the most convenient things about having cats is their independent lifestyle: most are happy to enjoy themselves outside all day, only coming back home when it’s time for dinner and a nap. What your cat gets up to during the day remains a mystery, unless you fit it with a GPS collar. When [Sahas Chitlange] went searching for a GPS tracker for his beloved Pumpkin, he found that none were exactly to his liking: too slow, too big, or simply unreliable. This led him to
design and build his own, called
Find My Cat
.
The heart of the device is an A9G GSM/GPS board, based on the RDA8955 system-on-chip. [Sahas] combined this with a data SIM card, a 2600 mAh lithium battery and a charger module to make a completely self-contained GPS tracker capable of transmitting location information in real time. The system is housed in a hand-made brass box designed to be attached to a cat harness, where it sits safely on Pumpkin’s back.
It took a bit of experimentation to find a workable antenna setup for this system, because the brass box works as a Faraday cage. [Sahas] therefore made the lid of the enclosure out of wood, and embedded two thin strips of brass within it to make a dipole antenna. Tests in his car confirmed that it got a reliable fix and was able to communicate through the GSM network.
On the software side, The A9G module came with a C/C++ based SDK that [Sahas] found so inconvenient to use that he decided to replace the whole thing with a MicroPython setup. He then programmed it with a simple routine that waits for an MQTT message to start tracking, and otherwise stays in sleep mode. Location data is sent to a Raspberry Pi running
Traccar
, an open-source GPS tracking server that provides a ready-to-use web interface. Finding Pumpkin’s location is now as simple as opening a web browser, navigating to the Pi’s IP address and looking at the map.
As in many wearables, the largest part of the system is the battery, which in this case provides a good twelve days of usage between recharge sessions. We’d assume that to be plenty, unless Pumpkin is one of those cats that like to go on multi-week expeditions. Limited battery life is
a common problem
for
GPS pet trackers
; perhaps switching to
an ultra-low-power LoRa-based system
might help. | 30 | 11 | [
{
"comment_id": "6588091",
"author": "lars klingman",
"timestamp": "2023-02-01T00:33:15",
"content": "here is a novel idea, keep your pets on your own property",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6588293",
"author": "TimT",
"timest... | 1,760,372,413.334868 | ||
https://hackaday.com/2023/01/31/kicanvas-helps-teach-and-share-kicad-projects-in-browsers/ | KiCanvas Helps Teach And Share KiCad Projects In Browsers | Arya Voronova | [
"PCB Hacks",
"Software Hacks",
"Tool Hacks"
] | [
"KiCAD",
"kicad integration",
"kicanvas",
"pcb viewer"
] | KiCad is undeniably the hacker favourite when it comes to PCB design, and we’ve built a large amount of infrastructure around it – plugins, integrations, exporters, viewers, and much more. Now,
[Stargirl Flowers] is working on
what we could call a web viewer for KiCad files – though calling
the KiCanvas project
a “KiCad viewer” would be an understatement, given everything it aims to let you do. It will help you do exciting things like copy-pasting circuits between KiCad and browser windows, embed circuits into your blog and show component properties/part numbers interactively, and of course, it will work as a standalone online viewer for KiCad files!
Of course, the “board viewer” part of the project is exceptionally handy alone, and will let you quickly show your PCB designs to others without having KiCad installed. When it comes to schematics and PCB embed features, we can already see examples of KiCanvas in action, too – with
exploreable circuits
in the extensive writeup about
a RP2040-based LumenPnP control board
, and
a PCB view in an assembly guide
for a precision adder. Quite a few basic goals are already achieved and the project aims to become open-source in February, but there’s plenty to work on – mobile browser support, blog integrations, assembly helper features, and of course, an inevitable pile of testing and polish – for these, you can
sponsor [Stargirl] on GitHub,
for perks like early access to the project.
When sharing your projects with others, embedding a JPEG of your schematic only gets you so far, so given all the interactivity you can have, browsers and KiCad files are a match made in heaven. Projects like KiCanvas end up as building blocks that hackers can rely on – like
the InteractiveHtmlBom project,
which now helps quite a few projects provide assembly diagrams, or
the Pinion project
that lets you quickly create wiring diagrams for your PCB.
You can also embed parts of your schematic or layout in web pages, perfect for educational articles and documentation. Select the items in KiCAD, copy, and then pass the copied text along to KiCanvas's <kicanvas-viewer> element. You can even make links to individual symbols!
pic.twitter.com/FxaCYm3Igq
— Stargirl🌠 (@theavalkyrie)
December 29, 2022
We thank [Ben Delarre], [Mithro] and [Helge Wurst] for sharing this with us! | 27 | 8 | [
{
"comment_id": "6587898",
"author": "Orzel",
"timestamp": "2023-01-31T21:22:26",
"content": "“…and the project aims to become open-source in February…” <- I stopped reading here",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6587915",
"author": "Jan... | 1,760,372,413.259505 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.