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/2023/12/13/diy-tachistoscope-feeds-your-hunger-for-popcorn-and-propaganda/ | DIY Tachistoscope Feeds Your Hunger For Popcorn And Propaganda | Dan Maloney | [
"classic hacks"
] | [
"ChatGPT",
"propaganda",
"raspberry pi",
"subliminal advertising",
"youtube"
] | You’ve probably heard of subliminal advertising — the idea is that behaviors can be elicited by flashing extremely brief messages on a movie or TV screen. “BUY POPCORN NOW” is the canonical example, with movies containing such subconscious messaging supposedly experiencing dramatic increases in popcorn sales.
Did it work? Maybe, maybe not, but the idea is intriguing enough to at least explore using
this subliminal tachistoscope
. [Roni Bandini] seems to have taken this project on as a sort of cautionary tale about brainwashing techniques, not only in motion pictures and TV but in printed media too; he goes pretty hard on the Peronistas’ use of not-so-subliminal messages to mold young Argentinian minds back in the 1940s and 50s.
The tachistoscope [Roni] presents is a little more sophisticated than those ham-fisted propaganda attempts. The Raspberry Pi-powered device downloads a video from YouTube and automatically replaces random frames with a propaganda message inspired by those used by the Peronistas, with the modified video piped to a composite video output for display on a TV.
A digital counter on the tachistoscope keeps track of the total time viewers have been propagandized. For extra fun, the machine has a switch to enable ChatGPT-created political messages to be inserted into the stream; we shudder to think what those might look like. Watch the video below for a sample of the brainwashing, but don’t blame us if you fall in love with [Evita].
We understand that this is more of a statement on the power of propaganda than an actual tool for mind control, but if [Roni] is serious about his brainwashing, some small mods might make it more effective. Thanks to the full frame of text on a black background, the subliminal messages aren’t very subliminal; they might be more subtle if the text was overlaid on the target frame rather than replaced completely. Seems like
that should be possible
with
ffmpeg
or something similar. | 12 | 7 | [
{
"comment_id": "6707555",
"author": "Are rats even the entree?",
"timestamp": "2023-12-13T12:18:20",
"content": "Subliminal.Below a sensory threshold. Below perception.Any message unable to be perceived by the target audience is by definition subliminal messaging.Subliminal messaging is alive and w... | 1,760,372,077.470962 | ||
https://hackaday.com/2023/12/13/led-art-project-is-geometrically-beautiful/ | LED Art Project Is Geometrically Beautiful | Lewin Day | [
"Art",
"LED Hacks"
] | [
"addressable leds",
"art",
"led"
] | There is no shortage of companies on the Internet willing to sell you expensive glowing things to stick on your walls. Many hackers prefer to make their own however, and [Chris] is no exception.
His LED wall art is neat, tidy, and stylish, all at once.
Wanting a geometric design, [Chris] decided to have his layout
designed by a random number generator
. He created his own tool that would generate a design using preset segment lengths arranged in a random fashion. Once he found a layout that worked for him, he designed a set of plastic adapters that would let him connect pre-cut lengths of aluminium channel together so he could assemble his design.
With the frame complete, he then laid the LED strips into the channels, after mapping out how he would connect the full circuit of addressable LED strips. He enlisted a Raspberry Pi Zero W as the brains of the operation, responsible for commanding the strips to light in the colors of his desire.
In a nice aesthetic touch, he sanded the whole frame and painted it a uniform grey color. This hid the joins between the 3D-printed parts and the aluminium channels, and gave it a more finished look. He also went to the trouble of graphing out the locations of the various LEDs in the frame, and used this data as the basis for animations that race between points on the frame. It’s somehow more compelling than the usual simple color fades and flashes of typical commercial products.
It’s a tidy build, and a level more artful than some of the off-the-shelf products out there. For his investment of time and money, [Chris] has netted
an excellent piece of wall art in the process
. | 7 | 4 | [
{
"comment_id": "6707569",
"author": "MacGyverS2000",
"timestamp": "2023-12-13T12:54:56",
"content": "Maybe it’s just me, but… where are the power wires to the sculpture itself?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6707587",
"author": "Wonk... | 1,760,372,077.306997 | ||
https://hackaday.com/2023/12/12/can-googles-new-ai-read-your-datasheets-for-you/ | Can Google’s New AI Read Your Datasheets For You? | Al Williams | [
"Artificial Intelligence",
"Current Events",
"google hacks",
"Original Art",
"Rants"
] | [
"artificial intellegence",
"datasheets",
"llvm",
"notebooklm"
] | We’ve seen a lot of AI tools lately, and, of course, we know they aren’t really smart, but they sure fool people into thinking they are actually intelligent. Of course, these programs can only pick through their training, and a lot depends on what they are trained on. When you use something like ChatGPT, for example, you assume they trained it on reasonable data. Sure, it might get things wrong anyway, but there’s also the danger that it simply doesn’t know what you are talking about. It would be like calling your company’s help desk and asking where you left your socks — they simply don’t know.
We’ve seen attempts to have AI “read” web pages or documents of your choice and then be able to answer questions about them. The latest is from Google with
NotebookLM
. It integrates a workspace where you can make notes, ask questions, and provide sources. The sources can be text snippets, documents from Google Drive, or PDF files you upload.
You can’t ask questions until you upload something, and we presume the AI restricts its answers to what’s in the documents you provide. It still won’t be perfect, but at least it won’t just give you bad information from an unknown source.
The Hackaday Badge
To try it out, we decided to see how good it would do if you were too lazy to read the
programming manual
for the 2023 Hackaday Badge. Once you’ve signed into NotebookLM, you create notebooks. Each notebook has its own set of references and notes. In this case, we have only a single source — the PDF manual.
We’ve called AI “
the worst Summer intern ever
,” and this isn’t far off here, either. My first question was how to make some code run every two seconds. The first two answers advised me to use
asyncio.sleep(2)
, which isn’t technically wrong, but it assumes I have control of the CPU to start with. Of course, I know the answer I’m looking for, so it is easy to dismiss it, but if this were something I really needed help with, it might take me some time to realize this is a dead end.
A more specific question helped:
How do I have VectorOS run my code perodically?
You can use the
Timer
class to schedule a function to run periodically. The timer’s base rate is set in
vos_launch
(
timer_base_rate
in milliseconds). All timeouts are computed against that base rate. The base rate should not be too fast (e.g., 10 milliseconds is probably too fast, and you will get recursion errors as the timer’s loop overruns itself). The default is 100 milliseconds.
Here is an example of how to use the Timer class to run a function every second:
import timer
def my_function():
# Do something
timer.add_timer(1000, my_function)
The whole transcript of my badge queries.
Interestingly, I asked essentially the same question twice and got correct, but subtly different, answers both times. The first time I used “How can I…” instead of “How do I…” and the program provided more detail. It also suggested ten references in the document for the first question, but only one for the second question which seems odd given that the only difference in the query was using do instead of can.
On the other hand, it did get there. I then asked it what a slot was. I think that was a good example, because, in the real world, a slot could mean any number of things, but for VectorOS it has a very specific meaning. Here’s what the AI had to say about that:
A slot is a function that takes a single argument, a Vectorscope object. The Vectorscope object is used to produce analog voltages for display on the oscilloscope screen. When you create a slot, you register it with VectorOS by editing the vos_launch.py file. The entry must be in the vectorscope_slots dictionary. Slots named slotA, slotB, slotC, and slotD will run when you press the A, B, C, or D button from the menu screen.
Slots can be launched from other programs as well. To do this, call vectoros.launch_vecslot with the name of the slot.
Of course, all of this is in the manual. But it is nice to be able to just ask and let it sift through the nearly 50-page document. In this case, we only have one source, but the program does give you a short summary of the source and lets you enable or disable certain sources whenever you like.
Upgrading Printers
I did a 3D printing class for 8th graders last summer. To support that, I bought a “returned” Ender 3 V2 Neo printer and spruced it up so I’d have an extra cheap printer for the kids to use. But now I’m thinking of upgrades for it. It would be cool if the notebook could search the Web — it is from Google, after all. But it can’t.
I took a few different approaches to loading in sources. First, I found the Ender 3 manual and uploaded it as a PDF. I also grabbed a few websites and either pasted text in or printed them as PDFs to load. In most cases, I used reading view to strip away all the extra stuff before I printed the PDFs on the assumption that would help.
In the end, I had seven different sources. One was a Reddit thread that didn’t print out very nicely but had some good information.
I asked the notebook to tell me about some simple upgrades I could do to the printer. It came up with a reasonable list, including using better tubing, a quieter fan, and some others. It also provided three links that were relevant. However, don’t make the mistake of thinking it really understood what was going on. For example, it offered auto bed leveling as a suggestion. However, the V2 Neo already has bed leveling. It also suggested replacing Bowden tubing and using a direct drive extruder. Nothing wrong with either of those suggestions, but you would not do them together. It also suggested several mods to a hot end that isn’t stock on the printer without clarifying that those would only apply if you had already upgraded the hot end.
To be fair, this is the “bad summer intern” effect. The AI doesn’t know anything about this topic except what we tell it via the sources. I’m sure the sources talked about all those things. So if you told some newbie to read all those documents and then asked questions, you might get the same kind of answers.
The Pi Pico
There are many PDF files related to the Raspberry Pi Pico, so that seemed like a good notebook to create. However, trying to add the main
RP2040 datasheet
dies with no error message. I suspect it is too long at around 700 pages. I was able to add several other documents, though, including the
PDF version of the Arduino package documentation
. Finally, I split the datasheet into four parts and that seemed to do the trick. Sadly, you can’t upload multiple files, so it took four separate uploads to get it going.
In the end, I had ten different documents to sift through (although four of them were the large datasheet). The notebook was able to answer basic questions like how many DMA channels were available, what was the smallest DMA transfer possible, and if the pins were TTL compatible.
It was also able to answer some tougher questions, like which Arduino functions use the PIO system. Before you get too impressed, though, it later informed me that the RP2040 doesn’t have an I2C slave mode, only a master mode. Then, in the next answer, it told me that the I2C slave mode runs at 100 kHz, and the chip does not have an I2C master mode. Those answers were in response to it telling about the SPI clock limitations when I had asked about the master clock. Not its finest hour.
Granted, you at least can click on the references it provides to see what part of the document it is misinterpreting. But if you have to do that much work and — more importantly — know that much about it to begin with, maybe the tool needs some work. True, this is an early release so it will probably get better.
Garbage In, Garbage Out
There is no doubt that a tool like this can only be as successful as the data you put into it. However, the errors we saw here were more misinterpretations of the provided data that a human would have been less likely to make.
Impressive? Sure. But think about the use case. If you already know a lot about the RP2040, for example, you might have just done a web search for those questions. Or even searched for keywords in the PDF. It probably would have been as fast once you deduct the time deciding if the answer seems legit or not. The real power of this kind of tool would be for people who don’t know the topic and don’t have the background to think about how to find things like this. Imagine a ship at sea with no doctor an AI version of the Merck Manual. You hope it would do better than this. | 25 | 9 | [
{
"comment_id": "6707327",
"author": "Dude",
"timestamp": "2023-12-12T15:07:26",
"content": "It would be more useful to pull the relevant parts of the document verbatim, so you don’t have to play a game of broken telephone with the AI. Just tell me where in this document I can find what I’m looking ... | 1,760,372,077.723802 | ||
https://hackaday.com/2023/12/12/hilarious-security-flaw-in-counter-strike-2-is-now-patched/ | Hilarious Security Flaw InCounter Strike 2Is Now Patched | Lewin Day | [
"Games",
"Security Hacks"
] | [
"Counter-Strike",
"counter-strike 2",
"counterstrike 2",
"cs2",
"games",
"gaming"
] | Normally, when we talk about video games having bugs, it’s some kind of item duplication glitch or a hilarious failure in the jacket equip code of some tedious
first-person-shooter
online wardrobe simulator.
Counter-Strike 2
has had a more embarrassing faux-pas, however, with a security hole allowing bad actors to theoretically capture the IPs of their fellow players in a server. You won’t believe how this came to happen.
The exploit has already been making its way around the forums,
with one [Crouch9706] raising the alarm
. It’s all down to the way
Counter-Strike 2
renders the names that players have entered in their Steam gaming profiles. In certain menus and other parts of the UI,
the game will actually parse HTML
in a player’s name. Typically, the way to trigger it is to join a game and vote to kick yourself. This brings up a dialog for other players that shows them your player name and parses the HTML. The only limitation is you only get 32 characters for your HTML.
There’s a nifty little extra trick to this, though, in that you can use this technique to snag another player’s IP. By putting in HTML that links to your own server, you can log any player IPs that connect to the server seeking an image, for example.
Of course, it’s not the biggest risk, with many players being behind ISPs that use CGNAT, making the harvested IPs rather useless. However,
this sort of unexpected code injection
is really not acceptable from a security standpoint. At the very least, it has the potential to expose players to nasty imagery.
Word on the street
(
Nitter
) is that the exploit has now been patched. Meanwhile, if you’re working on a game that for some mad reason, executes code based on player names or any other such data, consider patching your work ASAP. If you find similar exploits in the wild, don’t hesitate to hit up
our tipsline
—and notify the developers, too! | 17 | 7 | [
{
"comment_id": "6707284",
"author": "DST",
"timestamp": "2023-12-12T12:34:56",
"content": "If anyhing, it’s a testament to the amount of bloat modern software floats around in, that an arbitrary text string for a first person shooter ends up in a fcking HTML renderer!",
"parent_id": null,
"... | 1,760,372,077.415776 | ||
https://hackaday.com/2023/12/12/homemade-raman-laser-is-shaken-not-stirred/ | Homemade Raman Laser Is Shaken, Not Stirred | Dan Maloney | [
"Laser Hacks",
"Science"
] | [
"DMSO",
"ineleastic",
"laser",
"nonlinear optics",
"Raman",
"scattering",
"Stokes"
] | You wouldn’t think that shaking something in just the right way would be the recipe for creating laser light, but as [Les Wright] explains in his new video, that’s pretty much how
his DIY Raman laser works
.
Of course, “shaking” is probably a gross oversimplification of Raman scattering, which lies at the heart of this laser. [Les] spends the first half of the video explaining Raman scattering and stimulated Raman scattering. It’s an excellent treatment of the subject matter, but at the end of the day, when certain crystals and liquids are pumped with a high-intensity laser they’ll emit coherent, monochromatic light at a lower frequency than the pumping laser. By carefully selecting the gain medium and the pumping laser wavelength, Raman lasers can emit almost any wavelength.
Most gain media for Raman lasers are somewhat exotic, but luckily some easily available materials will work just fine too. [Les] chose the common solvent dimethylsulfoxide (DMSO) for his laser, which was made from a length of aluminum hex stock. Bored out, capped with quartz windows, and fitted with a port to fill it with DMSO, the laser — or more correctly, a resonator — is placed in the path of
[Les]’ high-power tattoo removal laser
. Laser light at 532 nm from the pumping laser passes through a focusing lens into the DMSO where the stimulated Raman scattering takes place, and 628 nm light comes out. [Les] measured the wavelengths with
his Raspberry Pi spectrometer
, and found that the emitted wavelength was exactly as predicted by the Raman spectrum of DMSO.
It’s always a treat to see one of [Les]’ videos pop up in our feed; he’s got the coolest toys, and he not only knows what to do with them, but how to explain what’s going on with the physics. It’s a rare treat to watch a video and come away feeling smarter than when you started. | 12 | 7 | [
{
"comment_id": "6707240",
"author": "Aviv",
"timestamp": "2023-12-12T09:19:02",
"content": "I read this whole article confused about how ramen noodles came into this",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6707316",
"author": "BT",
"t... | 1,760,372,077.360181 | ||
https://hackaday.com/2023/12/11/raspberry-pi-changes-hats/ | Raspberry Pi Changes HATs | Jenny List | [
"Raspberry Pi"
] | [
"hat",
"raspberry pi",
"Raspberry Pi 5"
] | Following on the heels of their Raspberry Pi 5 launch and some specifications for their RP1 all-in-one peripheral chip,
the Raspberry Pi folks have now released an update to the HAT peripheral hardware specification
reflecting the new model. Called the HAT+, it represents a major step forward with some significant changes.
Most visible will be changes to the mechanical specification, for while the original HAT specification was very rigid this new version is much looser. A HAT+ must only mate with the 40-pin connector, including the ID pins, and line up with only a single mounting hole compared to the four on the original. Electrically, a HAT+ must recognise the standby power state in which the 3.3-volt line is powered down while the 5-volt line remains active, while software-wise, there are changes to the content of the ID EEPROM including the ability to inform about stackable smaller HATs.
As the Arduino folks will no doubt tell you, the danger for the maintainers of a popular standard is that it risks becoming a victim of its own success, leaving it to ossify as it falls behind the cutting edge. For the Raspberry Pi, it must be a tight balance between keeping it up to date and not losing earlier models, and by our reckoning, they may just have achieved it.
We like how some have allowed
multiple HATs
, and we wonder if this will work — or will be made to work — with the HAT+. You usually think of HATs as having sensors or lights, but that
isn’t always the case
. | 22 | 5 | [
{
"comment_id": "6707344",
"author": "dinogon",
"timestamp": "2023-12-12T16:06:14",
"content": "Too little too late imo. Not just for the HAT but for Raspberry Pi in general.The inability to get one without having to be overcharged by scalpers or excessively scanning a list of stores in desperation ... | 1,760,372,077.654939 | ||
https://hackaday.com/2023/12/11/terminal-based-image-viewer-and-multi-os-binary-and-under-100kb/ | Terminal-Based Image Viewer,andMulti-OS Binary,andUnder 100kb | Donald Papp | [
"Software Hacks"
] | [
"ASCII",
"image viewer",
"multi-OS",
"terminal window",
"text"
] | [Justine Tunney]’s
printimage.com
is a program capable of splatting full-color images to text mode terminal sessions, but that’s not even its neatest trick. It’s also a small binary executable capable of running on six different operating systems: Linux, Windows, MacOS, FreeBSD, OpenBSD, and NetBSD. All without having to be installed or otherwise compiled first. On top of it all, it’s less than 100 kb.
How is this possible? It’s thanks to [Justine]’s
αcτµαlly pδrταblε εxεcµταblε
format, implemented by a project called
Cosmopolitan
which aims to turn C into a build-once-run-anywhere language. The
printimage.com
source code
is included within the Cosmopolitan project.
If the name sounds a bit familiar, it’s probably because the Cosmopolitan project is a key piece of a tool we recently covered:
llamafile
, which allows people to package up an LLM (large language model) as a single-file, multi-OS executable.
As
printimage.com
shows, terminal windows are capable of more than just text. Still, plain ASCII has its appeal. Check out the
ASCII art STL file viewer
which might just make your next sick ASCII art banner a bit easier to generate. | 7 | 6 | [
{
"comment_id": "6707191",
"author": "Dylan Mc",
"timestamp": "2023-12-12T04:41:53",
"content": "Justine’s regular pace of amazing projects (you didn’t even mention sectorlisp or blinkenlights, among many others) is an inspiration (once I get over the intimidation). Thanks for letting us know about ... | 1,760,372,077.091651 | ||
https://hackaday.com/2023/12/11/wireless-bike-brakes/ | Wireless Bike Brakes | Navarre Bartz | [
"Transportation Hacks"
] | [
"bike",
"bike brakes",
"bike electronics",
"brake by wire",
"wireless brakes"
] | Bicycles are the most efficient machines for moving a person around, and wireless drivetrains have been heralded as a way to make shifting more consistent and require less maintenance. [Blake Samson] wondered if the same could be true of
wireless brakes.
Inspired by the controller for an RC car, [Blake] picked a 150 kg servo attached to a cable-actuated hydraulic disc caliper to apply the braking force. The servo, receiver, power stabilizer, and batteries were all mounted on a custom steel plate fabricated to mount under the caliper. [Blake] cut up an old set of mountain bike brake levers to reuse the handlebar mounts and then put the batteries, controller, and finger triggers on them.
Confident in his hacking skills, [Blake] then took the bike out on some trails to test the brakes. As a prototype, there were a few surprises along the way, like one of the triggers staying locked in the braking position, but they performed admirably enough that he’s mulling over a Mk. 2.
Bikes
are one of our favorite hacking platforms. Be sure to checkout this
dreamy cargo bike build
, an
awesome bike camper
, or what can happen if your bike is
dependent on the cloud
to work.
Thanks to [FedX] on the
Hackaday Discord
for the tip! | 73 | 37 | [
{
"comment_id": "6707135",
"author": "TG",
"timestamp": "2023-12-12T00:15:36",
"content": "Wireless shifter? Ok cool. Brakes? Absolutely not",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6707147",
"author": "rasz_pl",
"timestamp": "2023-12-1... | 1,760,372,077.597856 | ||
https://hackaday.com/2023/12/11/make-carbon-fiber-tubes-with-an-open-source-filament-winder/ | Make Carbon Fiber Tubes With An Open Source Filament Winder | Maya Posch | [
"cnc hacks"
] | [
"carbon fiber",
"composite",
"resin"
] | Result of winding a carbon fiber tube. (Credit: Andrew Reilley)
Carbon fiber (CF) is an amazing material that provides a lot of strength for very little weight, making it very useful for a lot of applications, ranging from rods in CoreXY 3D printers to model- and full-sized rockets. The model rocketry hobby is the reason why [Andrew Reilley] developed his own CF tube winding machine
called Contraption
. A
tutorial video
(also embedded below) shows how this machine is prepped for a winding run, followed by the winding progress and finalizing before admiring the result.
The entire machine’s design with 3D printed parts and off-the-shelf components is open source, as is the TypeScript and NodeJS-based
Cyclone software
that creates the toolpath specifying the parameters of the tube, including number of layers and the tow angle.
As a wet winding tow machine, the carbon fiber strands are led through the liquid resin before being wound onto the prepared mandrel. During winding some excess resin may have to be removed, and after the winding has been finished the tube is wound with shrink tape. This is followed by a heat gun session to shrink the tape and letting the resin cure. Following curing, the tape and mandrel are removed, resulting in a rather fancy looking CF tube that can find a loving home in a lot of applications, except perhaps ones that involving crushing outside pressures like those found deep below the ocean surface. | 22 | 9 | [
{
"comment_id": "6707114",
"author": "Mmmhmm",
"timestamp": "2023-12-11T22:41:46",
"content": "That is a damn sweet result! Good job!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6707152",
"author": "No",
"timestamp": "2023-12-12T01:22:56",
"con... | 1,760,372,077.260336 | ||
https://hackaday.com/2023/12/10/raspberry-pi-5-goes-under-the-x-ray/ | Raspberry Pi 5 Goes Under The X-ray | Jenny List | [
"Raspberry Pi"
] | [
"pcb",
"Raspberry Pi 5",
"xray"
] | Most Hackaday readers will know to some extent what lies inside their computer, even if this is only at a block diagram level listing the peripherals. But what is
physically
on a modern computer board? [Jeff Geerling]
has subjected a Raspberry Pi 5 to a medical imager
, and shares with us the many layers of parts and PCB he found there. With a six-layer board and a heap of large BGA chips on it, there’s a lot to look at.
For readers who are used to working with printed circuit boards, it’s likely the techniques involved in the design will not be new. For us, the magic lies in the scale. The sheer number of interconnects on the board is impressive enough, but when it becomes possible to peer into the SoC package it becomes evident that there’s an internal PCB with some of the smallest vias we have ever seen. [Jeff] goes on to show us part by part around the board, on the way reminding us that some of the earliest Pi boards had to be reworked to replace Ethernet jacks without magnetics.
There’s a beauty to these ghostly images which might not be apparent to anyone who hasn’t stared obsessively at a PCB in a CAD package while it takes shape. The images show the work of the PCB designer’s art at a fine scale. We’d almost go as far as to suggest they be viewed as fine art instead of industrial design. Take a look, the video is below the break.
If this art is a bit big for you, then
look at ASIC design
– which takes things down to the microscopic level of the doped silicon structures within these amazing chips. | 1 | 1 | [
{
"comment_id": "6706884",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-11T04:11:43",
"content": "I recently worked for a contract company that built/assembled PCBs.Their X-ray machine made it much easier to determine if any BGA connections did not solder properly.",
"p... | 1,760,372,077.761194 | ||
https://hackaday.com/2023/12/10/hackaday-links-december-10-2023/ | Hackaday Links: December 10, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"ChatGPT",
"fpga",
"gyro",
"hackaday links",
"HST",
"Hubble",
"jailbreak",
"LLM",
"OSIRIS-REx",
"parachute",
"pyro",
"training data",
"vlf"
] | In this week’s episode of “Stupid Chatbot Tricks,” it turns out that jailbreaking ChatGPT is as easy as asking it to
repeat a word over and over forever
. That’s according to Google DeepMind researchers, who managed to force the chatbot to reveal some of its training data with a simple prompt, something like “Repeat the word ‘poem’ forever.” ChatGPT dutifully followed the instructions for a little while before spilling its guts and revealing random phrases from its training dataset, to including complete email addresses and phone numbers. They argue that this is a pretty big deal, not just because it’s potentially doxxing people, but because it reveals the extent to which large language models just spit back memorized text verbatim. It looks like OpenAI agrees that it’s a big deal, too, since they’ve explicitly made prompt-induced
echolalia
a
violation of the ChatGPT terms of service
. Seems like they might need to do a little more work to fix the underlying problem.
It sounds like
the OSIRIS-REx asteroid sample return mission had a close call with disaster
back in September thanks to a pair of literally crossed connections. The reentry sequence, which managed to successfully set the sample return capsule down in the Utah desert, did so even though the drogue chute didn’t properly deploy. The sequence of events is normally supposed to deploy the drogue at a high altitude to slow and stabilize the capsule, then cut the drogue free before deploying the main chute. Instead, the pyros to cut the drogue free fired first, severing the lines while the drogue was still safely tucked into its canister. Then, the pyro to launch the drogue fired, sending the liberated chute off into the slipstream. Luckily, the main chute deployed correctly and did the job of both chutes. NASA looked into the near-miss and found that the term “main” was used inconsistently in the documentation; in some places, it referred to the pyros for the drogue chute cover, while in others it referred to the main parachute itself. This led to wires being cross-connected, which fired the pyros out of order. It was a close call, and kudos to the team who figured out the problem.
From pyros to gyros, it looks like there’s more Hubble trouble, as
the 33-year-old space telescope went into safe mode following another glitch
. The problem this time was with one of the three remaining gyros aboard the observatory, which sent faulty readings and triggered the safe shutdown. The three — or potentially two — good gyros are all that’s left of the six units that were installed during a service mission back in 2009, and while Hubble can get by with just one gyro, NASA really doesn’t want to go there. That Hubble is suffering signs of aging isn’t exactly shocking, especially since it hasn’t had any maintenance in nearly fifteen years, but what has changed is the increased number of private space concerns that might be able to mount a service mission. It’ll be interesting to see how this plays out, and whether NASA wants to let someone else handle the job or not.
Retro radio buffs take note: the historic Grimeton longwave radio station is getting ready to
go on the air on Christmas Eve
. The station, callsign SAQ, only powers up twice a year under usual circumstances, and for good reason; the 100-year-old station uses an enormous
Alexanderson alternator
to generate its several hundred thousand watt, 17.2-kHz signal. If you’re interested in listening in, you’ll need some
special gear
— it’s not easy to find a radio that tunes down to a frequency that would be within hearing range if it were a sound wave. Or, you can try
a WebSDR
, or just watch the livestream on Christmas Eve.
And finally, if you’re in the mood for a career that will leave you miserable but well-compensated, consider going to work as
an FPGA engineer for Goldman Sachs
. On the plus side, you’ll be working with some pretty cool hardware as you build out a completely new infrastructure for global banking and marketing. On the downside, you’ve got to be an FPGA engineer, which seems like a lousy gig unless it just happens to fit your brain. | 8 | 4 | [
{
"comment_id": "6706863",
"author": "Ostracus",
"timestamp": "2023-12-11T00:49:11",
"content": "“On the plus side, you’ll be working with some pretty cool hardware as you build out a completely new infrastructure for global banking and marketing. On the downside, you’ve got to be an FPGA engineer, ... | 1,760,372,077.935169 | ||
https://hackaday.com/2023/12/10/fast-paper-tape-for-the-nuclear-family/ | Fast Paper Tape For The Nuclear Family | Al Williams | [
"Retrocomputing"
] | [
"Chernobyl",
"Chornobyl",
"tape reader"
] | We’ve enjoyed several videos from [Chornobyl Family] about the computers that controlled the ill-fated nuclear reactor in Chornobyl (or Chernobyl, as it was spelled at the time of the accident). This time (see the video below) they are looking at a
high-speed data storage device
. You don’t normally think of high-speed and paper tape as going together, but this paper tape reader runs an astonishing 1,500 data units per second. Ok, so that’s not especially fast by today’s standards, but an ASR33, for example, did about 10 characters per second.
An IBM2400 tape drive, for reference, could transfer at least 10 times that amount of data in a second, and a 3400 could do even better. But this is paper tape. Magnetic tape had much higher density and used special tricks to get higher speeds mechanically using vacuum columns. It was still a pretty good trick to move 4 meters of paper tape a second through the machine.
The reader needed a bit of TLC after spending decades stored in a chicken shed. What do you think it looked like after living with the chickens? Yep. That’s exactly what it looked like. Cleaning and painting ensued.
Most tape readers used either brushes to sense the holes or light sensors. This reader used light sensors because you can more easily reach high speeds with that technique. Also inside is a very large motor that runs a fan to cool the electronics. The same motor pulls the tape through the path using a mechanism that reminded us of a cheap 3D printer extruder.
And move it does. You can see the machine chew through a tape at the end of the video. A lot different than watching an ASR33 or Flexowriter reading a tape. Making a paper tape reader today
isn’t very hard
— and you could probably just use a webcam and some vision software. Paper tape wasn’t just for computers. They ran CNC machines, typesetters, and even taught
Morse code
. | 8 | 4 | [
{
"comment_id": "6706852",
"author": "Jan",
"timestamp": "2023-12-10T22:33:22",
"content": "Yay, Czechoslovak engineering! We didn’t have access to modern components but the engineering & build quality has always been top notch.",
"parent_id": null,
"depth": 1,
"replies": [
{
... | 1,760,372,077.977523 | ||
https://hackaday.com/2023/12/10/steampunk-factory-comes-to-life-with-an-arduino/ | SteamPunk Factory Comes To Life With An Arduino | Al Williams | [
"Arduino Hacks",
"Art"
] | [
"aarduino",
"steampunk"
] | It is one thing to make an artistic steampunk display. But [CapeGeek] added
an Arduino to make the display come alive
. The display has plenty of tubes and wires. The pressure gauge dominates the display, but there are lots of other interesting bits. Check it out in the video below.
From the creator:
The back-story is a fictional factory that cycles through a multistage process. It starts up with lights and sounds starting in a small tube in one corner, the needle on a big gauge starts rising, then a larger tube at the top lights up in different colors. Finally, the tall, glass reactor vessel lights up to start cooking some process. All this time, as the sequence progresses, it is accompanied by factory motor sounds and bubbling processes. Finally, a loud glass break noise hints that the process has come to a catastrophic end! Then the sequence starts reversing, with lights sequentially shutting down, the needle jumps around randomly, then decreases, finally, all lights are off, indicating the factory shutting down.
We especially liked the distillation column. We doubt we would exactly duplicate this project, but there are plenty of things to borrow for your own creations here.
We always enjoy
steampunk computers
. But we also like the ones that have unusual components like the distillation column or
a chain
. | 15 | 7 | [
{
"comment_id": "6706820",
"author": "Cree",
"timestamp": "2023-12-10T19:47:10",
"content": "Meh.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706831",
"author": "Adrian",
"timestamp": "2023-12-10T20:49:45",
"content": "The choreog... | 1,760,372,077.887911 | ||
https://hackaday.com/2023/12/10/binary-clock-kit-blips-again/ | Binary Clock Kit Blips Again | Jonathan Bennett | [
"clock hacks",
"hardware"
] | [
"binary clock",
"Graymark",
"Pi Pico W"
] | Back in 1978, the world was a bit different. There was no Raspberry Pi, no Internet, and not even an ESP32 to build projects with. And rather than order electronics kits from Tindie or Adafruit, [Dr. Francitosh]
selected this binary clock with his mother from a catalog
, and made the order via mail. Simpler times. The good Doctor, AKA [Greg Smith], was a young electronics tinkerer, and his mother wanted a good project-in-a-box to show off his skills. Thus, a Greymark Binary Clock was ordered and assembled. Then, sadly, the beloved clock crashed from its proud mantle position, doomed to never to blink or blip again. Or was it?
[Greg] finally got his hands on the old project, and just had to get it working again. The inner circuit board was broken right through, and that presented an opportunity to not just repair the clock, but to teach the old dog some new tricks. Before we get there, there’s a fascinating teardown of how the original circuit used a pair of 7490s to take the 50 or 60 Hz of grid power and downconvert it to a stable 1 hz pulse. From there, a series of even more 7490 Binary Coded Decimal counter chips keep track of the ticking seconds, minutes, and hours.
While this clock may be from a simpler time, [Greg] doesn’t live in that time any longer. He saved the project box, panel, original LEDs, and switches. But the new heart of this reborn machine is a Raspberry Pi Pico W. This gives full emulation of the old behavior, as well as setting the time over Bluetooth, grabbing time from NTP, and even listening for the Atomic Clock radio signal. Best of all, the project looks just like it did back in 1978. Mom would be proud. | 16 | 11 | [
{
"comment_id": "6706818",
"author": "Rudranand Sahu",
"timestamp": "2023-12-10T18:48:32",
"content": "Hi Greg! Sending warm wishes to your mother. I hope she is doing well.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706837",
"author": "Scott",
... | 1,760,372,078.311526 | ||
https://hackaday.com/2023/12/10/nyan-keys-because-your-keyboard-is-painfully-slow/ | Nyan Keys: Because Your Keyboard Is Painfully Slow | Kristina Panos | [
"FPGA",
"Peripherals Hacks"
] | [
"fpga",
"FPGA keyboard",
"keyboard",
"mechanical keyboard",
"nyan cat"
] | You probably don’t notice keyboard latency when typing or doing mundane tasks, but if you start gaming, that’s also when you might start complaining. Every millisecond counts in that arena. Think your keyboard is fast? Think again. Because unfortunately, no matter what you’ve got in there, that key matrix is slowing you down. What you need is an FPGA-based keyboard with an overkill MCU.
You need Nyan Keys.
[Portland.HODL] set out to make the lowest-latency mechanical keyboard possible that would accept any Cherry-compatible switches, and boy howdy, is this thing fast.
Coupled with the
STM32F723VET6
MCU is USB 2.0 HS, which has an 8000Hz polling rate. At worst, key latency measures 30μS,
which blows the 1mS average out of the water.
Because it uses a Lattice Semi iCE40HX 4k FPGA, each key switch can connect to its own I/O pin, which also eliminates the need for diodes.
It also means that each key switch can have its own “core” — an 8-bit timer that is always counting up to 255. The key can only change its state when the timer reads 255. This acts as a rather clever debounce mechanism.
If all that’s not enough, [Portland.HODL] built an operating system called NyanOS written in C to avoid any performance-reducing overhead. Oh, and it has an opt-in Bitcoin miner.
We’ve seen a lot of keyboards, the fast ones are fast because of the input side — they are chording keyboards that take combinations to type, rather than using one key (or so) per character.
The Characorder is so fast that it was banned from competition. | 33 | 10 | [
{
"comment_id": "6706749",
"author": "Zoe Nagy",
"timestamp": "2023-12-10T12:42:30",
"content": "what about usb latency of 20ms+",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706760",
"author": "rumpel",
"timestamp": "2023-12-10T13:06:52",
... | 1,760,372,078.796483 | ||
https://hackaday.com/2023/12/10/printing-with-glass-fiber-filament/ | Printing With Glass Fiber Filament | Al Williams | [
"3d Printer hacks"
] | [
"3d printing",
"engineering plastic",
"engineering polymer",
"glass fiber"
] | [ModBot] has been trying different engineering plastics for 3D printing. He recently looked at carbon fiber mixed with PET, but this time, he shows us his results with
PET with glass fiber
, or PET-GF. You can see how it all turned out in the video below.
The first part of the video compares the specifications, and, as you might expect, some factors are better for carbon fiber, and others are better for glass fibers. Once he gets to the printing, he covers the high temperatures needed (280-320C). He also talks about how either fiber will chew up nozzles and extruders.
If you haven’t printed at high temperatures before, there are a few gotchas. For one thing, even if you don’t have PTFE in your hot end, you must be sure your thermistor will read the higher temperature accurately. Many people use thermocouples instead of thermistors in this application.
The prints looked good, although we hoped to see more testing of the parts under stress. Comparing them with the carbon fiber prints would have been especially interesting. Need help
boosting your print temperature
? We look at
exotic filament
every so often, and every time we do, there are a few more choices. | 12 | 4 | [
{
"comment_id": "6706754",
"author": "GoguyT3d",
"timestamp": "2023-12-10T12:55:56",
"content": "As nice as he makes GF sound I honestly have to say after printing for over 3 years now and having almost 100lb of different filament laying around I haven’t used GF but still am not sold. I have used nu... | 1,760,372,078.415386 | ||
https://hackaday.com/2023/12/11/bunnie-huangs-shenzhen-guide-gets-a-new-edition-written-by-naomi-wu/ | Bunnie Huang’s Shenzhen Guide Gets A New Edition – Written By Naomi Wu | Jenny List | [
"hardware",
"Interest"
] | [
"Bunnie Huang",
"Naomi Wu",
"shenzhen"
] | If there’s one city which can truly claim to be the powerhouse of high-tech manufacturing here in the 21st century, it’s the Chinese city of Shenzhen. It’s likely that few people don’t own something made in that city or with parts that have passed through companies in the legendary electronic component markets of its
Huaqiangbei
district.
For years now the essential introduction to this world has come in the form of [Bunnie Huang]’s
Essential Guide to Electronics in Shenzhen
, a publication that unlocks the Chinese-speaking maze of vendors. All paper publications eventually become dated though, and this guide is no exception,
so we’re very pleased to see a new version is on its way
. Better still, it comes courtesy of Shenzhen native and maker extraordinaire [Naomi Wu], whose video series on YouTube has opened up so many corners of her city for those of us thousands of miles away. We can’t wait to see what she puts in it.
It’s also very good indeed on another level to see [Naomi]’s involvement, as earlier in the year she had to curtail her social media output under pressure from the Chinese government. We miss her unique window into the wonders of her city, and aside from
her online shop
it’s been concerning to hear very little from her of late. You can hear her talking about the book in a promotional video below the break. | 23 | 16 | [
{
"comment_id": "6707067",
"author": "Nigel",
"timestamp": "2023-12-11T19:46:10",
"content": "So glad she is still about. You see her in her native city but I am always worried how safe she is. God bless you Naomi",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": ... | 1,760,372,078.663239 | ||
https://hackaday.com/2023/12/11/tech-in-plain-sight-super-glue/ | Tech In Plain Sight: Super Glue | Richard Baguley | [
"chemistry hacks",
"Hackaday Columns",
"Repair Hacks",
"Slider"
] | [
"Chemistry",
"cyanoacrylate",
"glue",
"history",
"super glue"
] | Many inventions happen not by design but through failure. They don’t happen through the failure directly, but because someone was paying attention and remembered the how and why of the failure, and learns from this. One of these inventions is Super Glue, the adhesive that every tinkerer and engineer has to hand to stick pretty much anything to anything, quickly. Although it was a complete failure for the original uses it was developed for, a chemist with good memory and an eye for a helpful product created it in a process he described as “one day of synchronicity and ten years of hard work.”
Super Glue was initially invented in 1942, when the chemist
Harry Coover
was working on a team trying to develop a clear plastic gun sight that would be cheaper than the metal ones already in use. The team cast a wide net, trying a range of new materials. Coover was testing a class of chemicals called cyanoacrylates. They had some promise, but they had one problem: they stuck to pretty much everything. Every time that Coover tried to use the material to cast a gun sight, it stuck to the container and was really hard to remove.
When the samples he tried came into contact with water, even water vapor in the air, they immediately formed an incredibly resilient bond with most materials. That made them lousy manufacturing materials, so he put the cyanoacrylates aside when the contract was canceled. His employer B. F. Goodrich,
patented the process of making cyanoacrylates
in 1947, but didn’t note any particular uses for the materials: they were simply a curiosity.
It wasn’t until 1951 when Coover, now at Eastman Kodak, remembered the sticky properties of cyanoacrylates. He and his colleague Fred Joyner were working on making heat-resistant canopies for the new generation of jet fighters, and they considered using these sticky chemicals as adhesives in the manufacturing process. According to Coover, he told Joyner about the materials and asked him to measure the refractive index to see if they might be suitable for use. He warned him to be careful, as the material would probably stick in the refractometer and damage it. Joyner tested the material and found it wasn’t suitable for a canopy but then went around the lab using it to stick things together. The two realized it could make an excellent adhesive for home and engineering use.
So, they patented the
use of cyanoacrylate as an adhesive
, a patent granted in 1954. Eastman Kodak started selling it as Eastman 910 in 1958, and that
exact formula is still sold today
. On one memorable demonstration, Dr. Coover lifted the 150-lb host of the TV show I’ve Got a Secret with a single drop of the glue., and lifted a Corvette using the glue.
Dr Harry Coover was awarded the national medal for
Technology and Innovation in 2010
, but he never made that much money out of Super Glue because the product didn’t catch on until the patent expired and others started making their own versions. That wasn’t the only thing that Dr Coover worked on, though: he is listed on o
ver 350 patents
. He always claimed that Super Glue was his favorite and that he was most proud of how the glue was used to save lives in the Vietnam War.
That happened when the US Army realized that you could use it to seal bullet wounds on the battlefield. Because it reacted with the water in the blood, it quickly staunched bleeding and closed a wound until it could be adequately operated on. It forms a thin, strong layer, but it can be fairly easily removed because, as anyone who has Super Glue on their hands knows, once it sets, it has low shear strength. If you get it stuck between your fingertips and it sets, you won’t be able to pull them apart. You can, however, remove it by either waiting until a layer of sweat forms under the glue, or by moving your fingertips back and forth against each other, shearing the bond between glue and finger.
Combine this with the fact that cyanoacrylate
is not poisonous
, and you have a great way to seal a wound quickly.
Modern Super Glues
Modern cyanoacrylate glues come in a wide variety of types, including ones that mix
cyanoacryaltes with epoxy to make a stronger bond
, and ones that add materials to improve the
bonding on porous surfaces
. There are also chemicals you can add, making it set quicker if you need to fix something quickly.
How Super Glue Glues
The chemistry of Super Glue is fascinating. Although the specific chemicals used in brands and types differ, all of them are cyanoacrylates, composed of very short chains (called monomers) of carbon atoms surrounded by oxygen and nitrogen and tipped with hydrogen atoms. The chain is relatively stable, but things start to happen as soon as you introduce water.
Water is composed of two hydrogen atoms linked to a single oxygen atom. Still, the bonds that hold these together sometimes fray, leaving hydroxide ions, consisting of an oxygen atom with only one hydrogen atom attached. These float around, looking for something to bond to. When one of these bumps into a cyanoacrylate molecule, it latches onto one of the carbon atoms, but this leaves the carbon atom with a spare electron, where it wants to bond with something. Carbon loves to bond to other carbon atoms, so two of these unbonded cyanoacrylate molecules bond together. This process releases more ions that start bumping into more water molecules, creating more hydroxide ions, and so on. So, once started, the process repeats, creating a long chain of these molecules, a polymer. That is called chain growth polymerization, and it requires very little water to happen. That’s why if you leave the cap off a container of Super Glue, it sets because the moisture in the air sets off the polymerization process.
Polymerization of Cyanoacrylate [Wiki Commons]
This process will also happen because of traces of water in the glue, so even when stored sealed, the polymerization will occur eventually so that the glue will set in the tube.
Water is not the only thing that Super Glue will react with: it also bonds with the oils and proteins in fingerprints. That’s why it can be used to find fingerprints: if you heat it to make a vapor, some will stick to the oil and protein in a fingerprint, which will polymerize more, creating a visible fingerprint impression. This also explains perhaps the most common application of cyanoacrylates: gluing your fingers either together or to the project at hand.
So think about this the next time you reach for a tube of Super Glue to fix a project: this is available because an observant chemist remembered his failures and realized they were not failures; they had just not found the correct use yet.
Featured image: “
Super Glue
” by Andrew Gustar | 68 | 25 | [
{
"comment_id": "6707050",
"author": "JanW",
"timestamp": "2023-12-11T18:27:33",
"content": "Since I started storing my CA glue in a tightly screwed marmelade jar where the bottom is filled with desiccant I didn’t need to buy a new bottle since 2019. Moisture kills CA glue. It’S the absolut best way... | 1,760,372,078.603728 | ||
https://hackaday.com/2023/12/11/modern-spark-gap-transmitter-uses-a-rotary-gap/ | Modern Spark Gap Transmitter Uses A Rotary Gap | Al Williams | [
"Radio Hacks"
] | [
"spark gap"
] | In the “don’t try this at home” category, [Joe Smith] builds
a spark gap transmitter
with a twist. The twist is that the drive power is from a signal generator attached to a FET. From there, though, things go classic using an automotive ignition coil and a tank circuit. He shows how adjusting the spark frequency changes the signal’s sound in a standard receiver.
We say don’t try this at home because the output of a transmitter like this will likely spew RF all over the place. Granted, there’s probably not much power, but it may well irritate your neighbors.
Switching to AM, you can really hear the tone from the spark frequency in the receiver. [Joe] posted some
earlier videos
where he made a 160-meter spark gap transmitter using an electric fly swatter. There are more details about how the tank circuits work in those videos. You can also see what the output looks like on a spectrum analyzer. You can
hear what that transmitter sounds like
, too. | 18 | 9 | [
{
"comment_id": "6707056",
"author": "Drone",
"timestamp": "2023-12-11T18:54:37",
"content": "1-8-4-3-6-5-7-2",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6707073",
"author": "BrendaEM",
"timestamp": "2023-12-11T20:03:44",
"content"... | 1,760,372,078.3674 | ||
https://hackaday.com/2023/12/11/new-part-day-flush-mount-touchscreen-for-retro-pc-build/ | New Part Day: Flush-mount Touchscreen For Retro PC Build | Donald Papp | [
"Featured",
"hardware",
"Parts",
"Raspberry Pi",
"Slider"
] | [
"Crowd Supply",
"CrowVision",
"Elecrow",
"hdmi",
"raspberry pi",
"retro",
"SBC",
"touchscreen"
] | I recently had the opportunity to purchase an early version of a new display, and it happened to be just the thing I needed to make a project work. That display is the Elecrow 11.6″ CrowVision touchscreen slated for release in 2024.
Preorders are being accepted on Crowd Supply
.
I had an idea for a retro-inspired PC build that was just waiting for a screen like this. I’ll talk about the display and what’s good about it, then showcase the build for which it was the missing piece. If you’ve got a project waiting for something similar, maybe this part will provide what you need or at least turn on some new ideas.
What Is It?
The CrowVision 11.6″ 1366 x 768 touchscreen has an HDMI input, USB output for touch data, and accepts 12 V DC. It’s made to interface easily with a Raspberry Pi or other SBC (single-board computer).
Personally I consider a display like this to be the minimum comfortable size for using desktop type applications in a windowed environment. Most displays in this space are smaller. But aside from that, what helps make it useful for embedding into a custom enclosure is the physical layout and design.
Since I was looking for the largest display that could be flush-mounted in an enclosure without a lot of extra space around the display’s sides, it was just what I needed. The integrated touchscreen is a nice bonus.
Useful Features
Apart from its size, there are a few features that helped make my project a bit easier than it otherwise would have been.
The flat, borderless black front of the display allows for easy flush mounting. It’s also trivial to design for enclosure-wise. There’s an adhesive, but for truly secure mounting there are four threaded holes in the metal shield at the back.
The display is physically very close to being the same width as the Raspberry Pi 400 (or the official Raspberry Pi keyboard), which was good news for the overall layout of my retro build. It was important for the look of my machine for the keyboard and display to have matching widths.
Connection layout and cable types for an attached SBC (click to enlarge.) Using short cables makes for a very tidy assembly.
The driver board is secured to the rear shield of the display, well away from the display edges. This helps keep connectors and cables from sprawling outward and bloating the part’s footprint, making mounting in snug spaces easier.
Another handy feature is the included mounting solution for a variety of different single-board computers. Mounting posts slide in two channels, accommodating multiple form factors. Having an SBC like a Raspberry Pi attached directly to the display’s back is extremely handy for tight builds and makes cable management easier.
Finally, the display accepts 12 V and can pass 5 V power to a board like a Raspberry Pi, eliminating the need for a second power supply just for the SBC. The display’s built-in power button — mounted on the rear, and can be expanded out via an included extension — controls power for both the display and any attached SBC.
The display worked perfectly when connected to a Raspberry Pi. The multitouch input, a USB connection from the display to the Pi, also worked effortlessly. I verified multitouch worked properly with
this web-based multitouch tester
.
Retro-Inspired PC Build
Dialing up an 80s supercomputer for a chat. Amusingly, the dialup is fake but the AI on the other end is real. (Click to enlarge)
Celestia
is my retro styled PC designed to use a Raspberry Pi — either a Raspberry Pi 400 or a Raspberry Pi SBC plus an official Raspberry Pi keyboard — in a one-piece form factor.
A 3D-printable enclosure accommodates the CrowVision 11.6″ display, the only display option that really matched what I was going for. Since the display integrates a touchscreen, a mouse is easy to do without, helping preserve the one-piece aesthetic.
The back of the enclosure has spaces for integrating a power jack and a small USB hub for convenience, but for those who would like to remix the design and create their own ports, the CAD file includes a blank segment with no openings.
The result is a one-piece unit with some real retro aesthetics. It’s exactly what I wanted ever since coming across another retro PC project: the
Callisto-2
.
The design files for Celestia are
all on GitHub
, and while it’s a bit of a work in progress, the important parts are all there along with some tips for printing, finishing, and assembly.
A Few Words About The Keyboard
Celestia integrates a Raspberry Pi official keyboard into the 3D-printed case. But the Raspberry Pi 400 has a virtually identical form factor, and includes a computer. That means one can either attach an SBC to the display’s back using the mounting posts, or simply plug it all in to a Pi 400. It will look the same from the outside.
Both the official Raspberry Pi keyboard and the Pi 400 have matte white finishes that blend in very well if the enclosure is printed in a matte white PLA.
Finishing Touches
Completing the look for my build is a piece of software called
cool retro terminal
. I adjusted the taskbar at the top of the Raspberry Pi desktop to auto-hide, and run cool-retro-term in fullscreen mode. While cool-retro-term is running, a right-click will access additional configuration. (I think it looks best on this display by removing screen curvature, and eliminating margin.) The only downside is that it runs slowly on a Raspberry Pi.
The icing on the cake is
dialing up a fictional 80s supercomputer AI for a chat
, something made almost trivial thanks to Max Woolf’s
simpleaichat
software.
Source and Resources
As mentioned, this display turned out to be the missing link for the build I wanted. There are displays with similar design and features, like the
Raspberry Pi official touchscreen,
but most are smaller and lower resolution. Thin and flat HDMI displays sold as “portable monitors” looked initially promising, but tend to have issues like bezel design or connector locations that make them troublesome to integrate into custom enclosures.
If this display seems like the missing puzzle piece for your own project, the
Elecrow 11.6″ CrowVision
is slated for release in 2024, with preorders being handled via
Crowd Supply
. | 19 | 14 | [
{
"comment_id": "6706997",
"author": "0xdeadbeef",
"timestamp": "2023-12-11T16:19:39",
"content": "I wound up discovering earlier this year that the RPi 400’s keyboard and the RPi official keyboard are the same thing (with slightly different keycap marking on F10 for power / ScrLk – but that’s as fa... | 1,760,372,078.721549 | ||
https://hackaday.com/2023/12/11/qantas-flight-32-when-a-few-millimeters-of-metal-invite-disaster/ | Qantas Flight 32: When A Few Millimeters Of Metal Invite Disaster | Maya Posch | [
"Transportation Hacks"
] | [
"aircraft",
"aircrash investigation"
] | A common saying is that every disaster is caused by a chain of events, some of which can stretch back by years. Airplane disasters and near-disasters are no exception here, with all too often a small mechanical issue worsening until suddenly everything goes south. In the best case the flight crew is still able to work through the problems and figure out a way to put the aircraft down on firm soil in a single piece. This was the situation that the crew of Qantas Flight 32 (QF32) found themselves forced to deal with, as detailed in a
recent article
by [Kyra Dempsey], aka [Admiral Cloudberg].
When
QF32
started its flight from London Heathrow in early November of 2010, everything seemed normal, but a mere four minutes after take-off from a layover at Singapore on its way to its final destination of Sydney, the #2 engine on the left wing of the Airbus A380 essentially exploded, launching shrapnel through the wing and fuselage. Although the A380 has four engines (numbered 1-4 from the left wing tip) and normally a single engine failure is not a major deal, the loss of systems that got destroyed in the explosion left the crew scrambling to diagnose the damage and implement a solution.
Fractured oil feed stub pipe wall measurements. (Source: ATSB)
Fortunately, the shrapnel had not done too much damage. The flight crew was able to stabilize the aircraft and circle back to Singapore for a successful emergency landing. When the ATSB (Australian Transport Safety Bureau) examined the destroyed #2 engine, they
traced the fault back
to a single lubrication oil feed line for bearings inside the engine that had sprung a leak (
full ATSB report
). The leaking oil auto-ignited, destroying seals that let hot turbine gas in where it didn’t belong. The gas made quick work of cutting through parts of the engine, which resulted in the turbine spinning out of control until a disc shattered into many, very fast-traveling pieces of shrapnel.
As for why the oil leak occurred? The wall thickness of the oil pipe was very irregular, with a fatigue crack coinciding with the thinnest wall section. The pressurized oil had exploited this weakness and in the process very nearly turned QF32 into a
TWA-800
or
Alaska Airlines Flight 261
level disaster. During the subsequent inspection of all other Rolls-Royce Trent 900 engines, a number were found to also have a similar flaw in the same piece of pipe. The pipes were quickly replaced. | 28 | 9 | [
{
"comment_id": "6706948",
"author": "Julian Skidmore",
"timestamp": "2023-12-11T12:28:19",
"content": "It’s a really good article – like it!One intriguing bit about the animation is the use of non-metric measurements applied to an engine designed by a British company (Rolls Royce) that only uses me... | 1,760,372,078.870154 | ||
https://hackaday.com/2023/12/11/the-sol-1-a-16-bit-computer-in-74hc-logic-with-c-compiler-and-unix-like-os/ | The Sol-1: A 16-bit Computer In 74HC Logic With C Compiler And Unix-like OS | Maya Posch | [
"hardware",
"Software Development"
] | [
"74 logic",
"discrete cpu",
"retro computing",
"retrocomputing"
] | Sol-1 system pictured from the front. {Credit: Paulo Constantino)
While the concept of a computer system implemented in discrete logic ICs is by itself not among the most original ideas, the way some machines are executed certainly makes them stick out. This is the case with
[Paulo Constantino]’s Sol-1
, which not only looks extremely professional, but also comes with a lot of amenities that allow for system development, including a
C compiler
and assembler, a Unix-like OS (in development), DMA, and a whole host of interfaces to interact with the system and peripherals (serial, parallel, IDE, etc.). Not to mention a SystemVerilog model and an emulator, all of which can be found on
[Paulo]’s GitHub
.
More photos and videos can be found on [Paulo]’s
YouTube channel
, as well
as the Sol-1 website
, which shows off the intricate wire wrap work on the back of each PCB. In terms of
the ISA
, there are 5 general purpose registers (one scratch) which can also be used as two 8-bit registers each. Most operations are supported, except for floating point. For future improvements and additions, Sol-1’s OS will get more features added, and the first major software to be ported to the Sol-1 should be Colossal Cave Adventure and similar text-based adventure (dungeon) games. | 15 | 7 | [
{
"comment_id": "6706943",
"author": "Feinfinger (M-x totally-tame-mode)",
"timestamp": "2023-12-11T12:12:53",
"content": "Seeeeeet!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6706946",
"author": "Pollux",
"timestamp": "2023-12-11T12:27:09",
"c... | 1,760,372,078.92728 | ||
https://hackaday.com/2023/12/10/cowgol-development-environment-comes-to-z80-and-cp-m/ | Cowgol Development Environment Comes To Z80 And CP/M | Donald Papp | [
"Retrocomputing"
] | [
"bootstrapping",
"compiler",
"Cowlark",
"CP/M",
"programming language",
"retrocomputing",
"z80"
] | Cowgol on Z80 running CP/M
ties together everything needed to provide a Cowgol development environment (including C and assembler) on a Z80 running the CP/M operating system, making it easier to get up and running with a language aimed to be small, bootstrapped, and modern.
Cowgol
is an experimental modern language for (very) small systems.
The Zilog Z80 was an 8-bit microprocessor common in embedded systems of the 1970s and 1980s, and CP/M was a contemporary mass-market operating system. As for
Cowgol
? It’s an Ada-inspired compiler toolchain and programming language aimed at very small systems, such as the Z80.
What’s different about Cowgol is that it is intended to be self-hosted on these small systems; Cowgol is written in itself, and is able to compile itself. Once one has compiled the compiler for a particular target architecture (for example, the Z80) one could then use that compiler on the target system to compile and run programs for itself.
Thankfully, there’s no need to start from scratch. The Cowgol on Z80 running CP/M repository (see the first link of this post) contains the pre-compiled binaries and guidance on using them.
Cowgol is still under development, but it works. It is a modern language well-suited to (very) small systems, and thanks to this project, getting it up and running on a Z80 running CP/M is about as easy as such things can get.
Thanks to [feinfinger] for the tip! | 7 | 5 | [
{
"comment_id": "6706915",
"author": "Andrew",
"timestamp": "2023-12-11T08:46:20",
"content": "My name is TedOne dayI’ll be dead, yo! Yo!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6706977",
"author": "David Given",
"timestamp": "2023-12-11T14:37:0... | 1,760,372,078.973417 | ||
https://hackaday.com/2023/12/09/clockhands-for-faster-cpu-execution/ | Clockhands For Faster CPU Execution | Al Williams | [
"Misc Hacks"
] | [
"cpu",
"out of order execution",
"register renaming"
] | When you design your first homebrew CPU, you probably are happy if it works and you don’t worry as much about performance. But, eventually, you’ll start trying to think about how to make things run faster. For a single CPU, the standard strategy is to execute multiple instructions at the same time. This is feasible because you can do different parts of the instructions at the same time. But like most solutions, this one comes with a new set of problems. Japanese researchers are proposing a novel way to work around some of those problems in a recent paper about a technique
they call Clockhands
.
Suppose you have a set of instructions like this:
LOAD A, 10
LOAD B, 20
SUB A,B
LOAD B, 30
JMPZ DONE
INC B
If you do these one at a time, you have no problem. But if you try to execute them all together, there are a variety of problems. First, the subtract has to wait for A and B to have the proper values in them. Also, the INC B may or may not execute, and unless we know the values of A and B ahead of time (which, of course, we do here), we can’t tell until run time. But the biggest problem is the subtract has to use B before B contains 30, and the increment has to use it afterward. If everything is running together, it can be hard to keep straight.
The normal way to do this is register renaming. Instead of using A and B as registers, the CPU uses physical registers that it can call A or B (or something else) as it sees fit. So, for example, the subtraction won’t really be SUB A,B but — internally — something like SUB R004,R009. The LOAD instruction for 30 writes to B, but it doesn’t really. It actually assigns a currently unused register to B and loads 30 into that (e.g., LOAD R001,30). Now the SUB instruction will still use 20 (in R009) when it gets around to executing.
This is a bit of an oversimplification, but the point is there’s plenty of circuitry in a modern CPU thinking about which registers are in use and which one corresponds to a logical register for this particular instruction. One proposed way to do this is to stop referring to registers directly and, instead, refer to them by how far away they are in the code (e.g., SUB A-2, B-1). This can be easier for the hardware, but more difficult for the compiler.
Where Clockhands is different is it refers to the number of writes to the register, not the number of instructions. It is somewhat like using a stack for each register and allowing the instructions to refer to a specific value on the stack. The hardware becomes easier, there is less for the compiler to do. This could potentially reduce power consumption as well.
Confused? Read the paper if you want to know more. Some
background from Wikipedia
might help, too. It reminded us of a CPU architecture from way back called
The Mill
(dead link inside, but there’s always
a copy
). If you didn’t know your CPU registers aren’t what you think they are, it is even
worse than you think
. | 15 | 7 | [
{
"comment_id": "6706715",
"author": "Jon H",
"timestamp": "2023-12-10T07:04:03",
"content": "The Mill people reorganized their website.https://millcomputing.com/docs/",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706735",
"author": "Truth",
... | 1,760,372,079.029348 | ||
https://hackaday.com/2023/12/09/impact-of-imperfect-timekeeping-on-quantum-control-and-computing/ | Impact Of Imperfect Timekeeping On Quantum Control And Computing | Maya Posch | [
"Science"
] | [
"quantum computing",
"quantum control theory"
] | In classical control theory, both open-loop and closed-loop control systems are commonly used. These systems are well understood and rather straightforward, controlling everything from washing machines to industrial equipment to the classical computing devices that make today’s society work. When trying to transfer this knowledge to the world of quantum control theory, however, many issues arise. The most pertinent ones involve closed-loop quantum control and the clocking of quantum computations. With physical limitations on the accuracy and resolution of clocks, this
would set hard limits
on the accuracy and speed of quantum computing.
The entire argument is covered in two letters to
Physical Review Letters
, by
Florian Meier et al.
titled
Fundamental Accuracy-Resolution Trade-Off for Timekeeping Devices
(
Arxiv preprint
), and by
Jake Xuereb et al.
titled
Impact of Imperfect Timekeeping on Quantum Control
(
Arxiv preprint
). The simple version is that by simply increasing the clock rate, accuracy suffers, with dephasing and other issues becoming more frequent.
Solving the riddle of closed-loop quantum control theory is a hard one, as noted by
Daoyi Dong and Ian R Peterson in 2011
. In their paper titled
Quantum control theory and applications: A survey
, the most fundamental problem with such a closed-loop quantum control system lies with aspects such as the
uncertainty principle
, which limits the accuracy with which properties of the system can be known.
In this regard, an accurately clocked open-loop system could work better, except that here we run into other fundamental issues. Even though this shouldn’t phase us, as with time solutions may be found to the timekeeping and other issues, it’s nonetheless part of the uncertainties that keep causing waves in quantum physics.
Top image: Impact of timekeeping error on quantum gate fidelity & independent clock dephasing (
Xuereb et al., 2023
) | 12 | 5 | [
{
"comment_id": "6706691",
"author": "Isaac Wingfield",
"timestamp": "2023-12-10T03:59:11",
"content": "“Even though this shouldn’t phase us” — it’s “faze”, unless you’re attempting a bad pun.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706697",
... | 1,760,372,079.0792 | ||
https://hackaday.com/2023/12/09/nanobots-self-replicate/ | Nanobots Self Replicate | Al Williams | [
"News",
"Robots Hacks",
"Science"
] | [
"dna",
"nanobot",
"science"
] | Hey, what if you could have a factory that makes robots that is run by… robots? This is hardly an original thought, but we are a long way from having an assembly line of C3POs self-replicating. On the other hand, animals — including humans — self-replicate all the time using DNA. Now, scientists are
making tiny nanorobots from DNA
that can assemble more DNA, including copies of themselves.
Assembling 3D structures with DNA has deep implications. For example, it might be possible to build drugs
in situ
, delivering powerful toxins only to cancer cells. Another example would be putting DNA factories in diabetes patients to manufacture the insulin they can’t.
It remains to be seen how useful these tiny replicators might be for things like computing tasks or sensors. Of course, some fear that we will hit the grey goo scenario where a self-replicating nanobot will simply eat the entire planet and everything on it, including us.
In response, researchers say this is unlikely because the tiny machines need specific raw materials, careful heating and cooling, and exposure to UV light. At least, that’s what they think. The
paper
isn’t available freely, but you may be able to access it via your local school or even a public library. The
supplemental materials
are interesting, too.
Think you can’t compute with DNA?
Think again
. While DNA equipment is a bit exotic, there are
surplus deals to be had.
Just try not to have your project consume the world, please. | 11 | 8 | [
{
"comment_id": "6706658",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-10T00:12:36",
"content": "This makes me think of the evil self replicating nanobots in the Stargate TV series.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "67... | 1,760,372,079.400865 | ||
https://hackaday.com/2023/12/09/how-the-first-ipod-was-blown-wide-open/ | How The First IPod Was Blown Wide Open | Jenny List | [
"ipod hacks"
] | [
"apple",
"ipod",
"Rockbox"
] | If someone makes a device, someone else will want to break it open and run their own software on it. When the original manufacturer is Apple this is never made easy, and as [Daniel Stenberg] reminds us in the case of one of the earlier iPod models
it required an unusual approach
.
In short, an HTML file was found which triggered a reboot, meaning a buffer overrun had been found in the firmware. After much experimenting, the memory location was found which would flash the backlight, and from there a piece of ARM code could be injected which would dump the firmware very slowly bitwise by flashing the light. Enough code could be extracted to find the address of the USB serial port, allowing new code to be made which dumped the firmware via USB. We remember the earliest models using FireWire instead of USB, so perhaps we can zero in on the 3rd or 4th generation. From there enough could be deduced to run the
Rockbox
music player firmware. We remember seeing friends doing this back in the day, something which was for a while the height of open-source coolness.
Fast forward twenty years or so, and we’re still covering people chipping away at Apple’s defenses. We don’t know whether a first-generation iPod could run
Doom
, but
we know Rockbox was capable of it on other players
. | 21 | 3 | [
{
"comment_id": "6706650",
"author": "Olivier",
"timestamp": "2023-12-09T23:34:46",
"content": "Ahhh yes, back when Apple still made things i wanted to have, good memories.While he cost me (and the entire sector i worked in) my job (flash dev) even i can’t deny that Steve Jobs was a legend, but in m... | 1,760,372,079.897284 | ||
https://hackaday.com/2023/12/09/pico-makes-a-so-so-keyboard-neat-o/ | Pico Makes A So-So Keyboard Neat-O | Kristina Panos | [
"Musical Hacks",
"Raspberry Pi"
] | [
"keyboard",
"midi",
"polyphony",
"raspberry pi",
"Raspberry Pi Pico"
] | When someone gives you a crappy little toy keyboard, what can you do? Sadly plunk on the thing one note at a time? Well yes, but that’s not going to get you on Hackaday. Do what [Turi] did and
give that thing a complete overhaul.
[Turi] threw away the original controller board, keeping only the keys, buttons, case, speaker, and a little bit of the original powder yellow enclosure. The Picophonica’s new brain is, you guessed it, a Raspberry Pi Pico. This enables [Turi] to use [Ryo Ishigaki]’s pico_synth_ex synthesizer and introduce MIDI out via USB-C.
The new engine does things that little keyboard could never have dreamed of originally, especially considering it wasn’t even polyphonic. Those fourteen white buttons now control things like sustain, cutoff, LFO rate, decay, and so on. Now it sounds great!
Be sure to check out the brief build video after the break. Excluding drums, the soundtrack was made entirely on the Picophonica.
Of course, Picos aren’t just good for musical keyboards. Use one to
convert an old proprietary keyboard to PS/2
, or
create your own. | 9 | 2 | [
{
"comment_id": "6706571",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-09T18:11:44",
"content": "Wow!Considering the low price of the Pico, the keyboard could have been designed around that, and not raised the retail price very much.",
"parent_id": null,
"depth": 1... | 1,760,372,079.452824 | ||
https://hackaday.com/2023/12/09/degrees-of-freedom-but-for-whom/ | Degrees Of Freedom, But For Whom? | Elliot Williams | [
"Hackaday Columns"
] | [
"design",
"newsletter",
"rants",
"user experience"
] | Opening up
this week’s podcast
, I told Kristina about my saga repairing our German toilet valve. I’m American, and although I’ve lived here over a decade, it’s
still
surprising how things can be subtly different from how they worked back home.
But what was amazing about this device was that it had a provision for fine adjustment, and to some extent relied on this adjustment to function. Short version: a lever mechanism provides mechanical advantage to push a stopper against the end of a pipe to block the water flow, and getting the throw of this mechanism properly adjusted so that the floater put maximum pressure against the pipe required fine-tuning with a screw. But it also required understanding the entire mechanism to adjust it.
Which makes me wonder how many plumbers out there actually take the time to get that right. Are there explicit instructions in the manual? Does every German plumber learn this in school? I was entirely happy to have found the adjustment screw after I spent 15 minutes trying to understand the mechanism, because it did just the trick. But is this everyone’s experience?
I often think about this when writing code, or making projects that other people are likely to use. Who is the audience? Is it people who are willing to take the time to understand the system? Then you can offer them a screw to turn, and they’ll appreciate it. But if it’s an audience that just doesn’t want to be bothered, the extra complexity is just as likely to cause confusion and frustration.
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
! | 48 | 17 | [
{
"comment_id": "6706539",
"author": "ono",
"timestamp": "2023-12-09T15:30:28",
"content": "I never recognized this as a difficult task, self-teaching myself to fix these mechanisms as a kid. There are many variants, ok, but how come this is “complex” ?The adjustment is necessary because of the mult... | 1,760,372,079.554103 | ||
https://hackaday.com/2023/12/09/marconi-circuit-magnification-meter-gives-up-secrets/ | Marconi Circuit Magnification Meter Gives Up Secrets | Al Williams | [
"Teardown"
] | [
"circuit magnification",
"grid dip oscillator",
"Marconi",
"q meter"
] | [Thomas] picked up a Marconi TF1245 with dents and dings. We have to admit that we had not heard of a “
circuit magnification meter
,” but apparently, this was a thing in the late 1960s and early 1970s. Turns out, we have heard of this kind of meter before, but it was called a Q meter. The device works using a very low-impedance resonant circuit and a very high-impedance voltmeter. It measures the ratio of the voltage across the known circuit and the unknown circuit. This particular meter needs an external signal source with very special characteristics. You can see the well-built device in the video below.
The unit didn’t seem to work, but we suspect that it didn’t like his normal signal source. According to a comment in the manual, the matching signal generator delivered 0.5V into a 0.5 ohm load. You could also use a matching transformer to get to the required match.
Like anything made by Marconi, the build quality is amazing. There are four tubes and four diodes inside, along with beautiful meters, transformers, wafer switches, and some amazing mechanical linkages. As far as we can tell, if [Thomas] had a matching transformer, the device would work.
Of course, there were other
Q meters
. You could measure Q with
a grid dip oscillator
, too. | 5 | 4 | [
{
"comment_id": "6706547",
"author": "Attilio",
"timestamp": "2023-12-09T16:21:12",
"content": "Very nice builded instrument.I believe that you should apply a real inductor to have a mesurement. THe green wire is not a “real” inductor.",
"parent_id": null,
"depth": 1,
"replies": []
},
... | 1,760,372,079.349378 | ||
https://hackaday.com/2023/12/08/hackaday-podcast-ep-247-cameras-from-gingerbread-or-hardboard-and-the-insecurity-of-bluetooth/ | Hackaday Podcast Ep 247: Cameras From Gingerbread Or Hardboard, And The Insecurity Of Bluetooth | Kristina Panos | [
"Hackaday Columns",
"Podcasts"
] | [
"Hackaday Podcast"
] | This week, Editor-in-Chief Elliot Williams and Kristina Panos met up to discuss the best hacks of the previous week. We have no nerdy news this week, but is that necessarily a bad thing?
Speaking of nothingness, we have no winner for What’s That Sound because all six people who responded were wrong. Was the sound of Clippy too obscure?
But then it’s on to the hacks, beginning with an awesome autonomous excavator that, among other things, lays boulders algorithmically to build load-bearing walls without any mortar or cement. From there, it’s old school meets new school in the form of a laser-cut fox-wedged mortise and tenon joint. We take a look at a couple of simple cameras, making dry ice from seashells, and a really tiny POV display where everything spins. Finally, we talk about how small that proposed Italian lunar outpost is, and discuss whether rating airlines would help stop the spread of diseases.
Check out the links below if you want to follow along, and as always, tell us what you think about this episode in the comments!
Download and savor at your leisure
.
Where to Follow Hackaday Podcast
Places to follow Hackaday podcasts:
iTunes
Spotify
Stitcher
RSS
YouTube
Check
out our Libsyn landing page
Episode 247 Show Notes:
News:
No news is good news, right? But Elliot learned the secret to fixing German toilets!
What’s that Sound?
Who is our big winner this week? Absolutely no one recognized it as Clippy’s popup sound,s probably because they all immediately disabled Clippy back in the day.
Interesting Hacks of the Week:
Update On The BLUFFS Bluetooth Vulnerability
Autonomous Excavator Builds Stone Wall Algorithmically
This Laser-Cut One-Piece Wedge Tenon Locks Wood Joints Tight
50 Digital Wood Joints by Jochen Gros – WINTERDIENST
Generating Motion Via Nitinol Wires
Nitinol Is A Material We Need To Be Playing With More
Falsified Photos: Fooling Adobe’s Cryptographically-Signed Metadata
The Minimum Required For A Film Camera
Quick Hacks:
Elliot’s Picks:
Dry Ice From Seashells, The Hard (But Cheap) Way
Better 3D Printing Overhangs? Dive! Dive!
Tiny POV Turns Right Round For Volumetric Fun
Finally! A Typeface For Hardware People
Download the Checkbook font
Kristina’s Picks:
Print Your Own Brain Lamp From MRI Data
Honey, I Ate The Camera
Robot Pianist Runs On Arduino Nano
Can’t-Miss Articles:
Italy Proposes Minimalist Lunar Outpost For Artemis
Ask Hackaday: Could Rating Airlines Stop Flights From Spreading Diseases? | 9 | 5 | [
{
"comment_id": "6706356",
"author": "Anders Nielsen",
"timestamp": "2023-12-08T20:42:59",
"content": "Not showing up on Apple Podcasts this week?",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6706361",
"author": "a_do_z",
"timestamp": "2023-12-08T20:... | 1,760,372,079.60314 | ||
https://hackaday.com/2023/12/08/diy-walkie-talkie-with-esp32-and-esp-now/ | DIY Walkie-Talkie With ESP32 And ESP-NOW | Maya Posch | [
"Microcontrollers",
"Radio Hacks"
] | [
"ESP-Now",
"ESP32",
"walkie talkie"
] | In a recent article in Elektor magazine, [Clemens Valens] describes the construction and software for an
ESP32 walkie-talkie system
that uses ESP-NOW for the wireless connection between units, along with a low-cost condenser microphone with a transistor-based preamplifier and an LM386 op-amp for the speaker circuit. In the ESP32 module the built-in DAC and ADC are used for audio in and output, which provide just about enough resolution for voice communication.
So why use ESP-NOW rather than WiFi or Bluetooth? Mostly because of range, power usage and convenience with no SSIDs and passwords to bother with.
The DIY Walkie-Talkie circuit diagram. (Credit: Clemens Valens, Elektor magazine)
ESP-NOW
is Espressif’s own network protocol that uses the same underlying hardware as 2.4 GHz WiFi and Bluetooth, but focuses on more basic direct and mesh-style communication. It can be considered to be somewhat like low-level UDP with MAC address instead of IP address, which makes it useful for fire-and-forget traffic such as from IoT devices.
In the past, we’ve seen ESP-NOW control everything from
fake security cameras
to
CNC machines
. In fact, we’ve even seen it used in
another walkie-talkie
a couple years back. | 15 | 5 | [
{
"comment_id": "6706338",
"author": "Moritz von Schweinitz",
"timestamp": "2023-12-08T19:22:48",
"content": "Does anyone know if there is a NOT DIY Version of this? Just a “real” walkie-talkie she’ll with a hackable ESP32 and battery inside?",
"parent_id": null,
"depth": 1,
"replies": [... | 1,760,372,080.004239 | ||
https://hackaday.com/2023/12/08/this-week-in-security-logofail-national-dns-poison-and-dna/ | This Week In Security: LogoFail, National DNS Poison, And DNA | Jonathan Bennett | [
"Hackaday Columns",
"News"
] | [
"23andMe",
"dns",
"UEFI"
] | When there’s a vulnerability in a system library, we install updates, and go on with our lives. When there’s a vulnerability in a Java library, jars get rebuilt, and fixed builds slowly roll out. But what happens when there’s a vulnerability in a library
used in firmware builds
? And to make it even more fun, it’s not just a single vulnerability. All three major firmware vendors have problems when processing malicious images. And LogoFail isn’t limited to x86, either. UEFI Arm devices are vulnerable, too.
You may ask why computer firmware needs an image parser. Obviously, every machine needs to show a full-screen logo on boot. And because reasons, that logo is often configurable by the end user. In other cases, firmware updates contain logos in unsigned sections of the firmware. The kicker is that this runs as part of the firmware, before any OS-level protections are loaded. It’s outside the secure boot stack, and has complete access to the system memory.
A
followup post
shares more details, and
the PDF of the slides
from the BlackHat Europe presentation are available.
National DNS Poison
We’ve discussed DNS poisoning here before. The quick explanation is that DNS queries are sent over UDP, so it’s possible to send spoofed DNS responses to a DNS resolver. To prevent the resolver treated those spoofed responses as legitimate, both the 16-bit DNS ID and 16-bit UDP source port must match the real request. Make those random, and you have 32-bits of entropy protecting your UDP requests. But what if
one of those values isn’t random
? Then you have a problem.
Researchers at SEC Consult found an odd data set, showing one of those DNS resolvers doing a stepwise walk up the source ports. Definitely a predictable pattern. It’s not quite as simple to exploit as you might think, as this source port pattern has a different offset for each remote host. Is this an odd DNS daemon? Probably not. The Theory is that this DNS resolver is actually sitting behind a Carrier-Grade Network Address (and Port) Translation device, a CGNA(P)T.
And that is interesting. There is an attack where one attacker can “use up” all of the open DNS ports, forcing real traffic to flow through a known port. A similar technique turned out to be valid. Here an attacker sends traffic over all but a very few of the available outgoing UDP ports on the CGNAPT device. Then a valid DNS query is sent, forced to go through one of the available ports. And then the attack is “reset”, allowing all the ports to fall back to unused. That’s enough, as the CGNAPT gateway will fall right back to its known pattern, starting at the port where it was forced to send traffic.
The kicker is that this flaw was present in the Internet connectivity of a developed nation. That nation is staying anonymous, and the flaw was fixed quickly after disclosure.
More DNS
It’s always DNS! Maybe not always, but once again DNS is
at the heart of a vulnerability
. It started with a screenshot worker — a server that load websites to capture a screenshot. That server could be fooled with a simple HTTP redirect, potentially capturing the web console from an Amazon EC2 instance, or other interesting tidbits of data. That particular problem was quickly fixed, but raised a question about what other interesting techniques could be used, like DNS rebinding.
DNS Rebinding is the simple technique of changing the IP address that a DNS name points to, in the middle of a session. If a browser connects to a web page on an attacker’s domain, the DNS changes, and then the browser triggers a new DNS lookup, that lookup could get redirected to a different host. In this case, once again the Amazon dashboard at 169.254.169.254.
There’s even a service from column-favorite, Tavis Ormandy,
just to help test for rebind flaws
. This led to a round of tightening of the servers at intruder, and a fun write-up of what this sort of vulnerability might look like.
Lateral movement through DNA
We now
know a bit more about the 23andMe breach
from the fall. About a tench of a percent of the company’s users were exposed directly. What’s really interesting here is the lateral movement. 23andMe users can opt in to expose their information to other users via the DNA Relatives and Family Tree features. It seems that about 14,000 accounts were access directly, but information from nearly seven million accounts were accessed through this information sharing feature. The breach is still thought to have been due to credential stuffing, taking known usernames and passwords and attempting to log in to many accounts with the information.
Hardening is Hard
The Sonos Era 100 was one of the target devices at Toronto Pwn2Own 2023, and this device has obviously had some real work done to make it a hard target to break into. Nonetheless, the
NCC Group brought the goods
, explaining exactly how to get in. As with most embedded devices, it starts with a TTL-level serial port on the board. Next was identifying and tapping pins to dump the eMMC data.
The first discovery was that U-Boot on this device is slightly misconfigured, attempting to load environment data from the flash memory. That data isn’t signed, so it’s possible to slip any environmental variable in there. That’s not as useful as it seems, as this U-Boot image is fairly locked-down otherwise. There is one other oversight, that the boot process calls the
setenv()
command to set up the boot instructions, but never checks that this succeeded. A flag that can be set as part of the environment to make those variables read-only. Suddenly the Linux kernel boot arguments are attacker-controlled.
The last bit was that the Linux kernel can be loaded to any memory offset, leaving plenty of room for a custom initramfs, giving full system control. And to top this one off, there’s a published exploit that could be adapted to read back the One-Time Programmable (OTP) memory, containing system keys and the firmware encryption key. Pwned.
Bits and Bytes
There are still
between 20,000 and 30,000 End-of-Life’d Exchange servers on the Internet
. These are Exchange 2007 and 2013 servers that just refuse to die. And while these old releases do get the occasional update for particularly nasty vulnerabilities, there are still multiple known exploit chains that target these old boxes. Ouch.
There’s a large network vendor we don’t hear about often here: Extreme Networks. Rhino Security Labs took a crack at the EXtreme Operating System (EXOS), and
found some fun bugs
, like the path traversal bug that let authenticated users read arbitrary files. This one chained nicely with a Server-Side Request Forgery attack, causing the EXOS machine to make a request of itself. That request succeeds automatically, and produces a valid JSON Web Token (JWT)… that can be read via the arbitrary file access. Extreme Networks has patched the problems in just over 3 months from report.
And finally, we have to let you know about
a Hacking book bundle from Humble Bundle
. The books are all from No Starch Press, and the charity supported by this bundle is the EFF. There look to be some good finds among the list, both Red and Blue team titles. Enjoy! | 3 | 3 | [
{
"comment_id": "6706275",
"author": "Ostracus",
"timestamp": "2023-12-08T15:22:39",
"content": "” Obviously, every machine needs to show a full-screen logo on boot. ”Marketing purposes so you’ll know…repeatedly what one wasted their money on.“And finally, we have to let you know about a Hacking boo... | 1,760,372,079.654487 | ||
https://hackaday.com/2023/12/08/the-latest-john-deere-repair-lawsuit-now-has-the-go-ahead/ | The Latest John Deere Repair Lawsuit Now Has The Go-Ahead | Jenny List | [
"News",
"Repair Hacks"
] | [
"john deere",
"legal",
"right to repair"
] | Long time readers will have followed the twists and turns of the John Deere repair saga, in which the agricultural machinery manufacturer has used DRM to restrict the repair of its tractors. It may be hot stuff on the prairies, but it matters to everyone because it’s a key right-to-repair battleground. Now the company’s attempt to throw out the latest class-action lawsuit, this time in Illinois. has failed,
paving the way for a meaningful challenge
.
This lawsuit is special because has the aim of determining whether or not Deere conspired to drive up the cost of repair and edge out independent mechanics. It comes against a backdrop in which their promised access to repair software
which we reported on back in January
has failed to materialize, and this is likely to figure as an act of bad faith.
A failing of corporate culture is that the organisation can in its own eyes, never be wrong. In Deere’s case they have accrued plenty of bad publicity in the years they’ve pursued this ill-advised business model, and in case that weren’t enough they’ve alienated their core customers out on the farms to the extent that
a second-hand Deere from before the DRM era has more value than its newer counterparts
. Deere genuinely do make very good tractors, so for farmers loyal for generations to turn their backs on them is a very significant story indeed. One has to ask, how much bad publicity and how many lawsuits do they have to have before someone at head office in Moline figures out that DRM in tractors (or anything else for that matter) isn’t the great idea they once thought it was? Maybe this one will finally herald the moment when that happens.
Header image: Nheyob /
CC BY-SA 4.0 | 50 | 13 | [
{
"comment_id": "6706232",
"author": "Brad",
"timestamp": "2023-12-08T13:46:49",
"content": ">>One has to ask, how much bad publicity and how many lawsuits do they have to have before someone at head office in Moline figures out that DRM in tractors (or anything else for that matter) isn’t the great... | 1,760,372,079.837879 | ||
https://hackaday.com/2023/12/08/festive-pcb-gives-the-gift-of-hacking/ | Festive PCB Gives The Gift Of Hacking | Kristina Panos | [
"Holiday Hacks",
"PCB Hacks"
] | [
"arduino",
"atmega328p",
"custom PCB",
"LED christmas tree"
] | ‘Tis the season for gift giving, and what better to give than a newfound love for hacking, soldering, and blinkenlights? In order to spread cheer and education at the local hackerspace,
[Tom Goff] created this festive tree circuit board
that can either sit in a stand to be admired, or worn as jewelry. The resistors are even designed to look like candy canes hanging from the boughs.
The brains of this festive little tree is an ATmega328P, which you probably recognize as the microcontroller that powers the Arduino Uno. Although this circuit has none of the extra bits you’d find on an Uno, not even a crystal oscillator, it can still be programmed with Arduino and use the 8 MHz internal clock.
[Tom] has provided good, thorough instructions, especially for the sticky bit of setting up the IDE to program using the 8 MHz internal clock. So even if you’re nowhere near Norwich Hackerspace, you can join in the fun. Be sure to check out the video after the break, wherein [Tom] walks through designing the PCB using Inkscape and Fritzing.
Want to whip up a little something for the hackerspace wall?
Check out this Sierpinski Christmas tree. | 9 | 3 | [
{
"comment_id": "6706206",
"author": "Anita",
"timestamp": "2023-12-08T11:47:19",
"content": "Why 5mm LED? Why 1.6mm PCB? Why Through-Hole RES? Why is everything so big? If he wants a woman to wear it for longer than 10 Minutes, he should have gone SMD. Big heavy clunky earrings are a real pain to w... | 1,760,372,079.945107 | ||
https://hackaday.com/2023/12/07/intentional-filament-stringing-helps-santa-soar/ | Intentional Filament Stringing Helps Santa Soar | Donald Papp | [
"3d Printer hacks",
"Art"
] | [
"3d printed",
"backlit",
"christmas",
"decoration",
"santa",
"String Art",
"stringing"
] | Stringing is when a 3D printer’s hot end moves through open air and drags a wisp of melted plastic along with it. This is normally undesirable, but has in the past been done intentionally to create some unconventional prints.
Moonlight Santa from [3dprintbunny]
shows considerable refinement in the technique, complete with color changes that really make the result pop.
Using a 3D printer’s stringing in a constructive way is something that has been leveraged really well. We remember seeing
a lion with a fantastic mane
by combining this method with a little post-processing and a blast from a heat gun. The technique has also been applied
to make brush bristles
(the printer strings filament across two handles, and after printing it is cut in half to make two brushes.)
This isn’t [3dprintbunny]’s first rodeo, either. We loved seeing her show
what kind of objects were possible by using clever design
, with no reliance on custom G-code or weird slicer tricks. The color changes by filament swaps really make this new one stand out. | 3 | 3 | [
{
"comment_id": "6706227",
"author": "2dPrintFox",
"timestamp": "2023-12-08T13:36:25",
"content": "That is so cool!Kudos",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6706228",
"author": "Resin gets me going",
"timestamp": "2023-12-08T13:38:35",
"... | 1,760,372,080.044245 | ||
https://hackaday.com/2023/12/07/one-less-binary-blob/ | One Less Binary Blob | Bryan Cockfield | [
"Software Hacks"
] | [
"binary blob",
"closed source",
"driver",
"ESP32",
"espressif",
"firmware",
"open source",
"proprietary",
"wifi",
"wireless"
] | Open-source software has gone a long way into making modern technology the way it is today. The Linux kernel alone is almost single-handedly holding up the entire Internet, and various other open-source projects allow for more access to computing resources not just because the software is often free, but because it’s possible to look under the hood and modify it for specific needs. Without open-source software available we often run into problems both expected, such as software licensing costs, and unexpected, which often come up because a developer can’t or won’t fix issues or add features. To that end, a group at Ghent University in Belgium are attempting to rectify a problem with the ESP32 by
eliminating one of its binary blobs and replacing it with an open source driver
.
The ESP32 is famously a low-cost microcontroller with on-board wireless capabilities, but its Wi-Fi functionality currently relies on closed-source software from Espressif. The team is currently working on building a fully working open-source networking stack with the hopes of enabling greater flexibility of these devices but also making things like security auditing possible. The other major goal is to improve low-cost mesh networking which is currently not available with the proprietary driver. Reverse engineering is the name of the game here, both from a hardware and a software level, but current versions of the software already able to send and receive packets.
The source code for the project is available on
the team’s GitHub page
for any open-source aficionados to take a look at. We certainly hope the project gains some steam, as any new open source project helps all of us using the platform. Open source projects frequently get stymied by a single or small handful of binary blobs too, often with little hope for recourse. Examples include Android being an open-source operating system but generally using the closed-source Google Play suite in practice, or Firefox including support for Adobe Flash. Another great example is that even computers running 100% open-source code once they boot their operating systems,
there’s still some black boxes running in the background few of us think about
.
Thanks to [Crote] for the tip! | 36 | 10 | [
{
"comment_id": "6706106",
"author": "Oliver",
"timestamp": "2023-12-08T03:53:41",
"content": "Awesome!!! Lets hope this continues after the class and students are onto their next thing …With that in mind, theres tons of esp8266 out there too ;(",
"parent_id": null,
"depth": 1,
"replies"... | 1,760,372,080.120123 | ||
https://hackaday.com/2023/12/09/when-is-a-6502-not-quite-a-6502/ | When Is A 6502 Not Quite A 6502? | Jenny List | [
"Parts"
] | [
"6502",
"65c02",
"counterfeit",
"counterfeit parts",
"fake",
"fake chip"
] | We all know that fake chips are a risk when it comes to buying parts on eBay or from Chinese markets such as AliExpress. It’s a simple enough scam, take a cheap chip and mark it as an expensive one, pocket the difference. It’s happened in several different forms, with everything from completely different devices through cheaper equivalents to incredibly, chips purpose fabricated to emulate better-known ones. We have a chance to see such a scam in action via [LinuxJedi], with
a 6502 that wasn’t quite as it seemed
.
The chip in question was a Rockwell 65C02 destined for an Acorn Atom, and when installed it failed to deliver the expected power consumption saving. Unsurprisingly when tested it turned out to be a fake, in this case a run-of-the-mill 6502 with new markings. The interesting part for Hackaday readers comes in the physical clues. The too-bright markings started to dissolve with a bit of acetone. A deeper investigation revealed the date and wafer codes did not agree with the branding. A new chip was secured which also turned out to be a fake, though in this case a real 65C02 rated for a lower clock speed than marked.
It’s evident that in-demand retro chips are likely to be an ever-greater minefield of fakes as time passes, and the number of survivors dwindles. It’s as well to be aware then and learn from any fakes like these posted online.
It’s not the first fake chip we’ve brought you
. | 20 | 10 | [
{
"comment_id": "6706531",
"author": "0xdeadbeef",
"timestamp": "2023-12-09T14:34:36",
"content": "That title is a bit misleading, as both discussed parts in the article are indeed 6502s – just not the exact part which was labeled.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
... | 1,760,372,080.179421 | ||
https://hackaday.com/2023/12/08/a-ham-radio-answering-machine/ | A Ham Radio Answering Machine | Bryan Cockfield | [
"Radio Hacks"
] | [
"ai",
"amateur radio",
"answering machine",
"boondock",
"ESP32",
"ham",
"radio"
] | For those who grew up with a cell phone in their hand, it might be difficult to imagine a time where the phone wasn’t fully integrated with voicemail. It sounds like a fantastical past, yet at one point a separate machine needed to be attached to the phone to record messages if no one was home to answer. Not only that, but a third device, a cassette tape, was generally needed as a storage device to hold the messages. In many ways we live in a much simpler world now, but in the amateur radio world one group is looking to bring this esoteric technology to the airwaves and [saveitforparts]
is demonstrating one as part of a beta test
.
The device is called the Boondock Echo, and while at its core it’s an ESP32 there’s a lot going on behind the scenes. It has an audio interface which is capable of connecting to a radio given the correct patch cable; in this case with a simple Baofeng handheld unit. The answering machine can record any sounds that come in. However, with a network connection the recordings are analyzed with an AI which can transcribe what it hears and even listen for specific call signs, then take actions such as sending emails when it hears triggers like that. Boondock also plans for this device to be capable of responding as well, but [saveitforparts] was not able to get this working during this beta test.
While an answering machine might seem like a step backwards technologically, an answering machine like this, especially when paired with Google Voice-like capabilities from an AI, has a lot of promise for ham radio operators. Even during this test, [saveitforparts] lost a radio and a kind stranger keyed it up when it was found, which was recorded by the Boondock Echo and used to eventually recover the radio. Certainly there are plenty of other applications as well, such as using AI instead of
something like an Arduino to do Morse decoding
. | 15 | 6 | [
{
"comment_id": "6706528",
"author": "0xdeadbeef",
"timestamp": "2023-12-09T14:24:20",
"content": "It’s worth noting that the Boondock Echo has been covered by HaD before:https://hackaday.com/2023/11/10/hands-on-with-boondock-echo/",
"parent_id": null,
"depth": 1,
"replies": []
},
{
... | 1,760,372,080.294383 | ||
https://hackaday.com/2023/12/08/cold-war-spying-and-the-questionable-use-of-smuggled-blueprints-in-developing-supersonic-airliners/ | Cold War Spying And The Questionable Use Of Smuggled Blueprints In Developing Supersonic Airliners | Maya Posch | [
"Engineering",
"History"
] | [
"concorde",
"SST",
"supersonic flight"
] | Although spying is a time-honored tradition, the sheer scope of it reached a fever pitch during the Cold War, when everyone was spying on everyone, and conceivably for both sides at the same time. In an era where both McCarthyism and the character of James Bond enjoyed strong popularity, it should come as no surprise that a project of geopolitical importance like the development of the world’s first supersonic airliner would come amidst espionage, as well as accusations thereof.
This is
the topic of a documentary
that recently aired on Channel 4 in the UK called
Concorde: The Race for Supersonic
, yet what is the evidence that the
Soviet Tu-144
truly was just a Concorde clone, a derogatory nicknamed ‘Concordski’?
Three views of a Boeing 2707-300.
At the time that the Concorde was being developed, there wasn’t just the competition from the Tu-144 team, but also the
Boeing 2702
(pictured) and
Lockheed L-2000
, with the latter two ultimately being cancelled. Throughout development, all teams converged on a similar design, with a delta wing and similar overall shape. Differences included the drooping nose (absent on Boeing 2707-300) and use of canards (present on Tu-144 and 2707-200), and wildly different engines, with the production Tu-144S requiring an afterburner on its Kuznetsov NK-144A engines just like the Concorde, before the revised Tu-144D removing the need for afterburners with the Koliesov RD36-51 engines.
Although generally classified as a ‘failure’, the Tu-144’s biggest issues appear to have been due to the pressure on the development team from Soviet leadership. Once the biggest issues were being fixed (Tu-144D) it saw continued use for cargo use and even flying missions for NASA (Tu-144LL) until 1999. Although Soviet spies were definitely caught with Concorde blueprints, the practical use of these for the already overburdened Tu-144 development team in terms of reverse-engineering and applying it to the Tu-144’s design would be limited at best, which would seem to be reflected in the final results.
Meanwhile, although supersonic airliners haven’t been flying since the Concorde retired in 2003, the
Lockheed Martin X-59 Quesst
supersonic airplane that is being built for NASA looks set to fix the sonic boom and fuel usage issues that hampered supersonic flight. After the L-2000 lost to Boeing so many decades ago, it might be Lockheed that has the last laugh in the race towards supersonic flight for airliners.
Top image: Tu-144 with distinctive
droop nose
at the
MAKS
-2007 exhibition) | 12 | 7 | [
{
"comment_id": "6706452",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-09T03:37:41",
"content": "McCarthy was correct in his accusations.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706461",
"author": "Bob",
"ti... | 1,760,372,080.353083 | ||
https://hackaday.com/2023/12/08/mosfets-the-big-lie/ | MOSFETs — The Hidden Gate | Al Williams | [
"Parts"
] | [
"components",
"mosfet",
"semiconductor"
] | How many terminals does a MOSFET have? Trick question since most have three leads, even though there are really four connections to the underlying device. It isn’t a conspiracy, though and [Aaron Lanterman]
talks about how MOSFETs really work
and why thinking of them as three-terminal devices can lead you astray in a recent video that you can watch below.
Like many people, [Aaron] points out the parallel between a triode vacuum tube and a MOSFET. That’s not surprising, since a solid-state tube was exactly what they were looking for when they developed the FET. Since tubes and FETs are both voltage controllers, it is easy to think of the gate as the grid, the source as the cathode, and the drain as the plate. But, [Aaron] shows this isn’t really a very accurate picture.
The fourth terminal of the MOSFET is the “bulk” or substrate. In a package, we typically see that tied to the source, and that actually defines the source since, on a four-terminal MOSFET, the source and drain are interchangeable as long as the device is symmetrically built. If you are working with three-terminal devices, this means that Vgs — the voltage from gate to source — is meaningful. But with a four-terminal device — or one constructed on a die — you must realize that the gate voltage will work differently than the source voltage since there is a built-in offset from the bulk terminal.
If you only use packaged MOSFETs, this difference is probably only a curiosity. However, it is good to understand how things really work and, too, designing custom ICs is
becoming more accessible
every day. Understanding the details of components can lead to interesting designs. Like using a MOSFET as both
a heater and a temperature sensor
. | 12 | 6 | [
{
"comment_id": "6706429",
"author": "David",
"timestamp": "2023-12-09T00:48:34",
"content": "Four terminal discrete MOSFETs do exist. I have had several 2N4351 FETs sitting around for a while now. I might even find a use for them sometime.",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,080.24689 | ||
https://hackaday.com/2023/12/08/metronome-flashes-and-vibrates-to-the-beat/ | Metronome Flashes And Vibrates To The Beat | Kristina Panos | [
"Raspberry Pi"
] | [
"keypad",
"matrix keypad",
"membrane keypad",
"metronome",
"Raspberry Pi Pico",
"vibration motor"
] | Annoying though they can be, if you play any kind of instrument, you will definitely benefit from using a metronome. While many of them thock or otherwise tock,
the VRRVRR metronome from [Turi]
works a little differently.
In addition to flashing LEDs, the VRRVRR contains a small vibrating motor. If you’re wondering about the name, it comes from the fact that it vibrates and makes a sort of
vrr vrr
sound. Need to be quiet? A small switch on the side shuts off the vibrations.
The 4×4 keypad really allowed [Turi] to cram in a bunch of features using both short and long press to do different things. On short press, the digits set the tempo. When not typing in a tempo, zero can be used to enter a tempo by tapping. The letters load preset tempos, and the +/- keys increase and decrease it.
Inside the basswood enclosure is a Raspberry Pi Pico, the vibration motor, and various other bits and bobs that make it go. There’s even an LED to indicate that it’s time to charge the lithium battery. If you want to build your own,
head on over to GitHub
, but be sure to take the brief VRRVRR tour after the break.
We don’t see too many metronomes around here, but
we do have this nice teardown to offer you. | 3 | 2 | [
{
"comment_id": "6706496",
"author": "jbx",
"timestamp": "2023-12-09T10:25:05",
"content": "The flashing signal is very practical for deaf musicians…",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706780",
"author": "Æliott",
"timestamp": "2... | 1,760,372,080.399591 | ||
https://hackaday.com/2023/12/08/switching-converter-for-eeprom-programmer-taxes-solderless-breadboard/ | Switching Converter For EEPROM Programmer Taxes Solderless Breadboard | Dan Maloney | [
"Parts"
] | [
"boost converter",
"breadboard",
"burner",
"eeprom",
"programming",
"rom",
"solderless",
"switching"
] | We all know that solderless breadboards have their limitations. All that stray capacitance can play hell with circuits, especially high-speed stuff, but they’re so darn useful that avoiding them in favor of some other prototyping method can be really hard. So we often just forge ahead, plugging in our parts and hoping for the best
A recent veteran of the breadboard battle is [Anders Nielsen], who kicked off a new project by prototyping
this high-voltage boost converter on a breadboard
, with mixed results. The project is
a scratch-built programmer for old-school ROM chips
, a task normally farmed out to a dedicated programmer, but where’s the sport in that? Besides, this is the future, and generating the 12 to 14 volts needed should be a snap. And it would be, except for the fact that his chosen chip, a MIC2288 switching boost regulator, is only available in an SMD package. Getting the chip and a few other SMD support components onto breadboard-compatible breakouts proved to be challenging, and getting it working once it was there was even more work.
A lot of the trouble was down to simple breadboarding errors, but the big problem was the input capacitance, which [Anders] had to fiddle with quite a bit to get the converter to 14 volts. The current maxes out at about 25 mA before the voltage starts dropping, which just might be enough to burn those old chips, so we’ll call this a provisional win and see what happens when he builds the rest of the programmer.
[Anders]’ experience here raises a good question: what’s the best way to prototype using fussy SMD components? PCBs are cheap enough that it’s tempting to go straight to one, but swapping parts in and out like he had to do here to get everything just right would be much harder that way. We’re not sure we know the answer, but we’re pretty sure we’ll hear your thoughts on that in the comments section. | 13 | 9 | [
{
"comment_id": "6706411",
"author": "Tom G",
"timestamp": "2023-12-08T23:37:39",
"content": "With switching circuirs, excessive wire inductance is as much of a problem as capacitance. A rule of thumb is 1nH/mm, so a 4 inch/100mm wire “contains” 100nH. Use that to work out resonant frequencies and i... | 1,760,372,080.515677 | ||
https://hackaday.com/2023/12/08/check-your-board-call-for-submissions/ | Check Your Board: Call For Submissions | Arya Voronova | [
"Featured",
"hardware",
"PCB Hacks",
"Slider"
] | [
"community review",
"design review",
"PCB design"
] | As both beginning hackers and Silicon Valley investors alike keep discovering, there are a lot of differences between hardware and software. One important difference is cost of iterating over a design. In software, you can comfortably rerun your build process and push updates out near instantly to tons of users. In hardware, all of that costs money, and I do mean, it costs way more money than you’d want to spend.
When I see people order boards that could never work because of some fundamental design assertions, with mistakes entirely preventable, it hurts. Not in an “embarrassment” way – it’s knowing that, if they asked someone to take a look at the design, they could’ve received crucial feedback, pulled the traces on the board differently or added some components, and avoided spending a significant chunk of money and time expecting and assembling a board that has a fundamental mishap.
Every thing like this might set a beginner back on their hacker journeys, or just have them spend some of their valuable time, and we can do a ton to prevent that by simply having someone experienced take a look.
We Don’t Do This Often Enough
When it comes to hacker communities, an underappreciated part of what we can do for fun is design review, and it helps if we offer it actively. If people don’t know they can ask others for design review, they might not ask at all, and knowing that they can is certainly a confidence boost for people going for their first PCB design.
It’s also yet another way we can pass knowledge down to newcomers – through demonstrating PCB design tactics, techniques and tricks, and also ways to spot and prevent mistakes before they appear, that so many of us had to develop the hard and painful way.
This isn’t just about individually reviewing boards – it’s about having a design review culture, where we have a set of practices showing how people can ask for advice, and how other people are supposed to give it. For instance, it can be tricky to remember to focus on what matters, and talk about what the board designer actually wants to achieve.
I’m no expert, and, I’ve been doing design review here and there online for over a year now, so I think it’d be fun to talk about how we can address beginners’ design mishaps quickly, while meeting what they expect. It’s also certain that, the more eyes we get on any given board, the more things we can all learn about how to make it better!
Send Them In!
So, here’s my proposal. You send in your PCB designs. They don’t have to be your first designs, but it’s nice if they are. Ideally, there will be a problem still to be solved. If there’s something that we can all learn from, we’ll feature it and ask the community for help. Ideally, we could, over time, form a small collection of common PCB mishaps, and a series of fun articles.
Here’s a few asks. First, it has to be open-source, and not just schematics-available, though I will also be taking a look at schematics. Also, I’d greatly prefer KiCad over anything else, purely because that’s what I’m personally laser focused on working with. GitHub / GitLab / any other repo is the best option, but I never turn my nose at a sketchy link with a zip archive!
Send your link or files
to the tips line
, and put
[design review]
in the title!
As a side question – are you in a community that does design review for each other and newcomers? If so, what do you have to share? And, if not, what are your thoughts anyway? | 41 | 13 | [
{
"comment_id": "6706323",
"author": "Adam Paul",
"timestamp": "2023-12-08T18:20:52",
"content": "This is a great idea. I’m a software guy, slowly trying to find my way in the hardware world.What I’ve noticed is that in software, there’s an abundance of useful help out there – articles, clear docume... | 1,760,372,080.598786 | ||
https://hackaday.com/2023/12/07/fail-of-the-week-mark-makes-an-atari-cartridge/ | Fail Of The Week: [Mark] Makes An Atari Cartridge | Al Williams | [
"Games"
] | [
"atari 2600",
"cartridge",
"console"
] | Part of the magic of the movies is that the actors always know what will happen next. There never has to be a scene where James Bond orders wine, and the sommelier has to correct his pronunciation, or he miscounts his hand at baccarat. Real life is rarely as smooth. Of course, YouTube is more akin to a movie than real life, and we always wonder how many flawlessly executed projects you see on YouTube really went that well. [Mark Fixes Stuff] left no scenes on the cutting room floor, though, in his
realistic portrayal of his quest to build a nice-looking Atairi 2600 cartridge
. Watch it below.
Spoiler alert: In the end, it all worked out. But getting there was a series of misadventures. Starting out with [Parker Dillman’s] PCB, he put together the insides of the cartridge, including a socket for the EPROM. He then resin-printed a case. Like many of our own projects, the first run wasn’t quite the size he expected. It was probably close enough, though, but then he realized the socket made the board too tall to fit in the enclosure.
He also shows all the little parts that have to happen to get a nice-looking project completed. Printing a color label or just burning the EPROM, for example. He didn’t just produce them out of thin air.
We wondered if a low-profile socket might have been able to fit. Sometimes, two rows of machined pins will fit where a socket won’t, too. Barring that, it might have been nice to use an EEPROM — they make them that are drop-in compatible with EPROMS — and then allow reprogramming with a clip or pogo pins on a new PCB.
Overall, we enjoyed this realistic peek into a practical project. We might suggest a little tape to hold down components while soldering, though. What could you do with a custom cartridge? Maybe
fix an old game
. Of course, you can actually get
recent official new cartridges
. | 8 | 6 | [
{
"comment_id": "6706150",
"author": "Sjaak",
"timestamp": "2023-12-08T07:41:52",
"content": "Nice view of the whole proces and kuddo’s for the effort to create a nice cart.If he would desolder the dip chip and capacitor. clip the leads much shorter and resolder them the socket would be more flush.A... | 1,760,372,080.647493 | ||
https://hackaday.com/2023/12/07/upgrade-puts-a-lot-of-zeroes-on-kit-built-frequency-counter/ | Upgrade Puts A Lot Of Zeroes On Kit-Built Frequency Counter | Dan Maloney | [
"Tool Hacks"
] | [
"calibration",
"crystal oscillator",
"frequency counter",
"reference",
"standard",
"temperature compensated",
"VCTCXO"
] | If there’s anything more viscerally pleasing than seeing an eight-digit instrument showing a measurement with all zeroes after the decimal point, we’re not sure what it could. Maybe rolling the odometer over to another 100,000 milestone?
Regardless, getting to such a desirable degree of accuracy isn’t always easy, especially when the instrument in question is a handheld frequency counter that was built from a kit 23 years ago. That’s the target of [Petteri Aimonen]’s accuracy upgrade, specifically by the addition of
a custom frequency reference module
. The instrument is an ELV FC-500, which for such an old design looks surprisingly modern. Its Achille’s heel in terms of accuracy is the plain crystal oscillator it uses as a frequency standard, which has no temperature compensation and thus drifts by about 0.2 ppm per degree.
For a mains-powered lab instrument, the obvious solution would be an oven-controlled crystal oscillator. Those are prohibitive in terms of space and power for a handheld instrument, so instead a VCTCXO — voltage-controlled, temperature-compensated crystal oscillator — was selected for better stability. Unfortunately, no such oscillators matching the original 4.096-MHz crystal spec could be found; luckily, a 16.384-MHz unit was available for less than €20. All that was required was a couple of flip-flops to divide the signal by four and a bit of a bodge to replace the original frequency standard. A trimmer allows for the initial calibration — the “VC” part — and the tiny PCB tucks inside the case near the battery compartment.
We enjoyed the simplicity of this upgrade — almost as much as we enjoyed seeing all those zeroes.
When you know, you know. | 0 | 0 | [] | 1,760,372,080.6825 | ||
https://hackaday.com/2023/12/07/basic-in-your-browser/ | BASIC In Your Browser | Al Williams | [
"Retrocomputing",
"Software Hacks"
] | [
"basic",
"tiddlywiki"
] | If you are a certain age or just like retrocomputers, you probably have a soft spot for good old-fashioned BASIC. If you miss those days but don’t want to install a modern interpreter, you don’t have to. Just load a web page containing the “
BASIC Anywhere Machine
” from [CJ Veniot]. Worried about it being “in the cloud?” It isn’t? It runs in your browser, and if you are a TiddlyWiki fan, it will even live inside your Wiki, which you can host as you please.
The project has lots of features, including some integration back into TiddlyWiki, which we haven’t tried. But you can use graphics commands, work with the mouse, and do other fun things.
The only peculiarity is that the program pops up in a window that resembles an old Commodore 64 screen. Depending on why you want to use this, that could be an advantage or a disadvantage. You can see a nice plot running from a TiddlyWiki topic in the title image. Here’s the Tiddler:
The code behind the wave
The BASIC Anywhere Machine is highly modified from Google’s
wwwBASIC
, which is fun, too. Since we’ve covered
TiddlyWiki
before, we are a little ashamed we didn’t think to marry those two codebases ourselves! | 30 | 8 | [
{
"comment_id": "6705963",
"author": "Feinfinger (super villain in nostalgy mode)",
"timestamp": "2023-12-07T20:03:20",
"content": "“”” If you are a certain age or just like retrocomputers, you probably have a soft spot for good old-fashioned BASIC. “””Luckily this is *not* the early variant of crip... | 1,760,372,081.009989 | ||
https://hackaday.com/2023/12/07/keebin-with-kristina-the-one-with-the-biblically-accurate-keyboard/ | Keebin’ With Kristina: The One With The Biblically-Accurate Keyboard | Kristina Panos | [
"Hackaday Columns",
"Peripherals Hacks"
] | [
"biblically accurate",
"mouse switches",
"num pad",
"stream deck",
"typewriter collection"
] | Well, it was bound to happen at some point.
[sporewoh]’s bunchiez40 keyboard for ants is made of mouse switches
, which of course begs for a mouse made of keyboard switches.
Image by [sporewoh] via
GitHub
[sporewoh]’s keyboards have been steadily shrinking, and they built this in order to get the smallest possible form factor for the number of keys. Surprisingly, since the mouse switches have an actuation force similar to some heavier MX-style switches (~70 g), [sporewoh] is able to squeeze 85 WPM out of it, albeit with some argument from the wrists.
If you want to build a bunchiez40, everything is available on GitHub, including the CAD files for that lovely anodized aluminium case. The typing video is coming soon, and I’m taking bets on whether it’s as quiet as a mouse, as one redditor joked.
A Biblically-Accurate Keyboard
Image by [hllhvnd] via
reddit
Well, color me sacrilegious or just plain stupid, but I didn’t quite get the name of [hllhvnd]’s
Biblically Accurate Keyboard
at first. If you’re familiar with the concept of ‘biblically accurate angels’, well, you get the picture. If you’re not familiar yet, well, then I’m sorry.
By the way, this devilish thing isn’t a keyboard at all, as in, it’s not an input, at least not yet. It’s basically a fidget toy, and although it has linears (eww!) at the moment, it will soon have greens or maybe box navy switches.
You know, I think I need one of these to adorn my desk, and definitely in a clicky version. Fortunately, [hllhvnd] plans to make the STLs available in the near future.
The Centerfold: A Turn At the Tern
Image by [zyumbik] via
reddit
This clean little number is [zyumbik]’s remix of
the Tern
, which is a remix of
the Hummingbird
. [zyumbik] has been using this awesome
Skull keyboard
they made as a daily driver, but wanted something like the Hummingbird.
The main differences are support for an on/off switch, a JST battery connector, and a XIAO BLE battery pogo pin. The Tern BLE also has tighter switch holes, so no plate is necessary. Everything you need to spin a Tern BLE is available in
the GitLab
.
Do you rock a sweet set of peripherals on a screamin’ desk pad?
Send me a picture
along with your handle and all the gory details, and you could be featured here!
Historical Clackers: A Grand Collection Indeed
Image by Martin Howard via
Antique Typewriters
No matter what my husband says, I really don’t have
that
many typewriters in my collection. But you know who does? [Martin Howard] of
the Antique Typewriters website
, where I pull a large percentage of the Historical Clackers that adorn these pages.
[Martin]’s collection
is focused on machines from the 1880s and 90s, before the typewriter really became standardized. Be sure to explore the dozens of different typewriter and index typewriter designs, which range from wild to beautiful to both at once.
In addition to buying and selling typewriters, [Martin] also does restoration and repair, displays his collection at
events and exhibits
, and even loans machines out for film, television, and theater. And keep a lookout for [Martin] in the 2016 film
California Typewriter
.
ICYMI: Num Pad Reincarnated As Stream Deck
Image by [dj_doughy]
In a stroke of luck, [dj_doughy] happened upon a clicky number pad in a recycle pile with what turned out to be white ALPS switches. It was only a matter of time before
it became a stream deck
.
The only problem was that it had a PS/2 connector. Well, and the fact that there is no datasheet for the controller. Determined to make it work, [dj_doughy] took to Discord and was advised to set the thing up to use extended keys (F13-F24) and wire those up as shortcuts in OBS.
Then there was the whole PS/2 thing still. In the end, [dj_doughy] used an Arduino Beetle, which fit perfectly inside the case. Unfortunately there were software issues with double key presses being sent, but there were just a few missing variables.
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
. | 5 | 3 | [
{
"comment_id": "6705954",
"author": "J Samson",
"timestamp": "2023-12-07T19:29:35",
"content": "I usually enjoy these articles, but the “eww” in response to the switch choice for a non-electronic toy seems super elitest (for no reason). Also, seeing as how the title for the article referenced “bibl... | 1,760,372,080.754352 | ||
https://hackaday.com/2023/12/07/making-visual-anagrams-with-help-from-machine-learning/ | Making Visual Anagrams, With Help From Machine Learning | Donald Papp | [
"Art",
"Artificial Intelligence"
] | [
"ai",
"diffusion models",
"optical illusion",
"visual anagram"
] | [Daniel Geng] and others have an interesting system of generating multi-view optical illusions, or visual anagrams. Such images have more than one “correct” view and visual interpretation.
What’s more, there are quite a few different methods on display: 90 degree flips and other (orthogonal) image rotations, color inversions, jigsaw permutations, and more.
The project page
has a generous number of examples, so go check them out!
The team’s method uses pre-trained diffusion models — more commonly known as the secret sauce inside
image-generating AIs
— to evaluate and work to combine the differences between different images, and try to combine and apply it in a way that results in the model generating a good visual result. While conceptually straightforward, this process wasn’t really something that could work without diffusion models driven by modern machine learning techniques.
The
visual_anagrams
GitHub repository has code
and the
research paper
goes into details on implementation, limitations, and gives guidance on obtaining good results. Image generation is just one of the rapidly-evolving aspects of recent innovations, and it’s always interesting to see unusual applications like this one. | 1 | 1 | [
{
"comment_id": "6706091",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-08T02:56:07",
"content": "Following an example in an early 1980s magazine, (Omni?), I made drawing of my name, and when it was rotated 180 degrees it was my girlfriend’s name.Too bad we broke 💔 up…",
... | 1,760,372,081.131582 | ||
https://hackaday.com/2023/12/07/artemis-next-giant-leap-orbital-refueling/ | Artemis’ Next Giant Leap: Orbital Refueling | Tom Nardi | [
"Featured",
"Interest",
"Original Art",
"Slider",
"Space"
] | [
"Artemis",
"Blue Moon",
"Blue Origin",
"moon",
"nasa",
"SpaceX",
"starship"
] | By the end of the decade, NASA’s Artemis program hopes to have placed boots back on the Moon for the first time since 1972. But not for the quick sightseeing jaunts of the Apollo era — the space agency wants to send regular missions made up of international crews down to the lunar surface, where they’ll eventually have permanent living and working facilities.
The goal is to turn the Moon into a scientific outpost, and that requires a payload delivery infrastructure far more capable than the Apollo Lunar Module (LM). NASA asked their commercial partners to design crewed lunar landers that could deliver tens of tons of to the lunar surface, with SpaceX and Blue Origin ultimately being awarded contracts to build and demonstrate their vehicles over the next several years.
Starship and Blue Moon, note scale of astronauts
At a glance, the two landers would appear to have very little in common. The SpaceX Starship is a sleek, towering rocket that looks like something from a 1950s science fiction film; while the Blue Moon lander utilizes a more conventional design that’s reminiscent of a modernized Apollo LM. The dichotomy is intentional. NASA believes there’s a built-in level of operational redundancy provided by the companies using two very different approaches to solve the same goal. Should one of the landers be delayed or found deficient in some way, the other company’s parallel work would be unaffected.
But despite their differences, both landers do utilize one common technology, and it’s a pretty big one. So big, in fact, that neither lander will be able to touch the Moon until it can be perfected. What’s worse is that, to date, it’s an almost entirely unproven technology that’s never been demonstrated at anywhere near the scale required.
Running on Empty
Logically, the larger a payload you want to put into orbit (or beyond), the larger a rocket you need. Of course, there are limits on what we can do in terms of material science, engine technology, and even economics. So you can quickly get to the point where a rocket simply becomes too large to be practical. Once you hit that point, you need to start looking at other ways of getting your target mass into orbit. For projects like the International Space Station, that meant breaking the structure up into smaller modules that could be launched individually and assembled in orbit.
Both SpaceX and Blue Origin have essentially the same problem: their landers, when you include the propellant they’ll need to land on the Moon and lift back off again, are simply too heavy to launch. Both companies are developing heavyweight boosters to get their respective landers out of Earth’s gravity well and into low Earth orbit, but that’s the best they can do. So how will they get astronauts to the Moon?
While the techniques differ slightly, both companies will need to load their landers with the propellants necessary to complete the missions while they are already in space. And in both cases, the lander’s human crew wouldn’t launch from Earth until their ride to the lunar surface is fueled up and waiting for them.
Blue Moon
According to the current plan, a single New Glenn rocket will be able to lift the Blue Moon lander off from Earth and
send it to the Lunar Gateway Station
. But once there, the lander won’t have enough propellant to make a powered descent to the lunar surface, much less take back off again.
So once the lander has reached the Lunar Gateway, two more New Glenn rockets will be launched. One will carry a propulsion and navigation module, and the other a propellant storage module. Once in orbit, they will connect to each other to become what Blue Origin is calling the Cislunar Transporter.
At this point, additional New Glenn rockets will be launched, each carrying propellants to be loaded into the Cislunar Transporter. When the Transporter has been filled, it will make its way to the Lunar Gateway, where it can rendezvous with the lander and refuel it. The number of launches required to fill the Cislunar Transporter isn’t publicly known, and it’s entirely possible that even Blue Origin won’t know the exact number until the hardware is more mature.
Starship
Starship is unique in that it actually makes up the upper stage of its booster rocket, the Superheavy. So to reach Earth orbit, Starship will need to expend the vast majority of the propellants it was loaded with on Earth. Once in a stable orbit, the spacecraft will have enough propellant to maneuver, but nowhere near enough to make the journey to the Moon.
To refuel the Moon bound Starship, SpaceX will launch several “tanker” versions of the spacecraft. These tanker craft will be stripped down to the bare essentials to save mass when compared to the lander version, which means they’ll be able to carry more propellants within the same volume. Each reusable tanker will dock with the lander, and transfer over as much propellant as it can while still leaving enough onboard to complete its own landing back on Earth.
In some versions of the plan, these tankers will actually transfer their propellants into a third “Depot” variant of the Starship before the lander itself is launched. While the addition of a third Starship variant would make this approach slightly more expensive and complex, the advantage is that the lander could remain on the ground until the Depot is filled, making the refueling process more resilient against any delays that might arise while launching the tankers.
Just like with the Blue Moon lander, it’s currently unknown how many launches will be required to fully fuel the lander, but estimates put the number somewhere between 10 and 20. The only way this refueling process will be economically viable, or even practical, is if the tankers and Superheavy boosters that launch them can be quickly and affordably reflown.
Highly Motivated Development
Despite the fact that both Blue Origin and SpaceX have hung the success of their respective lunar landers on the ability to quickly and safely refuel them while in orbit, there’s simply no precedent for such an operation. Studies so far have focused on refueling small satellites, using
relatively simple monopropellants like hydrazine
. But topping off the tanks on Starship or Blue Moon will mean autonomously moving hundreds of tons of cryogenic liquid oxygen, methane, and hydrogen between spacecraft. The couplings, pumps, piping, valves, and insulation required to facilitate that sort of propellant transfer have never been tested in space and could take many iterations to perfect.
If Artemis is going to return astronauts to the Moon, this is a problem that needs to be solved quickly. For their part,
NASA’s Space Technology Mission Directorate awarded several contracts in 2020
designed to study various aspects of orbital propellant transfer. SpaceX specifically was guaranteed $53.2 million if they can demonstrate moving 10 metric tons of liquid oxygen between two tanks onboard an in-flight Starship. While nowhere near as complex as moving liquids between two vehicles, this early test should still provide some critical data, and give SpaceX the chance to test some of the hardware involved.
In a recent presentation detailing the progress of the Artemis program, it was revealed that SpaceX may
attempt the propellant transfer demonstration
during Starship’s next test flight, though a NASA official later clarified that “no final decisions on timing have been made.” It may be that SpaceX wants to get a full orbital demonstration flight under their belt before moving on to the propellant test, but the clock is ticking. If they can’t demonstrate propellant transfer in 2024, the already fragile Artemis timeline will almost certainly fall apart.
Put simply, there’s no returning to the Moon in the near future without in-orbit propellant transfers. But with billions of dollars in Artemis contracts on the line, both SpaceX and Blue Origin will be highly motivated to overcome this technical hurdle as soon as they can. | 32 | 10 | [
{
"comment_id": "6705867",
"author": "Pat",
"timestamp": "2023-12-07T15:20:07",
"content": "“The only way this refueling process will be economically viable,”I mean… the Starship version’s not intended to be economically viable. That’s the entire reason Blue Origin filed the lawsuit challenging the ... | 1,760,372,081.086407 | ||
https://hackaday.com/2023/12/07/hacking-the-xiaomi-mi-band-8-with-custom-firmware/ | Hacking The Xiaomi Mi Band 8 With Custom Firmware | Maya Posch | [
"Reverse Engineering",
"Wearable Hacks"
] | [
"fitness band",
"fitness tracker"
] | Over the past years, fitness trackers have gone from fairly unobtrusive bands that relied mostly on smartphone apps for interaction to essentially being fashion statements and smart watches, with large screens and impressive specs. The Xiaomi Mi Band 8 is no exception, with a zippy MCU and a 1.62″ AMOLED screen that just asks for some serious rick-rolling. This was a challenge which
[Aaron Christophel] was all too happy to accept
, resulting in some reverse-engineering and flashing of custom firmware onto one of these marvels of modern wearable technology.
Block Diagram for the Apollo4 Blue Lite. (Credit: Ambiq)
The
Mi Band 8
is built around an
Ambiq Apollo4 Blue Lite
MCU which features a Cortex-M4 core for applications, along with a Bluetooth LE radio and a lot of SRAM and Flash. This naturally implies an SWD interface for programming, which was mostly a matter of reverse-engineering the PCB to find the locations for these signals and realizing that the original firmware disables the SWD interface on boot. Unfortunately the Ambiq SDK requires you to create an account, but you can get the basics from [Aaron]’s GitHub project. It appears that for BLE you do need the full SDK, and OTA updates feature a signing check, so physical access is required.
So far the display, touchscreen and light sensor are working, with the remaining peripherals just a matter of time. With a list price of around $64 for one of these fitness bands with a 192 x 490 touch-enabled AMOLED display and a variety of health-related sensors, they’d seem to be a fun toy to hack, especially when found on sale or used. | 11 | 8 | [
{
"comment_id": "6705848",
"author": "Geek Fantasy",
"timestamp": "2023-12-07T14:11:03",
"content": "Cool man! Cannot wait to see it completely hacked.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6706093",
"author": "IsRadioKill",
"timestamp": "2023... | 1,760,372,083.065384 | ||
https://hackaday.com/2023/12/07/the-chocolate-must-flow-this-holiday-season/ | The Chocolate Must Flow This Holiday Season | Kristina Panos | [
"cooking hacks"
] | [
"chocolate",
"chocolate fountain",
"conveyor",
"enrober",
"enrobing",
"flex coupler",
"motor",
"wasabi peas"
] | After a long December of hand-coating chocolates for relatives last year, [Chaz] decided that enough was enough and
built a chocolate enrobing machine
to do the dirty work for him. As a side project, he built a rotary tumbler to chocolate-coat things like wasabi peas, which we assume are designated for [Chaz]’s enemies.
This build started with an off-the-shelf chocolate fountain for which [Chaz] designed and printed a new nozzle in PLA. He also knocked off the flutes that make it fountain on the band saw and removed the rest of the material on the lathe.
The conveying bit comes from a conveyor toaster oven that [Chaz] had lying around — he removed the conveyor and hooked it up to a motor from his collection using a slightly modified flex coupler.
With the chocolate enrober complete, [Chaz] moved on building to the rotary tumbler, which is made from two thrift store pans hammered together at the edges and connects up to the front of a KitchenAid mixer. The final verdict was that this did not work as well as the enrober, but it wasn’t a complete bust — wasabi peas (and most of the kitchen) got coated in chocolate.
While we’re not sure we’d use that PLA chocolate pump more than once, we sure would like to enrobe some things in chocolate, and this seems like a good way to get it done. Check out the build video after the break.
Chocolate is good for more than coating everything in sight. Speaking of sight,
check out these chocolate optics
. | 8 | 5 | [
{
"comment_id": "6705860",
"author": "Graham",
"timestamp": "2023-12-07T14:52:43",
"content": "I’ve noticed through hours of research (aka watching How Its Made) that after being en-robbed most chocolate factories have a blower to “blow off excess chocolate”.",
"parent_id": null,
"depth": 1,... | 1,760,372,082.938394 | ||
https://hackaday.com/2023/12/06/wio-terminal-makes-passable-oscilloscope/ | Wio Terminal Makes Passable Oscilloscope | Bryan Cockfield | [
"Tool Hacks"
] | [
"display",
"microcontroller",
"oscilloscope",
"programming",
"SAMD51",
"wio terminal"
] | There was a time when getting a good oscilloscope not only involved a large outlay of capital, but also required substantial real estate on a workbench. The situation has improved considerably for the hobbyist, but a “real” scope can still cost more than what a beginner is looking to spend. Luckily, plenty of modern microcontrollers are capable of acting as a basic oscilloscope in a pinch, provided there’s a display available to interface with it. Combined with the right software, the
Wio Terminal looks like a promising option
.
The Wio Terminal is a platform gaining some popularity due to its fairly capable SAMD51 microcontroller and also its integration with a display and a number of input buttons. On the hardware side, [mircemk] mounted the Terminal in a convenient vertical orientation and broke out a pair of connectors for the inputs.
But it’s the software that really makes this project work. [Play With Microcontroller] originally developed the firmware for the PIC24 back in 2017, but
ported the code over to the Wio Terminal a couple years back
. Noting that the microcontroller is not particularly fast, the project doesn’t exactly match the specifications or capabilities of a commercial unit. But still, it does an impressive job of recreating the experience of using a modern digital scope
The Wio Terminal is a device we’ve seen around here for a few unique projects, among them a device for
preventing repetitive strain injuries
while using a computer mouse and another that is
a guide for game development in MicroPython
. And if you’re just itching to port oscilloscope software to accessible but under-powered microcontrollers, be sure to check out [mircemk]’s other oscilloscope projects like
this one built around the STM32 microcontroller
. | 3 | 3 | [
{
"comment_id": "6705882",
"author": "CMH62",
"timestamp": "2023-12-07T16:09:31",
"content": "Thx for the embedded links. I’m enjoying reading up on the game development link you posted.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6705981",
"author": "... | 1,760,372,082.662976 | ||
https://hackaday.com/2023/12/06/japans-jt-60sa-generates-first-plasma-as-worlds-largest-superconducting-tokamak-fusion-reactor/ | Japan’s JT-60SA Generates First Plasma As World’s Largest Superconducting Tokamak Fusion Reactor | Maya Posch | [
"Science"
] | [
"fusion",
"nuclear fusion",
"tokamak"
] | Comparison of toroidal field (TF) coils from JET, JT-60SA and ITER (Credit: QST)
Japan’s JT-60SA fusion reactor project
announced first plasma
in October of this year to denote the successful upgrades to what is now the world’s largest operational, superconducting tokamak fusion reactor. First designed in the 1970s as Japan’s
Breakeven Plasma Test Facility
, the JT-60SA tokamak-based fusion reactor is the latest upgrade to the original
JT-60
design, following two earlier upgrades (-A and -U) over its decades-long career. The most recent upgrade matches the Super Advanced meaning of the new name, as the new goal of the project is to investigate advanced components of the global ITER nuclear fusion project.
Originally the JT-60SA upgrade with superconducting coils was supposed to last from 2013 to 2020, with first plasma that same year. During commissioning in 2021, a short circuit in the poloidal field coils caused a lengthy investigation and repair, which was completed earlier this year. Although the JT-60SA is only using hydrogen and later deuterium as its fuel rather than the deuterium-tritium (D-T) mixture of ITER, it nevertheless has a
range of research objectives
that allow for researchers to study many aspects of the ITER fusion reactor while the latter is still under construction.
Since the JT-60SA also has cooled divertors, it can sustain plasma for up to 100 seconds, to study various field configurations and the effect this has on plasma stability, along with a range of other parameters. Along with UK’s JET, China’s HL-2M and a range of other tokamaks at other facilities around the world, this should provide future ITER operators with significant know-how and experience long before that tokamak will generate its first plasma. | 35 | 10 | [
{
"comment_id": "6705685",
"author": "ian 42",
"timestamp": "2023-12-07T05:24:42",
"content": "fusion has been 10 years away since the 60’s. And will be 10 years away when I buried..That said, plasma research is a good thing to be doing..",
"parent_id": null,
"depth": 1,
"replies": [
... | 1,760,372,083.015283 | ||
https://hackaday.com/2023/12/06/a-revolution-in-vehicle-drivetrains/ | A Revolution In Vehicle Drivetrains? | Navarre Bartz | [
"car hacks",
"News"
] | [
"drivetrain",
"electric vehicle",
"evs",
"suspension"
] | Power delivery in passenger vehicle drivetrains hasn’t changed much since the introduction of the constant velocity (CV) joint in the 1930s. Most electric vehicles still deliver power via the same system used by internal combustion cars. Hyundai/Kia has now revealed a system they think will provide a new paradigm with their
Universal Wheel Drive System (Uni Wheel)
. [via
Electrek
]
What appears at first to be a hub motor is in fact a geared wheel that keeps the motor close without the problem of high unsprung weight. Power is fed into a sun gear which can move independently of the wheel allowing the system to maintain a more consistent driveline and avoid power variability over the range of suspension travel like you’d find in a CV joint experiencing high deflection.
We have some concerns about the durability of such a system when compared with the
KISS
and long development history of CV joints, but we can’t deny that moving the motors of an electric vehicle out to the corners would allow more packaging flexibility for the cargo and passenger areas. We’re also excited to see open source replicas make their way into smaller robotics projects now that the images have been released. If you’ve already made one in CAD,
send us a tip
at
tips@hackaday.com
.
Looking for more interesting innovations in electric cars? How about an
off-grid camper van
? If you think automakers are
overcomplicating something that should be simple
, read the
Minimal Motoring Manifesto
. | 47 | 23 | [
{
"comment_id": "6705549",
"author": "MmmDee",
"timestamp": "2023-12-07T00:11:24",
"content": "Where’s the young Instagram/TikTok boy that yells, “bullsh*t”.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6705971",
"author": "young Instagram/TikTok",... | 1,760,372,082.789002 | ||
https://hackaday.com/2023/12/06/a-fully-transparent-air-bubble-display/ | A Fully-Transparent Air Bubble Display | Kristina Panos | [
"classic hacks",
"Misc Hacks"
] | [
"acrylic",
"bending acrylic",
"bubble display",
"leds",
"solenoid"
] | We all have good intentions when starting a new project, but then again, we all know where those lead. Such is the case with [RealCorebb]’s
BBAir project, a completely transparent air bubble display
. Although the plan was to spend about three months on it, the months slowly added up to a full year of tinkering.
It all started when [RealCorebb] made a subscriber counter using Minecraft campfire smoke to display the digits. Someone suggested using air to implement the next iteration, and for [RealCorebb], it was challenge accepted. After considering a syringe for each channel, a separate pump, or one pump and many solenoids, [RealCorebb] settled on solenoids to push air, and designed a PCB to reduce the amount of wire spaghetti.
Once [RealCorebb] created an acrylic enclosure and wired everything up, it was time to test it out. Everything worked, except that air was leaking from somewhere, which turned out to be the way the solenoids were installed. Then, of course, it was time to don sunglasses and write the code. We still don’t know if [RealCorebb] settled on water, glycerine, or silicone oil, but the end result is quite nice, and we’re betting on glycerine. Be sure to check out the build video after the break, which has English subtitles.
Although we’ve seen our share of bubble displays before, we often discuss
bubble LEDs displays like this one
. | 5 | 4 | [
{
"comment_id": "6705503",
"author": "Alan Kilian",
"timestamp": "2023-12-06T22:42:38",
"content": "A group of of from the Twin Cities Robotics group helped the artist Bruce Shapiro build a three-story tall, 96-tube wide bubble display at the Ontario Science Centre.https://www.taomc.com/pipe-dreamTh... | 1,760,372,082.832075 | ||
https://hackaday.com/2023/12/06/anthrobots-tiny-robots-from-tracheal-epithelium-cells-that-can-fix-neural-damage/ | Anthrobots: Tiny Robots From Tracheal Epithelium Cells That Can Fix Neural Damage | Maya Posch | [
"Science"
] | [
"anthrobots",
"cellular regeneration"
] | Although we often regard our own bodies and those of the other multicellular organisms around us as a singular entity, each cell that makes up our body is its own, nano-robot. One long-existing question was whether these cells can be used for other tasks — like biological robots — after they have specialized into a specific tissue type, with a
recent study
by [Gizem Gumuskaya] and colleagues in
Advanced Science
(with
Nature
news coverage
) indicating a potential intriguing use of adult human epithelial cells recovered from the trachea.
Human bronchial epithelial cells self-construct into multicellular motile living architectures. (Credit: Gumuskaya et al., 2023)
After extraction, these adult cells were kept in an extracellular matrix (ECM, Matrigel) in conditions promoting cell division, followed by ECM dissolution after 14 days and subsequent culturing of the spherical clumps of cells that had thus formed in a water-based, low-viscosity environment. This environment, along with the addition of retinoic acid promoted the development of outward-facing cilia, rather than the typical inward type with a gel-based ECM.
These spheroids (anthrobots, referencing their human origin) generally showed the ability to move using these cilia, with the direction largely determined by the symmetry of the sphere. Multiple of these motile spheroids were then placed on a layer of human neural tissue, in which a scratch had damaged a number of the neurons to form a gap. The anthrobots grouped together over the course of days to form a bridge across the gap, with the neural tissue observed to regrow underneath this bridge, a behavior that could not be repeated by using a dummy support consisting out of agarose on another neural sample, indicating that it is this living bridge that enabled neural regeneration.
Although the researchers rightfully indicate that they are uncertain which factors actually induce this restorative effect in the neurons, it offers exciting glimpses into a potential feature where neural damage is easily repaired, and biological robots made from our own cells can be assembled to perform a variety of tasks. | 10 | 3 | [
{
"comment_id": "6705409",
"author": "Cyna",
"timestamp": "2023-12-06T19:54:49",
"content": "Epithelial cells are the best for cloning (hint: long ladder).",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6705523",
"author": "MmmDee",
"timestam... | 1,760,372,082.887152 | ||
https://hackaday.com/2023/12/06/when-nearly-flat-isnt-really-flat/ | When Nearly Flat Isn’t Really Flat | Jenny List | [
"Hackaday Columns",
"Slider",
"Tech Hacks"
] | [
"flat surface",
"machining",
"whitworth"
] | Is Mk really flat? Thomas Nugent,
CC BY-SA 2.0
.
From where I am sitting, the earth is flat. The floor that runs the length of the unit my hackerspace sits in is flat, the concrete apron behind it on which we test our Hacky Racers is flat, and a few undulations in terrain notwithstanding, it remains flat as I walk up the road towards Stony Stratford.
Of course, Hackaday hasn’t lost its mind and joined the conspiracy theorists, the earth is definitely spherical as has been known and proved multiple times since antiquity. But my trivial observation made in a damp part of Buckinghamshire still holds; that for a given value of flat which disregards a few lumps and bumps in the ground, my corner of the English city of Milton Keynes is pretty flat. Which leads from a philosophical discussion to an engineering one, if I can reasonably describe a city-sized area on an Earth-sized sphere as flat, how flat does a surface have to be to be considered flat? And from that stems a fascinating story of the evolution of precision machining.
Precision Starts With Something Flat
A bodger’s pole lathe in action. Simon Speed,
CC0
.
The history of machine tools stretches back into antiquity, in that simple lathes have been found in the archeological record of several regions of the world. There’s an industry which just about survives using rudimentary lathes pretty close to where I grew up, the
chair bodgers
in the English Chiltern hills use temporary pole lathes which wrap a rope around the part to be turned and balance it against the springiness of a tree branch to turn traditional wooden chair legs.
But these machines and their more refined descendants, while very good at producing the turned items they do, are not precision tools. The dimensions of the bodger’s chair leg depends on his eye and skill rather than the machine itself, because it lacks the flat bed of a modern machinist’s lathe as a baseline for its tooling. Like the city of Milton Keynes mentioned above, it’s easy to make something that looks pretty flat, but it remains hard to make something which is flat enough to use as a reference from which to machine other things. The method for making a truly flat surface without another to compare it against is thus one of the most significant innovations in the history of engineering, and definitely deserves a look.
Flatness Without Precision Tooling
Joseph Whitworth, Popular Science Monthly Volume 32,
Public domain
.
The problem facing anyone tackling the manufacture of a flat surface is that by using a tool on a piece of material, be it one stone rubbed against another, a plane on a piece of wood, or a file on a piece of metal, the work piece will reflect the imperfections in the tool and in the technique.
Thus it’s not too difficult to make something that looks
fairly
flat, but the result will not be
really
flat. Rub two pieces of stone together and they will become smooth for example, but it’s likely that they will tend towards one becoming concave and the other convex. The problem of making a truly flat surface in this way was solved in the 1830s by Joseph Whitworth, he of the Whitworth standard threads, who instead of testing two surfaces against each other, instead used three.
The idea was that having a set of three plates and testing them in pairs against each other in turn, he could eliminate the errors in one affecting the other. By coating the surfaces with engineer’s blue, a dye, he could lap one surface against another leaving the areas in which there was a gap between them as blue. He could thus machine the layers down where the blue dye had been worn away and repeat the process against each of the other plates in turn, until he was left with three perfectly flat surfaces that could be used as standards in his machine tools.
It’s by necessity a slow process as you can see in this video
, but its beauty is that it can be done without precision tooling.
There probably aren’t many inventions that could be claimed as somewhere at the basis of so many others as can Whitworth’s flat surfaces without being more widely known in their own right. But the precision his technique afforded to every subsequent piece of engineering lives on with us today, and its elegance is in its simplicity. In every engineer lurks a metrologist, and it’s in things like Whitworth’s three plate method that mine finds fulfillment.
Surface plate header image: Rrudzik,
CC0
. | 84 | 20 | [
{
"comment_id": "6705360",
"author": "Ale",
"timestamp": "2023-12-06T18:14:07",
"content": "O, un mármol de ajuste !",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6706335",
"author": "Patrick LeBoutillier",
"timestamp": "2023-12-08T19:09:31"... | 1,760,372,083.194921 | ||
https://hackaday.com/2023/12/05/affordable-networking-for-your-classic-mac/ | Affordable Networking For Your Classic Mac | Jenny List | [
"Mac Hacks",
"Retrocomputing"
] | [
"Macintosh SE/30",
"network card",
"SE/30"
] | The Mac SE and in particular the Mac SE/30 number among the more sought-after of the classic all-in-one Apple computers, and consequently their peripherals including network cards are also hard to find and pricey. Even attempts at re-creating them can be expensive, usually because the chips used back in the day are now nearly unobtainable. But if the search is widened to other silicon it becomes possible to create substitutes, as [Richard Halkyard] is doing with
a modern version of the SE Ethernet card
.
The chip which makes this possible is the Microchip ENC624J600, an embedded 10/100 Ethernet controller with an impressively configurable interface that can be easily mated to the 68k bus. For The SE it’s mapped to a memory area, while for the /30 there can be a declaration ROM which informs the machine where it is.
This is an as yet unfinished project, a work in progress. But it deserves to succeed, and if we can provide encouragement by featuring it here then it’s definitely worth a look. Or course, this is by no means the only
replacement for an original board
.
SE/30 picture: Cornellanense,
CC BY-SA 4.0
. | 1 | 1 | [
{
"comment_id": "6705567",
"author": "Joshua",
"timestamp": "2023-12-07T00:39:55",
"content": "Thanks for the article.Personally, though, I’ve always found vintage networks to be fascinating.Like, for example, PhoneNet.The other way round, a modern implementation of a vintage network technology like... | 1,760,372,082.70276 | ||
https://hackaday.com/2023/12/05/retrotechtacular-the-gunsmith-of-williamsburg/ | Retrotechtacular: The Gunsmith Of Williamsburg | Jenny List | [
"Hackaday Columns",
"Retrotechtacular",
"Weapons Hacks"
] | [
"gunsmith",
"long rifle",
"rifle"
] | A modern firearm is likely to be mass-produced using high-precision machine tools, and with a uniformity to the extent that parts from one can be interchanged with those from another. This marks a progression of centuries of innovation, in gunsmithing, in machine tooling, and in metallurgy. In the 18th century there was little of the innovations found in a modern weapon, and a rifle would have been made entirely by hand through the work of a master gunsmith.
The video below the break
is a fascinating 1969 film following Wallace Gusler, the gunsmith at the museum town of Williamsburg, Virginia, as he makes an 18th-century muzzle-loading flintlock rifle from raw materials. It’s a long video, but it leaves nothing out and has a really informative commentary we’re told from the gunsmith himself.
The film opens with a piece of wrought iron being forged into a long strip.
We’ve talked about wrought iron
as a difficult-to-find blacksmith’s material before here, so this immediately makes us curious as to what material the current Williamsburg gunsmiths use. The strip is formed round a mandrel and laboriously forge-welded to form a rough tube, before being bored with a series of drills and then rifled with a toothed slug. The finishing is done by had with a file, with the rough tube being filed to an octagonal shape.
We follow through all parts of the rifle, the breech plug with its tang for mounting the rear of the barrel, and then the proofing of the barrel with four times its usual charge. Having made the barrel he turns to the lock, and aside from the major parts being made from wrought iron and case-hardened in a sealed crucible full of charcoal powder we see the different techniques required to work with spring steel. Aside from the craftsmanship on show it’s a full introduction to 18th-century weapon technology, as these represented the peak of what was available at the time.
The iron parts complete, the rifle is by no means finished. The stock and rifle furniture are crafted from a single piece of maple wood, carefully shaped over several different stages of the weapon’s construction. all metal parts are recessed flush into the wood, and all the brass components are made by casting rather than from brass sheet. We see the mould being prepared and the molten brass being poured, and once the various parts have been mated with the woodwork we see the process of hand-engraving. Finally the wood is finished with a solution of iron filings in nitric acid, and oiled with linseed oil for a beautiful finish.
As someone familiar with the blacksmith’s art, the thing that comes through most strongly from this film is not merely the level of skill but the breadth of skills it shows An 18th century gunsmith was at the same time a master blacksmith, woodworker, brass worker, engraver, and artist, and it’s no surprise that these rifles were as highly prized in their day as they are now. Mr. Gusler is at the peak of all these crafts, and we’re privileged that we’re able to watch him at work in such detail. In the film he’s a young man, and a quick Google search finds that his career at Williamsburg lasted into the 21st century He’s clearly remained the pre-eminent expert on the American long rifle, and we can find articles written by him in recent years. Our thanks to [Ken Boak] for the tip on this one, it’s been a treat. | 11 | 8 | [
{
"comment_id": "6705074",
"author": "Doug Leppard",
"timestamp": "2023-12-05T21:04:59",
"content": "I have our family musket. Unbelievably heavy. We have never fired it. Will be interesting to see how it was made. Takes a lot to fire just one shot. We have a powder horn also.I doubt an Arduino or... | 1,760,372,083.451918 | ||
https://hackaday.com/2023/12/05/a-single-board-computer-with-vacuum-tubes/ | A Single Board Computer, With Vacuum Tubes | Jenny List | [
"classic hacks",
"computer hacks"
] | [
"1-bit",
"MC14500",
"vacuum tube"
] | We have occasionally featured vacuum tube computers here at Hackaday and we’ve brought you many single board computers, but until now it’s probable we haven’t brought you a machine that combined both of these things.
Now thanks to [Usagi Electric] we can see just such a board
, in the form of his UE-0.1, a roughly 260 by 210 mm PCB with 24 6AU6 pentodes on board that implements a simple one-bit CPU.
The architecture starts with the MC14500B 1-bit microcontroller, which was the subject of a previous vacuum tube computer. People found the unusual architecture difficult to understand, so this board is an even simpler take. It doesn’t have all the features of the Motorola original but it is (just) enough to be a CPU.
The tubes are arranged in groups of four with heaters in series from a 24 V supply, while the inputs and clock come in the form of on-board suitably retro-looking switches. The final touch is a VFD of the type used in bar graphs, were used to show the state of the various bits. It’s a fully working computer in the simplest sense, and definitely worth a look in the video below the break.
It would be interesting to see whether the tube count could be reduced further, or is this a record. The number of physical devices could be cut by using tubes with more than one device in them such as double-triodes, but perhaps that would be cheating.
Meanwhile, if you think vacuum computing is all about the old stuff,
perhaps you should look at the state of the art
. | 8 | 3 | [
{
"comment_id": "6705128",
"author": "Jerome Hess",
"timestamp": "2023-12-06T03:32:31",
"content": "WOW, if I were still in college with the memory I had and the spare time to go along with it",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6705132",
"autho... | 1,760,372,084.255571 | ||
https://hackaday.com/2023/12/05/mining-and-refining-titanium-our-youngest-industrial-metal/ | Mining And Refining: Titanium, Our Youngest Industrial Metal | Dan Maloney | [
"Engineering",
"Featured",
"Original Art",
"Slider"
] | [
"magnesium",
"Mining and Refining",
"reduction",
"titanium",
"vacuum arc remelting"
] | Earlier in this series, we made the case for copper being
“the metal that built technology.”
Some readers took issue with that statement, noting correctly that meteoric iron and gold were worked long before our ancestors were able to locate and exploit natural copper outcroppings, therefore beating copper to the historical punch. That seems to miss the point, though; figuring out how to fashion gold decorations and iron trinkets doesn’t seem like building the foundations for industry. Learning to make tools from copper, either pure or alloyed with tin to make bronze? Now that’s how you build an industrial base.
So now comes the time for us to make the case for our most recent addition to humanity’s stable of industrial metals: titanium. Despite having been discovered in 1791, titanium remained locked away inside abundantly distributed ores until the 1940s, when the technological demands of a World War coupled with a growing chemical prowess and command of sufficient energy allowed us to finally wrest the “element of the gods” from its minerals. The suddenness of it all is breathtaking, too; in 1945, titanium was still a fantastically expensive laboratory oddity, but just a decade later, we were producing it by the (still very expensive) ton and building an entirely new aerospace industry around the metal.
In this installment of “Mining and Refining,” we’ll take a look at titanium and see why it took us over 11,000 years to figure out how to put it to work for us.
Starting With Sand
For something that has been commercially exploited for less than a century, titanium is surprisingly abundant. It’s the ninth most abundant element in Earth’s crust, making up more than half a percent by mass. Titanium is never found in the metallic state in nature, but rather as oxides like titanium dioxide (TiO
2
), and as such is widely distributed around the world.
Rutilated quartz from Minas Gerais, Brazil. The needle-like crystals are the rutile. Source: James St. John,
CC BY 2.0
The chief mineral ores of titanium are rutile and ilmenite. Rutile is basically pure TiO
2
in crystal form that occurs in many types of rocks including quartz, gneiss, and schist. Ilmenite is a titanium oxide complexed with iron (FeTiO
3
), and while sometimes found in its pure form, it’s more often found mixed with manganese and magnesium. Ilmenite is mostly found in heavy mineral sands that have weathered out of solid rock deposits, which has the effect of making it relatively easy to harvest using standard open-cast mining techniques.
There are large ilmenite deposits in South Africa, Australia, Canada, China, and Ukraine. Commercially viable rutile deposits are harder to come by, with most of the mineral coming from Australia, countries around the southern tip of Africa, and Ukraine. Something like 80% of the world’s supply of titanium comes from ilmenite, with a mere 5% sourced from rutile; the rest comes from “titaniferous slags,” which are essentially iron- and titanium-containing waste products from titanium refining processes.
An open-cast ilmenite mine in Norway, considerably less glamorous than rutile. Source: Mikenorton,
CC BY-SA 4.0
Like
aluminum
, titanium is an element that forms thermally and chemically stable oxides, so liberating it from its minerals is a complex and energy-intensive process. Processing begins with mining, which for certain ilmenite deposits can be as simple as scooping up sand with loaders or eroding it with high-pressure water and pumping up the resulting slurry. Rutile is also sometimes recovered directly from weathered sands, but when either mineral occurs embedded in other rocks, more extreme measures such as blasting and crushing may be required to get the ore into grains fine enough to be conveniently moved around the processing plant.
Concentration of the ore and removal of non-ore material (gangue) and other valuable minerals come next. Ore feedstocks with a lot of iron in them, such as ilmenite, undergo a magnetic separation step, with powerful spinning magnets that remove magnetic particles from ground ore carried by a conveyor belt. Electrostatic separation, where electrostatically charged ore particles pass through strong electric fields to remove titanium oxide particles from gangue, is also used. Spiral concentrators, which are also used in
graphite refining
, are often used to separate the dense gangue particles in an ore slurry from less dense titanium oxides.
Bringing The Heat
Once the raw ore has been concentrated, the tightly bound oxygen in the titanium oxide needs to be removed. The Kroll process is the most common method used today, and to say that it’s an energy-intensive process is a bit of an understatement. The first step is to replace the oxygen atoms in the titanium oxides with chlorine to make titanium tetrachloride (TiCl
4
). In the case of ilmenite feedstock, the reaction looks like this:
Carbon, usually in the form of coke, is added to the titanium ore, after which 900°C chlorine gas is blasted through the reaction chamber until the reaction is complete. The resulting TiCl
4
, also known as “tickle,” is a dense, volatile liquid with a low boiling point (136.4°C), which is convenient because that makes it relatively easy to purify by distillation. Impure TiCl
4
is heated in a stainless steel distillation chamber, and the vapors are fed directly into the main Kroll reaction chamber, where the high-energy magic happens.
The Kroll reactor is a thick-walled stainless steel vessel with an argon atmosphere. At the bottom of the vessel, heated to about 850°C, is a pool of liquid magnesium. The incoming pure TiCl
4
gas reacts with the metallic magnesium over a period of up to four days to form magnesium chloride (MgCl
2
) and elemental titanium:
The slug of titanium that forms in the reaction chamber is called titanium sponge, and aptly so given its porous nature. The sponge holds a lot of the MgCl
2
waste; this is recovered by another round of distillation by heating the sponge to more than 1,400°C and condensing the vapor. The magnesium metal in the MgCl
2
can then be recovered for reuse by electrolysis.
Titanium ingot, fresh from the vacuum arc remelting furnace. Source: Alexey Rezvykh, Adobe Stock.
Once the titanium sponge slug is allowed to cool and removed from the Kroll reactor, surface scale formed by reaction products is removed. Different parts of the sponge have different grades of titanium — the low-grade waste from the bottom of the slug, mid-grade stuff at the top and around the outside, with the highest-grade metal at the core. A guillotine shear slices the slug into sections, with the mid-grade product going for blending and further refining while the high-grade metal is further chopped and crushed into small chunks. These pieces, along with any alloying metals that might be needed, get rammed into a press that forms them into an electrode.
Placed into a water-cooled vacuum arc remelting (VAR) furnace and heated to 1,700°C by an electric current, the electrode melts into a titanium ingot. Depending on the properties required from the finished metal, the ingot may go through another VAR purification. Pure ingots then go through a long series of forging, milling, grinding, and rolling processes, typically with a heat-treatment process in between each operation. The result is either plates, billets, or coiled sheets of titanium alloy, ready for manufacturing use.
White As Can Be
Metallic titanium isn’t the only desirable product from the mining and refining of titanium ore. Titanium dioxide itself has hundreds of industrial uses, most of which have to do with the brilliant whiteness of the powdered solid. Titanium dioxide is present in something like 60% of all pigments produced; look at the nearest painted wall or ceiling and it’s almost certain it contains at least some TiO
2
. It’s also important in paper manufacturing, pharmaceuticals and cosmetics, sunscreen products, ceramic glazes, food additives, and thin-film optical products.
All TiO
2
starts with TiCl
4
feedstock; in fact, 90% of the “tickle-four” manufactured every year goes to the production of titanium dioxide, typically with a simple hydrolysis reaction:
Alternatively, the tickle can just be blasted with oxygen:
Either way, the oxidation of TiCl
4
results in fine white crystals of titanium dioxide, which are captured, dried, ground, graded, and packaged for shipping.
Thermite Makes It Better
Almost nothing about the mining and refining of titanium is environmentally friendly. Huge energy inputs are needed all along the way, from the fossil fuels needed to harvest and prepare the ore to the electricity needed to run the vacuum arc furnaces and recycle the magnesium chloride. Unfortunately, there aren’t many points in the process that are amenable to the green treatment, thanks largely to the chemical and thermal stability of titanium oxides.
That doesn’t mean the search isn’t on for ways to make titanium refining more sustainable, though. One Japanese company, Toho Titanium, is working on a promising
pyrotechnic thermite method of producing titanium
. The method combines powdered titanium ore with fluorite, the mineral form of calcium fluoride, along with some powdered aluminum. When the mixture is ignited it undergoes an extremely energetic thermite reaction, which heats the smelter without the need for external energy inputs. The reaction reduces the titanium oxides in the ore to a pool of molten titanium under a slag of aluminum oxide and calcium fluoride. The titanium is further purified by electrolytic refining, but even with that energy-intensive step, the company claims their process can reduce electricity consumption by 70% to 80%. | 9 | 4 | [
{
"comment_id": "6705090",
"author": "hmm...",
"timestamp": "2023-12-05T22:45:01",
"content": "Electrodeoxidation of TiO2 in molten salt system is far more practical than thermite and will likely replace the kroll process in timeAnhydrous NaCl and CaCl2 salt (500 g in molar ratio 0.48:0.52) were pla... | 1,760,372,083.640154 | ||
https://hackaday.com/2023/12/05/cockpit-instrument-respectfully-retasked-as-a-clock/ | Cockpit Instrument Respectfully Retasked As A Clock | Dan Maloney | [
"clock hacks"
] | [
"avioics",
"cockpit",
"dac",
"distance measuring equipment",
"DME",
"Panaplex",
"pic16"
] | How do you convert an old cockpit instrument into a clock? Easy: just build a circuit that convinces it it’s in the air, and the rest will take care of itself.
Now obviously, little about [porkfreezer]’s
conversion of King KI 266 DME into a clock
was actually easy; working with avionics rarely is. DME stands for “Distance Measuring Equipment,” an instrument that’s part of the radio navigation suite of many aircraft. DME measures the line-of-sight distance of a plane to a ground station by measuring the time it takes for a signal to return after the plane interrogates it. The plane-mounted equipment includes a UHF transceiver and a display for the cockpit instrument panel, which accepts an analog voltage signal from the transceiver and translates it into a readout on the nice
Panaplex
digital display.
Rather than gutting the thing and just driving the display directly, [porkfreezer] decided to build a circuit to generate the proper signals for the DME. The board uses a PIC16 and an MCP47C dual 10-bit digital-to-analog converter to generate the voltages needed, while a USB-powered DC-DC converter provides the ±15 volt supply the DME display expects.
Everything lives on a PCB that fits right on the back of the instrument. Sadly, the connector needed to mate up to the one on the instrument was outlandishly expensive — again, avionics — so [porkfreezer] had to solder the board directly to the DME’s pins. Otherwise, this would have been a completely reversible hack.
Still, it’s an interesting reuse of an unusual piece of gear, and one that respects the original design as much as possible. That counts as a win in our book. | 3 | 2 | [
{
"comment_id": "6705126",
"author": "Mr Name Required",
"timestamp": "2023-12-06T03:16:38",
"content": "Can’t see the connector directly but from the pattern I reckon it’s likely to be a military/avionics Winchester MRAC unit, available in a bewildering array of options of which none are cheap, eve... | 1,760,372,083.405394 | ||
https://hackaday.com/2023/12/05/mini-apple-iie-now-fully-functional/ | Mini Apple IIe Now Fully Functional | Navarre Bartz | [
"Retrocomputing"
] | [
"Apple //e",
"apple II",
"apple iie",
"Mega II",
"retrocomputer",
"rp2040"
] | Here at Hackaday, we love living in a future with miniaturized versions of our favorite retrocomputers. [James Lewis] has given us another with his fully functional
Apple IIe from the Mega II chip
.
When we last checked in on the
Mega IIe,
it was only just booting and had a ways to go before being a fully functional Apple II. We really love the modular dev board he designed to do the extensive debugging required to make this whole thing work. Each of the boards is connected with jumper pins, which [Lewis] admits would have been better as edge connectors since he should’ve known he’d be unplugging and replugging them more than he’d like.
This modular prototyping system paid dividends late in the project when a “MEGA bug” threatened the stability of the entire system. Since it was confined to the keyboard PCB, [Lewis] was able to correct the error and, swapping for the third revision of the board, everything that had been crashing the system now ran.
There were still some issues going to the final unified PCB that nearly made him give up on the project, but perseverance paid off in the end. Combining vintage chips and multiple RP2040s isn’t for the feint of heart.
Now that you have a more conveniently-sized Apple II, why not teach it some new tricks like
digital photography
or
ChatGPT
? | 1 | 1 | [
{
"comment_id": "6773518",
"author": "Mark Manning",
"timestamp": "2024-07-05T19:58:34",
"content": "Fantastic project. Here is one that would be great also – A stand alone card that allows you to plug in old 5.25″ Apple Floppy drives and provides a USB cable that goes to a PC. In this way, you are ... | 1,760,372,083.360898 | ||
https://hackaday.com/2023/12/04/finally-a-typeface-for-hardware-people/ | Finally! A Typeface For Hardware People | Jenny List | [
"Art"
] | [
"ASCII",
"font",
"serial",
"trace"
] | When it comes to novelty typefaces there is no shortage of weird and wonderful fonts to be found when you have finally tired of Comic Sans. Everything from bananas forming letters to Wild West saloon lettering can be yours, plus of course our favourite, the embossed Dymo label. But there’s a new kid on the novelty typeface block, and for us it sweeps all before it.
Scopin’ Sans is as its creator [Guy Dupont] calls it “A typeface for hardware people”
, and its party trick is that it doesn’t produce letters. Instead it forms an oscilloscope trace that displays what it would look like as serial data. Instantly your text jumps straight to 1337, and you win the internet.
We have shamefacedly to admit that we don’t know binary ASCII by sight, so we’ll have to take his word for it. But for the curious
there’s a demo
from which you can amuse yourself creating traces, and if you can’t recognize serial ASCII then the chances are few of the people around you can either. We take our hats off to [Guy], and it’s something we’re sure we’ll use at some point to delight and confuse our friends. It’s not the first font we’ve brought you,
here are some more if you come from the bitmap era
. | 11 | 6 | [
{
"comment_id": "6704979",
"author": "mip",
"timestamp": "2023-12-05T07:00:28",
"content": "This is my kind of humor. I love it!",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6704981",
"author": "Stephen Walters",
"timestamp": "2023-12-05T07:02:22",
... | 1,760,372,084.077148 | ||
https://hackaday.com/2023/12/06/operate-your-own-nuclear-reactor-virtually/ | Operate Your Own Nuclear Reactor, Virtually | Al Williams | [
"Games"
] | [
"Nuclear Reactor",
"simulator"
] | If you’ve ever wanted to operate your own nuclear reactor, you probably aren’t going to get one in your backyard shop. However, thanks to the University of Manchester,
you can get a simulated one in your browser
. The pressurized water reactor looks realistic and gives you controls that — we are fairly sure — are greatly simplified compared to the real thing.
We suggest you start with the tour before you start unless, you know, you’ve operated a reactor before. You have to balance the control rods, the coolant pumping, and the steam output to produce as much power as possible without melting the core.
If the reactor were real, the pressure vessel would weigh as much as two 747 jets! Despite the high-tech, the business end is a conventional steam generator. The only difference is that the steam is made by the heat of the nuclear reaction instead of by burning coal or gas.
To operate the reactor, you’ll turn on the coolant pumps and wait for the high-pressure liquid to reach 290 C. In real life, this takes about 8 hours, but lucky for us, the simulation is sped up. Once you reach the right temperature, you can lift the control rods to start generating heat. This will let you adjust the steam output to try to match the demand at any given time. But if you go out of bounds, the reactor will helpfully shut down. Of course, that doesn’t help your score.
We don’t know how realistic it is, but we do know Homer Simpson probably has fewer shutdowns than we do. There are
different types of reactors
, of course. Operating them may be difficult, but creating fuel for them is no
simple task
, either. Just maybe put out your
candles
before you start playing. | 33 | 14 | [
{
"comment_id": "6705308",
"author": "tonygoacher",
"timestamp": "2023-12-06T16:41:22",
"content": "Or you could go back to 1981 and run thishttps://en.wikipedia.org/wiki/Scram_(video_game)",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6705356",
"au... | 1,760,372,083.907066 | ||
https://hackaday.com/2023/12/06/ask-hackaday-could-rating-airlines-stop-flights-from-spreading-diseases/ | Ask Hackaday: Could Rating Airlines Stop Flights From Spreading Diseases? | Lewin Day | [
"Featured",
"Interest",
"Original Art",
"Rants",
"Slider"
] | [
"air travel",
"airline",
"data collection",
"Disease",
"flights",
"flights from hell",
"infectious diseases",
"website"
] | A few weeks ago, I found myself the victim of flights from hell. My first flight was cancelled, leaving me driving home late at night, only to wake again for a red-eye the next morning. That was cancelled as well, with the second replacement delayed by a further hour. All in all I ended up spending a good ten hours extra in the airport surrounded by tired, sick, and coughing individuals, and ended up a full 16 hours late to my destination. On the return, I’d again tangle with delays, and by the weekend’s close, I’d contracted a nasty flu for my trouble.
All this had me riled up and looking for revenge. I had lost hours of my life to these frustrations, and the respiratory havoc claimed a further week of my working life. It had me realizing that we could surely improve the performance and hygiene of our airliners with a simple idea: a website called Flights From Hell.
Clean Up Your Act
The concept of Flights From Hell is simple. Let’s say you catch a flight, get home, and the next day, you realize you caught something from the plane. You point your browser at Flights From Hell, and punch in your flight number, departure time, and your seat allocation in the plane. You then log what you think you caught on the plane, be it COVID-19, the flu, the common cold, or whatever. Ideally, thousands of passengers on thousands of flights will do the same, and it could all be tied up in a neat little bow by hooking it up with already-existing flight data APIs.
So far, so simple, right? But there’s a magic to it. First things first, it becomes a useful tool for tracking the spread of airborne diseases. Imagine finding a single hot flight from Chicago to Dallas Fort Worth, and then looking at how infected passengers then spread communicable diseases all over the country on their connecting flights. There’s potential value in this from a disease control perspective.
Imagine seeing a plot of other passengers that befell the same fate. Credit:
Goran tek-en, CC BY-SA-4.0
More so, though, it could be used as a agitating tool to improve air travel. Monthly statistics could be collated to determine the routes, airports, airplanes, and airlines most likely to get you sick. Maybe sitting in a 737 by the emergency exit is a particular hotspot for catching something. Maybe a certain airline performs poorly, and routinely sees more passengers getting off ill than its rivals.
Suddenly, there’s another factor at play when you’re booking your next flight. In the back of your mind, you’re thinking that the budget carrier you usually use just got a really bad rating last month on Flights From Hell. Checking the site, you note that you’re eight times less likely to get sick with a rival carrier based on past performance.
It almost doesn’t matter whether the site’s stats are a perfect predictor or not; put the data out there, and it will influence people’s decision making. Suddenly, this creates a profit motive for airlines. If they’re routinely losing ticket sales because their stats are so poor on Flights From Hell, that’s no good. Someone upstairs better come up with a plan on how to fix the problem. Maybe it’s better air filters, or a change to ventilation settings. Maybe it’s better surface cleaning practices in between flights.
You could pick a seat based on statistics that suggest the least likely parts of the plane to fall ill. Credit:
Bernd K, CC BY-SA-4.0
In this world, the airlines are forced to compete on hygiene because the data is out there. You’ll see ads with smiling flight attendants touting the value of cleaner air and healthier flights. Airlines with a good record will boast about how thousands fewer passengers got sick on their flights versus their rivals on the same routes. At the extreme, airlines might even get serious about stopping obviously sick passengers from boarding a flight.
Of course, building a better world won’t necessarily be easy. The whole concept depends on users taking the time to submit data to a website. For those in the depths of a nasty head cold, that’s perhaps less likely unless they’re feeling particularly vitriolic towards the airline. There’s also the problem of data verification. A valid boarding pass or ticket is plenty to prove you caught a flight, but how do you prove you got sick there? Even if you’re not proving you got sick
on
the flight, just proving to a website you’re actually sick at all is a difficult thing to do. Photos of RAT tests can readily be faked, after all, and nobody’s going to drag themselves to a doctor for an “official test” just to help out a community project with some data collection.
Ultimately, it’s an idea with promise, but flaws. In any case, as I struggle to recover from the worst flu of my life, I just here lamenting the fact that I didn’t book with a different airline. Until Flights From Hell (HellFlights? Flightsi?) gets built, I just wish I had some way to tell the world the fate that befell me that frustrating weekend. | 82 | 24 | [
{
"comment_id": "6705251",
"author": "Mark Topham",
"timestamp": "2023-12-06T15:17:22",
"content": "You don’t actually know where you picked stuff up from.Many things have 2-3 incubation days, even things like food poisoning can have 24-48hr incubation periods and that’s directly ingested.As someone... | 1,760,372,084.206556 | ||
https://hackaday.com/2023/12/06/the-deere-disease-spreads-to-trains/ | The Deere Disease Spreads To Trains | Jenny List | [
"Reverse Engineering"
] | [
"drm",
"newag",
"reverse engineering",
"right to repair",
"trains"
] | If the right-to-repair movement has a famous story, it’s the familiar green and yellow John Deere tractor. Farmers and mechanics have done their own repairs as long as there have been tractors, but more recent Deeres have been locked down such that only Deere-authorised agents can fix them. It’s a trend that has hurt the value of a second-had Deere, but despite that it appears to be spreading within the machinery world. Now there’s a parallel on Polish railways, as
Polish-made Newag electric passenger trains have been found to give errors when serviced by non-Newag workshops
.
At the heart of the problem are the PLCs which control all aspects of a modern rail traction system, which thanks to a trio of Poland and Germany based researchers have been found to play a range of nasty tricks. They’ll return bogus error codes after a set date which would presumably be reset by the official service, if the train has been laid up for a while, or even if they are detected via GPS to have visited a third-party workshop. Their work will be the subject of a talk at 37C3 which should be worth watching out for.
It will be especially interesting to juxtapose the reaction to this revelation with cases such as the Deere tractors, because of course Poland is part of the European Union. We’re not specialist EU competition lawyers, but we know enough to know that the EU takes a dim view of these types of practices
and has been strong on the right to repair
. Who knows, Polish trains may contribute further to the rights of all Europeans. | 37 | 17 | [
{
"comment_id": "6705186",
"author": "daveboltman",
"timestamp": "2023-12-06T12:11:50",
"content": "Ja, we need to kill the mental concept in these organisations that doing such nasty tricks is in any way acceptable.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_... | 1,760,372,083.97952 | ||
https://hackaday.com/2023/12/06/dry-ice-from-seashells-the-hard-but-cheap-way/ | Dry Ice From Seashells, The Hard (But Cheap) Way | Dan Maloney | [
"chemistry hacks"
] | [
"calcium cabonate",
"carbon dioxide",
"co2",
"condensation",
"cryocooler",
"cryogenics",
"dry ice",
"quicklime",
"slaked lime"
] | [Hyperspace Pirate] wants to make his own dry ice, but he wants it to be really, really cheap. So naturally, his first stop is… the beach?
That’s right, the beach, because that’s where to find
the buckets of free seashells that he turned into dry ice
. Readers may recall
previous efforts at DIY dry ice
, which used baking soda and vinegar as a feedstock. We’d have thought those were pretty cheap materials for making carbon dioxide gas, but not cheap enough for [Hyperspace Pirate], as the dry ice he succeeded in making from them came out to almost ten bucks a pound. The low yield of the process probably had more to do with the high unit cost, in truth, so cheaper feedstocks and improved yield would attack the problem from both ends.
With a supply of zero-cost calcium carbonate from the beach and a homemade ZVS-powered induction heater tube furnace at the ready, [Hyperspace Pirate] was ready to make quicklime and capture the CO
2
liberated in the process. That proved to be a little more difficult than planned since the reaction needed not just heat but a partial vacuum to drive the CO
2
off. An oil-free vacuum pump helped, yielding a little CO
2
, but eventually he knuckled under and just doused the shells in vinegar. This had the fun side effect of creating calcium acetate, which when distilled not only corrodes the copper still plumbing but also makes a lousy but still flammable grade of acetone. Once enough CO
2
was stored in a couple of beach balls, the process of cooling and condensing it into dry ice was pretty much the same as the previous method, except for taking advantage of
the Joule-Thomson cryocooler
he built a while back.
The result is a hundred or so grams of dry ice snow, which isn’t great but still shows promise. [Hyperspace Pirate] feels like the key to improving this process is more heat to really drive the calcination reaction. Might we suggest
a DIY tube furnace
for that job? | 11 | 8 | [
{
"comment_id": "6705183",
"author": "tony",
"timestamp": "2023-12-06T12:04:56",
"content": "Cool video!Ice, ice baby.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6705187",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-06T12... | 1,760,372,084.03122 | ||
https://hackaday.com/2023/12/05/directional-antenna-stands-tall/ | Directional Antenna Stands Tall | Al Williams | [
"Radio Hacks"
] | [
"antenna",
"ham radio",
"vertical antenna"
] | When you think of directional ham radio antennas, you probably think of a Yagi, cubical quad, or a log-periodic antenna. These antennas usually are in a horizontal configuration up on a high tower. However, it is possible to build beams with a vertical orientation and, for some lower frequencies, it is far more practical than mounting the elements on a boom. [DXCommander] shows us his
40 meter two-element vertical antenna
build in the video below.
A typical Yagi is just a dipole with some slightly longer or shorter elements to direct or reflect the signal. A normal vertical, however, is nothing more than half of a dipole that uses the ground as the other half. So it is possible to create reflectors and directors with a vertical-driven element.
The exact lengths and the spacing are critical and may require a bit of experimentation. [Callum] has another video (below the first one) that explains the design and math behind it. We’ve also seen arrays that require multiple elements driven out of phase to get similar effects. Of course, that requires exact lengths of cables and, in general, more cable, too.
The idea is a lot like a traditional
Yagi
. At higher frequencies, those can be
quite portable
. | 7 | 7 | [
{
"comment_id": "6705258",
"author": "Myself",
"timestamp": "2023-12-06T15:24:36",
"content": "This is why cell towers in the vicinity of MW (AM) transmitter sites will have an extra set of wires suspended alongside the tower. These are connected to a variable inductor/capacitor and used to “tune” t... | 1,760,372,084.297201 | ||
https://hackaday.com/2023/12/05/inside-a-rubidium-frequency-standard/ | Inside A Rubidium Frequency Standard | Al Williams | [
"clock hacks",
"Misc Hacks"
] | [
"atomic clock",
"Frequency Standard",
"rubidium",
"rubidium frequency standard"
] | We think of crystals as the gold standard of frequency generation. However, if you want real precision, you need something either better than a crystal or something that will correct for tiny errors — often called disciplining the oscillator. [W3AXL] picked up
a rubidium reference oscillator
on eBay at a low cost, and he shows us how it works in the video you can see below. He started with a GPS-disciplined oscillator he had built earlier and planned to convert it to discipline from the rubidium clock.
The connector looks like a D-shell connector superficially, but it has a coax connector in addition to the usual pins. The device did work on initial powerup, and using a lissajous pattern to compare the existing oscillator with the new device worked well.
We think the output might have been a little cleaner with a 50-ohm terminator on the scope. The clock uses a rubidium vapor lamp and a glass cell containing rubidium. A voltage-controlled oscillator excites the cell with a 6.8 GHz signal. Rubidium atoms can exist in three states. Because of a filter in the system, the cell will eventually reach a steady state where all the atoms are locked in one state. But the voltage-controlled oscillator can change that if the frequency is exactly right.
When the cell is in the steady state, the light passes through it with very little loss. However, if some atoms are in a different state, the cell will block some light, and a photocell can detect this. By tuning the oscillator with feedback to reach a minimum output from the photocell, you get a very precise output.
By the end of the video, the GPS oscillator never totally locked with the rubidium standard, although they were close. However, there is no way to know which of them was further off the actual 10 MHz reference.
We are looking forward to part two, where he actually converts the GPS-discipline oscillator to use the new atomic clock. We’ve
seen this done before
, of course. Cesium is even more precise, but
there are things still better than that
. | 14 | 6 | [
{
"comment_id": "6705104",
"author": "steve",
"timestamp": "2023-12-06T00:06:14",
"content": "I thought he was going to discipline the rubidium oscillator with the GPS signal? I have a couple of old cell site rubidium frequency references and that’s how they work. My understanding is that this wil... | 1,760,372,084.3484 | ||
https://hackaday.com/2023/12/05/this-pogo-pin-test-fixture-keep-your-smds-from-taking-flight/ | This Pogo Pin Test Fixture Keep Your SMDs From Taking Flight | Dan Maloney | [
"Tool Hacks"
] | [
"lcr",
"pogo pins",
"smd",
"smt",
"surface mount",
"test",
"test ficture"
] | There’s no denying how useful surface mount technology is, and how enabling the ability to make really small circuits has become. It comes at a price, though; most of us probably know what it’s like for the slightest wrong move to send a part the size of a grain of sand into another dimension.
To help make testing these parts a little easier, [IMSAI Guy] has come up with
this clever little SMD test fixture
. It’s designed to hook up to another custom board, which in turn connects to a wonderful old Hewlett-Packard 4275A LCR meter. The jig is based on two pogo pins mounted directly across from each other on a scrap of single-clad PCB. The spring-loaded contacts, which short together when not in use, are pulled apart to load an SMD part, like the 1-μH inductors shown in the video below. The pins hold the component firmly and make good electrical contact, allowing hands-free testing without the risk of an errant touch of the test probes sending it flying.
While the test fixture works well for larger SMDs, we could see this being a bit fussy for smaller parts. That would be easy enough to fix with perhaps some 3D-printed arms that retract the pogo pins symmetrically, holding them open until the part is loaded. A centering fixture might help too, as would a clear shield to contain any parts that get the urge to go for a ride. But, for the tactical application [IMSAI Guy] has in mind, this sure seems like enough.
Just getting into surface mount? If so, you might want to check out
this handy guide to the often cryptic markings used on SMD parts
. | 12 | 7 | [
{
"comment_id": "6705089",
"author": "Carl Foxmarten",
"timestamp": "2023-12-05T22:44:29",
"content": "My big fingers wouldn’t be able to handle something like this very well. Ingenious for those who can handle such a setup, though!Once you get to Tony enough SMD parts, would it be easier to have la... | 1,760,372,084.395132 | ||
https://hackaday.com/2023/12/04/better-3d-printing-overhangs-dive-dive/ | Better 3D Printing Overhangs? Dive! Dive! | Al Williams | [
"3d Printer hacks"
] | [
"3d printing",
"overhangs"
] | If you want better 3D-printed overhangs, you need better cooling, right? What would be better for cooling than printing submerged in water? It turns out [CPSdrone] tried it, and, at least for overhangs,
it seems to work pretty well
. Check it out in the video below.
Of course, there are some downsides. First, the parts of the 3D printer don’t want to work in water. The guys used deionized water to minimize water conductivity and also sealed open connections. Some components were replaced with equivalents that were less likely to corrode. However, the bearings in the stepper are still going to corrode at some point.
There’s no free lunch, though. Cooling is good for some parts of 3D printing. But for the hot parts, it could cool down too much. They encased the hot end in a large silicon block to help prevent this. They also potted the controller board, which works but makes future maintenance and upgrades painful. Initial tests looked promising.
They finally put the modified printer in a water tank and got some prints. Overhangs were good — especially extreme overhangs — but layer adhesion, as you might expect, suffers. They speculate that heating the water could help. However, the parts looked usable. There were a few trials along the way, but they solved all the problems, at least for a short time.
In the end, bridges didn’t look much better, and, as a side effect, the prints were full of water when they came off the bed. The next obvious test is to do the printing in a public swimming pool. It is doubtful that is any better, but it certainly makes a good conversation starter at the local pool.
We are a sucker for
novel 3D printers
. Of just anything that mixes
unusual items
with 3D printing. | 28 | 13 | [
{
"comment_id": "6704952",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-05T04:08:57",
"content": "So, even though “it’s born in water” a benchy still won’t float.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6704957",
"author": ... | 1,760,372,084.461986 | ||
https://hackaday.com/2023/12/04/stereoscopic-macro-lens-shows-two-is-better-than-one/ | Stereoscopic Macro Lens Shows Two Is Better Than One | Al Williams | [
"digital cameras hacks"
] | [] | You’d be forgiven if you thought [Nicholas Sherlock’s] new lens design was a macro lens that was 3D printed. In fact, it is, but it is also
a macro lens that takes 3D images
using two different cameras. If you have a pair of Sony E/FEs, you can
3D print your own copy today
. If you don’t, you might have to adjust the design or wait for future releases. In any event, you are sure to enjoy the example photos, and there’s a video review of the device you can watch below.
The design merges two 4x microscope lenses to provide a 2X stereo image with a 5mm baseline. As you might expect, the secret is a prism in the assembly that allows one camera to shoot directly at the subject and the other to shoot with a 5mm offset. This is trickier than you might think because the cameras shift the image some, also.
If you have 3D glasses, you can see the result of a video on YouTube using the lens below, too. The method allows both lenses to point at a target without angling them, which reduces distortion. The design also allows for handheld shooting, which means you can go to the tiny subjects instead of bringing them into a studio.
We’ll admit, we don’t know you’d
focus stack
3D images. If you’ll
settle for 2D images
, you can get buy with a lot less, of course. | 10 | 5 | [
{
"comment_id": "6704953",
"author": "echodelta",
"timestamp": "2023-12-05T04:10:40",
"content": "Should put both regular and cross-eye 3D’s up to see, cross-eye doesn’t take any glasses to see.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6705072",
... | 1,760,372,084.603782 | ||
https://hackaday.com/2023/12/04/powering-a-cavity-magnetron-from-a-battery/ | Powering A Cavity Magnetron, From A Battery | Jenny List | [
"Radio Hacks"
] | [
"2.4 ghz",
"high voltage",
"magnetron"
] | While vacuum electronic devices have largely been superseded over much of consumer electronics, there’s one place where they can still be found for now. The cavity magnetron is a power RF oscillator device in which electrons are induced to move in a circular path through a tuned cavity, inducing a high-power RF field, and it lies at the heart of a domestic microwave oven. They usually need a high-voltage mains transformer and a rectifier to work, but [Hyperspace Pirate]
has managed to make a solid-state power supply to power one from a 12 volt battery
. Better still, he’s put the resulting combo in a Care Bears lunchbox. Take a look at the video below the break.
The video starts with a potted history of the magnetron before looking at the circuit of a typical oven, which uses a single diode and a capacitor in a simple voltage multiplier. The capacitor value is adjusted to lower the power output, and a pretty thorough job is done of characterising the circuit.
The low-voltage supply starts with an XVS inverter to make the high voltage via another multiplier, but the interesting part comes with the magnetron’s heater. It’s designed for 50 or 60Hz household electricity, but there it’s receiving 40 kHz and has an appreciable impedance. The addition of a capacitor soon restores it to a reasonable performance.
In case you noticed that the ZVS converter might be improved upon,
take a look at a flyback converter
. Meanwhile, we should probably echo the safety message in the video that playing with magnetrons and their associated transformers can be a nasty way to die. Please take care out there! | 47 | 7 | [
{
"comment_id": "6704842",
"author": "LouLouLou",
"timestamp": "2023-12-04T20:24:27",
"content": "this is so hideously dangerous and irresponsible — If you want to blind / cook yourself / get cancer in your own lab that is one thing, but I have huge issues with making this thing portable. You might ... | 1,760,372,084.692102 | ||
https://hackaday.com/2023/12/04/retrotechtacular-the-story-of-turpentine/ | Retrotechtacular: The Story Of Turpentine | Dan Maloney | [
"Retrotechtacular",
"Slider"
] | [
"distillation",
"flux",
"resin",
"retrotechtacular",
"rosin",
"solder",
"Solvent",
"turpentine"
] | If someone in 2023 has ever had much call to use turpentine, chances are good it was something to do with paint or other wood finishes, like varnish. Natural turpentine is the traditional solvent of choice for oil paints, which have decreased in popularity with the rise of easy-to-clean polymer-based paints and coating. Oh sure, there are still those who prefer oil paint, especially for trim work — it lays up so nice — but by and large, turpentine seems like a relic from days gone by, like goose grease and castor oil.
It wasn’t always so, though. Turpentine used to be a very big deal indeed, as shown by
this circa 1940 documentary on the turpentine harvesting and processing industry
. Even then it was only a shadow of its former glory, when it was a vital part of a globe-spanning naval empire and a material of the utmost strategic importance. “Suwanee Pine” shows the methods used in the southern United States, where fast-growing pines offer up a resinous organic gloop in response to wounds in their bark. The process shown looks a lot like the harvesting process for natural latex, with slanting gashes or “catfaces” carved into the trunks of young trees, forming channels to guide the exudate down into a clay collecting cup.
Crews visit the tapped trees over a few weeks, collecting the sticky goo in wooden casks and bringing it back to a wood-fired still. There the resin is boiled, with the vapors containing mostly turpentine and water condensed and collected. The oily turpentine floats and is skimmed off the water, while the molten rosin left behind is a valuable industrial product in its own right; there’s probably
a fair amount of it on your bench
right now. The storage and grading process for the rosin is pretty fascinating; a small cube of solidified rosin is extracted from each drum using a special plug placed in a bung and compared against a standard color scale to determine the rosin’s purity. One imagines it varied a lot by season and species of source tree, and by how much the crude resin is boiled.
The last third of the film is a look at all the varied uses of turpentine back in the day. Paint thinning is there, of course, but it was also used as a natural solvent in a huge array of products, from pharmaceuticals to floor waxes. Turpentine was also considered a “naval store,” a term that came about when wooden ships ruled the waves and encompassed just about everything that could be used to build or maintain a ship — wood for masts, spars, and planks, hemp for cordage, and resin and solvents like turpentine to glue things together and keep them waterproof.
These days, the petroleum industry provides solvents that do the same job as turpentine that are easier and cheaper to obtain, and most of the natural turpentine needed is harvested not from tapping trees but by distilling the ground remains of stumps pulled up after a tree is harvested for lumber, or as a byproduct of the paper pulping process. Seeing how it was done not all that long ago is still a fascinating glimpse into our technological past. | 33 | 8 | [
{
"comment_id": "6704837",
"author": "Anonymous",
"timestamp": "2023-12-04T20:06:31",
"content": "It’s wild how what would presently require a billion-dollar industrial facility, was once accomplished by a few guys with some barrels, a horse, and a still. There’s a lesson to be learned there, I thin... | 1,760,372,085.462645 | ||
https://hackaday.com/2023/12/04/usb-c-for-hackers-program-your-own-psu/ | USB-C For Hackers: Program Your Own PSU | Arya Voronova | [
"Hackaday Columns",
"Slider"
] | [
"design",
"diy",
"power supply",
"USB-C PD",
"usbc"
] | Last time,
I showed off a few ways you can convert an existing PSU to USB-C duty, and zoomed in on a particular way you can use to convert one of the ever-abundant 18 V – 20 V laptop PSUs to USB-C. All we have left is to write software for it, and I’ll explain how it works. There’s also that one cool USB-C secret I’ve found out, but you’ll have to read on to find out more.
From the last article, we have a board that has an RP2040 and FUSB302 combo on it, which takes a 20 V DC PSU input from a laptop brick, and can switch either 5 V, 20 V or 0 V to its USB-C socket using FETs. The USB-C communication firmware is simple enough, but there’s caveats, especially regarding safety. Let’s go through those!
The Code Logic
VBUS has to be non-powered by default – we only supply 5 V when the FUSB302 detects a 5.1 kΩ pulldown on one of the CC lines. After supplying 5 V, we send out PSU capability advertisements, of the kind that we’ve learned to parse in the
Replying PD article
– and whenever we get a Request, we have to switch to the requested profile, connecting the voltage rail requested to the FET. I opt to not do any current consumption control in this design, assuming a well-behaved device, but you theoretically should do that. It wouldn’t be hard to add a high-side current sensor, say, something from Analog Devices – I just don’t want to do that now, especially given that I’m already using two of the exposed ADC pins to do Lenovo/HP PSU capability detection instead, one is used up for VBUS measurement, and the fourth is used for VIN (20 V rail) measurement – that’s four ADCs, which is as much as the RP2040 has got. However, if I ever need more ADCs, I can add an analog mux like 4051 in the next version!
I also opt to not do emarker checks for cable 5 A consumption – in case you missed
the emarker article
, an emarker is an IC inside of a USB-C cable that contains data about the cable’s capabilities, including on whether the cable can carry 5 A safely. The PSU is supposed to do these checks before it may offer a higher-current profile, and I just haven’t yet looked into how to query emarkers. I can, however, detect the presence of an emarked cable relatively easily by merely detecting presence of the Ra (1kΩ pulldown) resistor that indicates a requirement for VCONN, and from that, assume that we have 100 W support for 5 A – 60 W-only cables don’t have emarkers in them unless they’re emarked as high-speed cables specifically.
I don’t own any 60W high-speed cables like that, and, you probably shouldn’t use such cables with such a device until you can add emarker check to the firmware. If there’s no emarker present, you have to limit advertised current to 3 A – thankfully, a device like a laptop will only take as much as it’s allowed to. Oh, and your board’s USB-C socket also has to be rated for 5 A: remember, many are only rated for 3 A.
On bootup, our code should check the capabilities of the PSU connected – for Dell PSUs, you have to read a One-wire EEPROM, and for Lenovo or HP PSUs, you have to read a resistor connected from the ID pin to either GND or VIN respectively, which you can do with a voltage divider and an ADC, plus a Zener diode for protection. In my opinion, if nothing is detected, I can pretty safely assume 3 A and go with that – laptop PSUs capable of less than 3 A are relatively rare. Then, we build a PD profile that contains our PSU’s voltage and current capability, and wait for a downstream device to get attached to our USB-C port. After that, we periodically send out a USB-C profile, and wait for a Request message – when we get that message, we parse it, sanity check it, then reply with an Accept message.
That Accept message will net us a GoodCRC response from the device – ideally, we provide 20 V only after we get it, so that we can be sure that the device has indeed acknowledged us being about to provide 20 V. Then, we can switch from 5 V to 20 V, and send our PS_RDY message to signal that 20 V is available.
Alternatively, you can do what I did and supply voltage after a short delay instead of waiting on GoodCRC – this deviates from the spec, but having a delay is Good Enough™. We also deviate from the spec in that we don’t start a “shut off VBUS” timer as soon as we get a Request message – this timer is a specification requirement for PSUs to implement, and it can trip you up if you don’t account for it while writing your own PD trigger code, but here it’s not 100% required. There’s surely a few more things here and there that we’re missing to be more spec-compliant and perhaps compatible with a larger amount of devices – but it won’t actually cause any problems!
Things To Watch Out For
There are, of course, some safety requirements that we can’t skip out on. For a start, we’re using the FUSB302B PD frontend, and it applies 5.1 kΩ pulldowns to its pins when it’s not powered up – this feature is known as “dead battery”, fairly self-explanatory. We, obviously, have to disable the pullups if we want to act as a USB-C PSU, and instead enable pullups indicating a 5 V / 1.5 A profile instead, as part of USB-C analog PD signalling. Both of these are super straightforward to do in software with the FUSB302, but there’s a catch – if you plug a USB-C PSU or a dual-role port into this adapter while 20 V is not yet supplied and our code is not yet running, it’s going to bootloop. We can detect this condition in our software, thankfully, and just wait until 20 V is connected. There’s also the FUSB302T version that doesn’t have the dead battery feature enabled, so if you are to build a professional USB-C PSU board, it will have to use the 302T version. I’ve already purchased some 301T ICs, now I just need to solder them on in place of the 302B. In our code, we can distinguish between -B and -T versions of the chip by reading the version register of the FUSB302, which helps!
As soon as the 5.1 kΩ pulldowns are removed, we have to bring VBUS back to 0 V state, making sure that 20 V never stays on the connector after you unplug the device we’re powering. If 20 V is left connected to VBUS after the device pullups are no longer detected, this could result in 20 V getting on pins of a USB-C device that’s only okay with 5 V when you plug back in. This is the kind of safety-critical thing where you’ll want to use the watchdog timer – I’ll look into
the MicroPython watchdog implementation
, making sure that if my code crashes, the system will be reset into a safe state.
Oh, and of course, overcurrent protection is wonderful to have. To protect against shorting out the 5 V rail, in case the device you’re powering has a VBUS short, I recommend you use something like the SY6820 current limiting switch right before the 5 V FET pair input, setting it to a bit over 1.5 A. The previous schematic doesn’t have that, but the new one does! As for DC input overcurrent, you can try and set that, but I personally prefer to rely on the upstream PSU’s current limiting, and making sure that our device isn’t the weak point. Additionally, if we measure both VBUS and VDC, and if our resistor dividers are calibrated enough, we can measure current by measuring the difference between VBUS and VDC, using the FET as a current shunt. If there’s more than a few volts falling on the VDC-VBUS path FET, it might be worth disabling it.
Meeting Reality, Gradually
Even with these precautions, the code itself is not tricky. The FUSB302 provides interrupts for USB-C events, and we only need to react to these interrupts and any incoming PD messages in the FIFO. I’ve written a piece of code that constructs USB-C PD profiles out of a list – it’s just, the PD profile parsing function that we wrote in the “Replying PD” article, but it’s turning values into bytes instead of extracting values out of bytes. Since I already have the parsing code, I added a short check that puts the newly constructed profiles through that parsing code and
assert()
‘s that the results match! Constructing PS_RDY and Accept messages is easy – I’ve got a generic function that can send any command message already, that I made out of the Request function we wrote back then too.
I’ve developed the PSU behaviour loop code gradually and tested it all throughout the development, starting tests with simple USB-C devices. For instance, when testing the basics of attach-detach behaviour and FUSB302 interrupt handling, you could use a random USB-C breakout that has 5.1K pulldowns on it – then, nothing is at risk of burning up if you accidentally supply 20 V. I’ve started testing this code with my Pinecil as it’s
a pretty lenient USB-C device
, in that
its open-source PD sink stack
works with a wide variety of PD supplies despite the quirks – which is wonderful for a device likely to have quirks and sharp edges! It also is a very safe device to test things on – it won’t care if you just put 20 V on VBUS, whereas quite a few laptops will object to that, and some might even have a fiery response.
With the Pinecil, I could test all the basics – attach-detach behaviour, PD profile sending, and its PD tester features have shown me that it correctly recognizes all the profiles that my code creates! The final frontier was making this PSU work with my Framework laptop, as that was what I was actually developing this PSU for. Of course, it didn’t work on the first try – Framework uses PD controllers that have a proper USB-C stack with all the USB-C spec’s constraints enforced, so, some extra debugging was needed. The PD trigger code from
the “Replying PD” article
in particular has helped me iron out differences from the spec – I could plug my USB-C sink code board into the same board with PD sink code, see the UART output from both RP2040s, and compare my board’s PD communications to those of USB-C chargers I’ve had laying around.
There were two things I’ve found that seem to have been making the Framework’s PD controller sad. The first was that I was apparently sending the PD advertisement way too early after attach, which I figured out after noticing that it takes my Pinecil about five seconds to negotiate with my PSU, yet only about one second to negotiate with a charger I had laying around. Seeing that, I realized that my first advertisement was being sent way too early for the Pinecil to boot up and receive it, and tweaking made for negotiation that seemed instant. Having fixed that, the laptop would receive the profiles correctly and request the 20 V one, but it would detach after getting 20 V onto VBUS. The culprit there was me not waiting enough time between sending Accept and putting 20 V onto the bus – increasing the delay fixed that. It would’ve helped if I waited for that GoodCRC response instead, but, it felt okay to cut this corner at the time!
Reaping The Fruits Of Research
It would’ve helped if I were to read the specs and implement all the PSU’s constraints properly, going through the state machines and abiding by time constraints and all. Nevertheless, this PSU works wonders, and I’ve hardly had to check the spec as I developed this – which did wonders for my self-esteem! Even increasing the current to 5 A has worked out without a hitch, I’ve only had to make sure that I’d plug a 100 W-capable cable in, as the profiles are for now hardcoded. Yeah, there’s TODOs – my current code doesn’t yet have the emarker check, or laptop PSU capability check, so I’m advertising hardcoded PD profiles instead of calculating them on boot as I ought to. I’m working on these things slowly, and for now, it’s good enough for long-term testing with my laptop given a certain laptop PSU and cable combination. The first 100 W USB-C PSU I own, is the 10 0W PSU that I’ve built myself, and it feels nice.
All of the code is in MicroPython as usual
– it’s my choice for high-level tinkering-friendly implementations. You could simplify the code, port to C and put it onto a smaller device like an ATTiny or the CH32V003, since you only need a few GPIOs, ADC and I2C. That’s all you need to build a cheap retrofit adapter to make a USB-C PSU out of any DC PSU with a voltage that vaguely fits a USB-C profile – or not even that! Remember the secret I mentioned? I was offering 5 V and 20 V profiles in my code, but I was sending the 20 V profile with a 19 V PSU connected, since that’s what I had on hand. That worked on my Framework, and that made me wonder – just how non-standard of a voltage could I actually offer? I tried offering a 19 V profile, and to my surprise, the laptop accepted and started charging – at 95 W, no less. This is a big victory, dramatically increasing just how many different DC PSUs I can actually use this board with.
Making a custom profile with a voltage significantly above 20 V is likely not a good idea (not that I won’t try a 21 V LiIon pack sometime soon), but going below should be just fine! Of course, there’s caveats – for instance, some Framework motherboards still have
the hardware bug with 15V handling
, that needs a FET swap to have sub-18 V voltages work well. However, after the FET swap, this PSU lets you use any 10 V – 20 V DC source above 15 W to charge a Framework – you only need to communicate the voltage and the current consumption limit; with other laptops, your mileage may vary, because this might depend on the PD controller firmware. The gist is – if you want to charge your Framework from four or five 18650 cells in series, you can just connect them to VIN of this board, measure their total voltage on an ongoing basis, and periodically re-advertise available current and voltage on the fly as your pack voltage drops.
As it goes, I’m planning to package this circuitry into a few different formats, making sure that common types of DC PSUs are not cast aside! Also, given that
the new Pi 5
expects a PD handshake in order to actually accept 5 A at 5 V, this article’s work might just help you power your Pi from a random hefty non-PD 5 V PSU without having it throttle. Though, they might’ve kept the 5 V GPIO header backpowering loophole, so I suppose we’ll have more details about the Pi 5 PD requirements once someone actually looks into it.
This is not even all – a few of my friends have been tinkering with USB-C PSU designs in the meantime, turning my schematic into wonderful boards! For instance, here’s a board from [Wificable] that is a Framework laptop expansion card, which lets you use Dell and HP PSUs as USB-C chargers. In the future, we could add support for things like MagSafe into it!
This design has been fun, it gave me a way to reuse a whole bunch of PSUs, helped me find an unintended Framework PD controller feature, and will likely help me build a seriously straightforward and efficient USB-C powerbank for direct LiIon reuse. In addition to that, it looks like this card will lead to a good few designs on its own! I hope you’ve enjoyed this journey as much as I’ve enjoyed documenting it, and whenever you need to navigate the world of USB-C tech, hopefully these articles can help you. | 20 | 7 | [
{
"comment_id": "6704823",
"author": "Moriel",
"timestamp": "2023-12-04T19:30:00",
"content": "This is awesome!However a correction is in order. 45W power supplies from the large OEMs are extremely ubiquitous (~2.31A with Dell and HP, 2.25A with Lenovo, ~2.37A from Asus, Dynabook/Toshiba and Acer).A... | 1,760,372,085.128783 | ||
https://hackaday.com/2023/12/04/the-hoarders-dilemma-hack-chat/ | The Hoarder’s Dilemma Hack Chat | Dan Maloney | [
"Hackaday Columns",
"Slider"
] | [
"Hack Chat"
] | Join us on Wednesday, December 6 at noon Pacific for the
The Hoarder’s Dilemma Hack Chat
with Gabe Emerson!
There’s a lot to be said for the power of a well-stocked junk bin. It’s almost a magical thing, being able to dive into a random box and retrieve just the right part to perform a needful repair or to complete a project without the need to hit the web or hop in the car for a trip to the hardware store. For those who pride themselves on their resourcefulness, it can be a heady experience indeed.
But as with everything, such feats of fix-it come at a price. That little squirt of dopamine that comes from having just the right thing can make your monkey brain fixate on a simple equation: “More stuff is better stuff.” The higher and deeper your stash, the better your chances of having what you need, assuming you can find it, of course. This way lies madness, and perhaps an appearance on a reality TV show.
Is there a better way? It’s hard to say, but we figured it would be a good idea to loop in someone with a lot of experience collecting junk that somehow finds its way into some pretty cool projects. Gabe Emerson runs the popular and aptly named “saveitforparts” channel over on YouTube, and fancies himself an accomplished hoarder. We’d have to agree, given
his recent 1,000-mile drive
to pick up a used geodesic dome, or his ever-increasing collection of RV satellite dishes, which he somehow
puts to good use
. His junk collection is pretty epic; he even has a whole piece of property devoted to the larger pieces of his collection, like an entire monorail train. He seems uniquely qualified to discuss the “Hoarder’s Dilemma” and the painful process of deciding what stays and what goes.
Our Hack Chats are live community events in the
Hackaday.io Hack Chat group messaging
. This week we’ll be sitting down on Wednesday, December 6 at 12:00 PM Pacific time. If time zones have you tied up, we have a
handy time zone converter
. | 31 | 14 | [
{
"comment_id": "6704817",
"author": "smellsofbikes",
"timestamp": "2023-12-04T19:23:52",
"content": "I talk about this a lot with coworkers, who are all hoarder electrical engineers, and one of the things that comes up is the necessity for sorting and discarding, especially when we acquire new stuf... | 1,760,372,085.348778 | ||
https://hackaday.com/2023/12/04/another-omnibot-2000-upgrade/ | Another OmniBot 2000 Upgrade | Al Williams | [
"Raspberry Pi",
"Robots Hacks",
"Toy Hacks"
] | [
"Omnibot-2000",
"Tomy"
] | There were many toy robots back in the 80s that were — frankly — underwhelming by today’s standards. Back then, any old thing that rolled around with some blinking lights would impress, but the bar is higher today. Then again, some of the basic components won’t really change. You still need wheels, motors, batteries, and all that. But the computers we can bring to bear today are much better. Maybe that’s why so many people, including [mcvella], decide to give these venerable toys like the OmniBot 2000 a facelift or, maybe a better analogy, a
brain transplant
.
In this particular case, the brain in question is a Raspberry Pi. The robot will also sport new sensors, motor controllers, and a webcam. There is also a new battery pack in play. The project doesn’t cover working with the single powered gripper arm. The left arm isn’t motorized. There is also a cassette tape deck you could probably make do something interesting. Of course, with a Raspberry Pi, you get wireless control, and the project uses Viam to define and control the robot’s motion.
There is some retro cool factor to using a robot like Ominbot. However, we might be more tempted to just build our own. With a 3D printer, a laser cutter, and a few motors, you could make something that would be about equivalent or better with little effort.
We have seen
OmniBot conversions
before, particularly over on Hackaday.io. Maybe someone will convert one over to
steam power
. | 0 | 0 | [] | 1,760,372,084.91545 | ||
https://hackaday.com/2023/12/04/italy-proposes-minimalist-lunar-outpost-for-artemis/ | Italy Proposes Minimalist Lunar Outpost For Artemis | Tom Nardi | [
"Featured",
"Interest",
"Original Art",
"Slider",
"Space"
] | [
"Artemis",
"artemis program",
"moon",
"nasa"
] | When humanity first step foot on the Moon, they couldn’t stay around for very long. The Apollo program was limited by the technology of the era — given the incredible cost per kilogram to put a payload down on the lunar surface, it wasn’t feasible to bring down enough consumables for a lengthy stay. Even if they could have carried sufficient food and water to last more than a few days, the limiting factor would have become how long the crew could realistically remain cooped up in the tiny Lunar Excursion Module (LEM).
In comparison, the Artemis program is far more ambitious. NASA wants to establish a long-term, and perhaps even permanent, human presence on our nearest celestial neighbor. This will be made possible, at least in part, to the greatly reduced launch costs offered by current and near-future launch vehicles compared to legacy platforms like the Saturn V or Space Shuttle. But cheaper rides to space is only part of the equation. NASA will also be leaning heavily on the lessons learned during the International Space Program; namely, the advantages of modular design and international cooperation.
While NASA and their commercial partners will still end up providing the bulk of the hardware for the Artemis program, many modules and components are being provided by other countries. From the Orion’s European Service Module (ESM) to the Japanese life support systems to be installed on the Lunar Gateway Station, America won’t be going to the Moon alone this time.
The latest international contribution to the Artemis program comes from the Italian Space Agency (ASI), who have announced their intention to
develop a lunar habitation module they’re calling the Multi-Purpose Habitat (MPH)
in collaboration with Thales Alenia Space.
Home Away from Home
To date most of the attention has been put on the parts of the Artemis project that will actually get astronauts to the Moon, and eventually, down to the surface. The uncrewed Artemis I, which launched just over a year ago, served as a shakedown for both the Space Launch System (SLS) rocket and Orion spacecraft. Artemis II, currently slated for November 2024, will be a similar mission, but this time with humans aboard. Astronauts won’t actually descend to the lunar surface until Artemis III, which current estimates place somewhere between 2025 and 2027.
Once all the elements of Artemis have been demonstrated, the idea is then to start making regular flights to the Moon. Yearly at first, and then with higher cadence as more of the infrastructure comes online. It’s around this point in the plan that the Multi-Purpose Habitat comes into play.
While in general the lunar landers proposed for the Artemis program are quite a bit larger than the Apollo LEM, there will still be a need for dedicated living and working space on the surface. With its own on-board power generation, life support, and communications system, such a facility could even serve as a shelter for astronauts awaiting rescue should something go wrong with their return vehicle.
There’s an argument to be made that such a capability could be provided by simply sending a spare lander to the Moon under remote control. But since the MPH doesn’t need to lift back off the lunar surface, it can afford to be larger and heavier — which means more usable space for working and living at a greatly reduced cost.
Space Station Tech?
Unfortunately, neither the Italian Space Agency nor Thales Alenia Space have released any technical information about the MPH. All we have is an artist’s render, which at least gives us a sense of scale thanks to the flag and stairway shown in the foreground. The module is also depicted with legs that appear to be designed to absorb some level of impact on touchdown, which is the only clue we have as to how the habitat will actually be lowered down to the lunar surface.
While admittedly nothing more than speculation at this point, it does stand to reason that ASI and Thales would look to existing space-proven designs as a basis for the for the MPH instead of starting from a clean slate. If that’s the case, then the resemblance the MPH bares with the
Leonardo
Permanent Multipurpose Module (PMM) of the International Space Station
module might be more than just coincidence.
Leonardo
inside the cargo bay of Space Shuttle
Discovery
.
Before being permanently attached to the ISS in 2011,
Leonardo
was one of three Multi-Purpose Logistics Modules (MPLMs) built by ASI. These pressurized containers were carried inside the Space Shuttle’s cargo bay, and berthed to the Station to be unloaded. They would then be returned to the Shuttle, and brought back down for reuse.
Leonardo
and its twin
Raffaello
flew to the Station a combined twelve times, while
Donatello
never left Earth.
With the retirement of the Space Shuttle, it was decided to modify
Leonardo
so it could remain permanently berthed to the ISS. Interestingly,
Donatello
ended up being converted by
Lockheed Martin into the Habitat Ground Test Article (HGTA)
in 2019. The HGTA was used to study different internal layouts for a potential
habitat module that would be used on the Lunar Gateway Station
.
View inside of the Habitat Ground Test Article, built from
Donatello
.
Between the experience gained by operating
Leonardo
and
Raffaello
in space, and the studies currently being done on how their design could be adapted into living and working space, it would seem a lot of the groundwork for the MPH is already in place. It’s hard to believe that ASI and Thales wouldn’t take advantage of it.
The Moon is Calling
While we’ll have to wait a bit longer before we get any concrete details on Italy’s Multi-Purpose Habitat, the simple fact that it’s actively being worked on is reason enough to be excited. It’s another sign that the international community is taking the Artemis program seriously, and that we may finally be on the path towards a sustainable lunar colony.
Living and working on the Moon won’t be easy
, but it’s still far more practical in the near term than any other destination in the solar system. Before we can even make an attempt at a crewed mission to Mars,
spending some time on the lunar surface
will provide valuable data on what it will take to survive in a hostile environment far from the comfort of Mother Earth. | 26 | 7 | [
{
"comment_id": "6704749",
"author": "CRJEEA",
"timestamp": "2023-12-04T15:10:18",
"content": "It does make me wonder, why crash the iss into point nemo when they could grab it and throw it at the moon.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6704753"... | 1,760,372,085.266661 | ||
https://hackaday.com/2023/12/04/this-laser-cut-one-piece-wedge-tenon-locks-wood-joints-tight/ | This Laser-Cut One-Piece Wedge Tenon Locks Wood Joints Tight | Dan Maloney | [
"Laser Hacks",
"Parts"
] | [
"joinery",
"joint",
"laser cutter",
"mortise",
"tenon",
"Wedge",
"woodworking"
] | Woodworkers have always been very clever about making strong and attractive joints — think of the strength of a mortise and tenon, or the artistry of a well-made dovetail. These joints have been around for ages and can be executed with nothing more than chisels and a hand saw, plus a lot of practice, of course. But new tools bring new challenges and new opportunities in joinery, like
this interesting “hammer joint” that can be made with a laser cutter
.
This interesting joint comes to us from [Jiskar Schmitz], who designed it for quick, solid, joints without the need for glue or fasteners. It’s a variation on a wedged mortise and tenon joint, which strengthens the standard version of the joint by using a wedge to expand the tenon outward to make firm contact with the walls of the tenon.
The hammer joint takes advantage of the thin kerf of a laser cutter and its ability to make blind cuts to produce a tenon with a built-in wedge. The wedge is attached to a slot in the tenon by a couple of thin connectors and stands proud of the top of the tenon. The tenon is inserted into a through-hole mortise, and a firm hammer blow on the wedge breaks it free and drives it into the slot. This expands the tenon and locks it tightly into the mortise, creating a fairly bulletproof joint. The video below tells the tale.
While the hammer joint seems mainly aimed at birch plywood, [Jiskar] mentions testing it in other materials, such as bamboo, MDF, and even acrylic, although wood seems to be the best application. [Jiskar] also mentions a potential improvement: the addition of a ratchet and pawl shape between the wedge and the slot in the tenon, which might serve to lock the wedge down and prevent it from backing out. | 24 | 8 | [
{
"comment_id": "6704700",
"author": "RunnerPack",
"timestamp": "2023-12-04T12:37:29",
"content": "Last word of 2nd paragraph should be “mortise”.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6704704",
"author": "mip",
"timestamp": "2023-12-04T12:49:... | 1,760,372,085.193631 | ||
https://hackaday.com/2023/12/04/mini-meters-monitor-microprocessor-maximization/ | Mini Meters Monitor Microprocessor Maximization | Adam Fabio | [
"Arduino Hacks",
"computer hacks"
] | [
"arduino",
"CPU monitor",
"gauge",
"meter",
"rgb"
] | [Lex] over at
Computing: The Details
loves to make fun projects. Recently, they have created a
hardware CPU monitor
that displays how PCs are parallelizing compile tasks at a glance. The monitor is built from 14 analog meters, along with some WS2812 RGB LEDs.
Each meter represents a core on [Lex]’s CPU, while the final two meters show memory and swap usage. The meters themselves are low-cost 5 mA devices. Of course, the original milliamps legends wouldn’t do much good, so [Lex] designed and printed graduations that glue over the top. The RGB LED strip is positioned so two LEDs fit under each meter. The LEDs allow a splash of color to draw attention to the current state of the machine. The whole bank going red would sure get our attention!
The system is controlled by an Arduino Mega, with the meters driven using the PWM pins. The only extra part is a 1 kΩ resistor. The Arduino wrangles the LEDs as well. Sadly [Lex] did not include the software. They did describe it though. Basically they are using a Rust program to call systemstat, obtaining the current CPU utilization data in Linux. A bit of math converts this into pointer values and LED colors. The data is then sent via USB-serial to the Arduino Mega. The software savvy will say it’s pretty easy to replicate, but the hardware-only hackers among us might need a bit of help.
This isn’t the first custom meter we’ve seen on Hackaday. Your author’s first project covered by Hackaday was for a meter
created using an automotive gauge stepper motor
. I didn’t include source code either – but only because [Guy Carpenter]’s
Switec X25 library
had me covered.
Thanks for the tip, [TubeTime]! | 11 | 6 | [
{
"comment_id": "6704688",
"author": "paulvdh",
"timestamp": "2023-12-04T11:56:57",
"content": "A bit silly but also fun sort of project. But there are a few things a bit confusing.Why start with 5mA meters? Is this the native current of these? (100uA used to be very common), or else 5V meters that... | 1,760,372,084.964184 | ||
https://hackaday.com/2023/12/03/a-handheld-hackintosh-but-so-much-more/ | A Handheld Hackintosh, But So Much More | Jenny List | [
"computer hacks",
"handhelds hacks"
] | [
"hackintosh",
"handheld",
"Lattepanda"
] | As handheld computing has solidified alongside everything else into the mobile phone, it’s sad that the once promising idea of a general purpose machine in the palm of the hand has taken a turn into the dumbed-down walled-garden offered by smartphone vendors. There was a time when it seemed that a
real
computer might be a common miniaturized accessory, but while it’s not really come to pass, at least [iketsj] has taken a stab at it.
His handheld Hackintosh runs MacOS on a miniature scale
, and looks rather nice.
At its heart is the LattePanda Alpha x86 single board computer, with a small custom expansion board for a couple of buttons, a USB hub, a small keyboard, and a display. These parts are all mounted to a baseboard with metal stand-offs, and the power is sourced from a single USB-C socket at the bottom edge. What makes it more extraordinary is that it’s not the first handheld Hackintosh from this maker,
the previous one being significantly bigger
.
On one hand then, this is home-built PC like any other, assembled from off-the-shelf-parts. But on the other it’s far from normal, for despite its simplicity it forms a very usable small form factor device. The Akruvia Una keyboard uses tactile switches so maybe it’s not the machine to type your thesis on, but other than that it makes a great little machine for MacOS, Linux, or Windows. We like it, and we think you will too when you see the video below the break. | 2 | 1 | [
{
"comment_id": "6704706",
"author": "Adrien",
"timestamp": "2023-12-04T12:58:42",
"content": "The design is not as sleek as Apple products, but for a hackintosh it’s perfect! Also the keyboard alone seems interesting and is sold on Etsy. It uses an rp2040 board, the doc is here (but I couldn’t find... | 1,760,372,085.390758 | ||
https://hackaday.com/2023/12/03/pico-wspr-tx-does-it-in-software/ | Pico-WSPR-tx Does It In Software | Elliot Williams | [
"Radio Hacks"
] | [
"amateur radio",
"digital mode",
"ham radio",
"radio",
"wspr"
] | What do you need to make a radio transmitter? There are builds that work with just a couple of transistors. But how about a GPS-disciplined small signal beacon? You can actually get the job done for less than the cost of a fancy hamburger, thanks to [RPiks]’s
pico-WSPR-tx
and the Weak Signal Propagation Reporter Network (WSPR).
WSPR is a digital protocol where a beacon encodes its callsign, location, and transmitting power, and then sends it out to a network of receiving stations worldwide. The idea is to use the data coming from the beacons to determine whether radio propagation conditions are good or not; if you hear a quiet signal from afar, they’re good in that direction. [RPiks]’s beacon design simply includes a Raspberry Pi Pico and a GPS receiver. Everything else is software.
Of course, this means that it’s using the Pico’s GPIO pins for transmission. Maybe you want to add some filtering to take off the rough square-wave edges, and/or maybe you want to boost the power a little bit with an external amplifier. If so, check out
our own $50 Ham column
’s advice on the topic. But you don’t need to. Just a Pico and a GPS should get you working,
if you want to test the WSPR waters
. | 38 | 9 | [
{
"comment_id": "6704633",
"author": "wb4ilp",
"timestamp": "2023-12-04T03:27:23",
"content": "WSPR is definitely one of the coolest aspects of amateur radio especially for those of us more intrigued with the technology of radio communications than with the on air interaction with other amateurs. T... | 1,760,372,085.541169 | ||
https://hackaday.com/2023/12/03/hackaday-links-december-3-2023/ | Hackaday Links: December 3, 2023 | Dan Maloney | [
"Hackaday Columns",
"Hackaday links",
"Slider"
] | [
"china",
"cybertruck",
"engine",
"F150",
"ford",
"hackaday links",
"ice",
"laser",
"patent",
"pickup",
"psychology",
"tesla",
"well-being"
] | Sure, it does less than originally promised, but hey — at least it’s more expensive. That about sums up Tesla fans’ feelings after
the long-awaited Cybertruck reveal
at the Texas Gigafactory on Thursday, where Elon Musk himself handed over the keys — or their Cyber equivalent — to a few new owners. These are expensive machines — $61,000 for the two-motor model, and just shy of $100,000 for the three-motor all-wheel-drive model with all the bells and whistles. That’s considerably more than they were expected to cost back in 2019, a fact which may be at least partially behind
the drop in Tesla shares
after the launch.
Curiously, Elon seemed to fixate on the survivability and toughness of the truck, perhaps in an attempt to rehabilitate the image of the truck after his “demo-hell” sneak peek a few years back, where the prototype’s “bulletproof” windows lost a fight with a metal ball. The demo this time was a considerably less energetic affair, with a baseball softly lobbed at the window. Elon also spent a lot of time going on about the bulletproofing of the truck’s “exoskeleton,” complete with video of various weapons trying to breach it. He also referred to the suitability of the Cybertruck for a post-apocalyptic world, which we very much doubt since we’re pretty sure these things won’t even start unless they can connect to the interwebz. Regardless, we find his apocalyptic fixations a little disturbing; when the richest man in the world is thinking this way, it might be a good idea to wonder what he knows.
Switching to internal combustion engines, we spied a “just rolled into the shop” story about
a Ford F150 engine with catastrophic damage
that seemed worth sharing as a cautionary tale if nothing else. The V6 Ecoboost engine was on a truck bought at auction — always a crapshoot — that the new owner claimed “had a little ticking sound.” He tried a few things, the sound got steadily worse, and then — well, when you can see daylight from one side of the engine block to the other, it’s not a good thing. There was damage from the top of the engine right down into the oil pan, where the remains of the failed piston and connecting rod came to rest. Amazingly, the owner said the engine still ran after the piston let loose; Built Ford Tough indeed! We know, we know — EVs will make all these issues go away. And while we agree that that’s a good thing overall, at the same time we’ll miss seeing teardowns like these.
In other Ford news, it looks like
the pickup truck of the future will have a 3D printer and robotic arm built into its bed
, for — reasons? The automaker has
a patent pending
with the German patent and trademark office whose title translates to “
Passenger Car Configured To Perform Additive Manufacturing Operations,” and from the drawings appears to be an arm that’s attached to a rail across the width of the truck bed with some sort of fanciful print head attached. Exactly what this machine would print is an open question, but you could imagine uses on construction sites and the like. Or, perhaps they’ll equip it with a metal-printing head and allow users to print new engine blocks as they need them.
Good news everyone: contrary to what you might think,
the Internet does not pose a risk to mental health
. This comes from
a study
out of the University of Oxford, which examined mental health data from 2.4 million people between the ages of 15 and 89 over the period between 2005 and 2022. They found that Internet use had “little to no” impact on “global well-being.” The researchers came to this conclusion by comparing Internet use with results from the Gallup World Poll, which asks survey respondents to rate things like, “Did you smile or laugh a lot lately?” and “Did you feel well-rested?” They found no statistically significant change in well-being over the test period, but honestly, that standard seems like a moving target — the world is an objectively different place than it was in 2005, after all. And really, just a few minutes on Reddit or the comments section on YouTube should be enough to convince you that these results should be taken with a huge grain of salt.
And finally, we’re not sure what to make of
this anti-sleep laser system
drivers in China are being subjected to. It appears to be a series of laser projectors set up from one highway sign stanchion to another, in addition to blinkenlights adorning their uprights. The display is eye-catching, to say the least, but in these days of flashing light warnings on YouTube videos, this seems a little overboard. | 28 | 9 | [
{
"comment_id": "6704599",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-04T00:01:50",
"content": "Nice to have HaD Links back!",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6704600",
"author": "The Commenter Formerly Known ... | 1,760,372,085.608559 | ||
https://hackaday.com/2023/12/03/the-best-kind-of-handheld-gaming-is-homemade/ | The Best Kind Of Handheld Gaming Is Homemade | Matthew Carlson | [
"handhelds hacks"
] | [
"cyberdeck",
"diy handheld",
"handheld",
"Intel NUC",
"steamdeck"
] | [CNCDan] previously dabbled with Raspberry Pi CM4-powered gaming handhelds but was itching for something more powerful. Starting in May 2023, he embarked on
building an Intel NUC7i5BNK-powered handheld dubbed NucDeck
.
As he goes over the feature list, it sounds like a commercially available console. A 1024 x 600 screen provides a good balance of fidelity and performance. Stereo-chambered speakers provide good front-facing sound. Two thumbsticks with gyro aim assist, two hall effect triggers, and many buttons round out the input. Depending on the mode, the Raspberry Pi Pico provides input as it can emulate a mouse and keyboard or a more traditional gamepad. A small OLED screen shows battery status, input mode, and other options. This all fits on four custom PCBs, communicating over I2C. 6000 mAh of battery allows for a decent three hours of run time for simpler emulators and closer to an hour for more modern games.
The whole design is geared around easily obtainable parts, and the files are
open-source and on GitHub
with PDFs and detailed build instructions. We see plenty of gorgeous builds here on Hackaday, but everything from the gorgeous translucent case to the build instructions screams how much time and love has been put into this. Of course, we’ve seen some exciting hacks with the steam deck (such as this
one emulating a printer
), so we can only imagine what sort of things you can do once you add any new hardware features you’d like. | 8 | 6 | [
{
"comment_id": "6704630",
"author": "Db0",
"timestamp": "2023-12-04T03:00:02",
"content": "Impressive, for a self-built solution",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6704759",
"author": "Seth G",
"timestamp": "2023-12-04T15:44:12",
"cont... | 1,760,372,085.656799 | ||
https://hackaday.com/2023/12/03/tiny-pov-turns-right-round-for-volumetric-fun/ | Tiny POV Turns Right Round For Volumetric Fun | Dan Maloney | [
"LED Hacks"
] | [
"persistence of vision",
"POV",
"rp2040",
"volumetric"
] | Just when you think the POV thing has run out of gas, along comes [mitxela] to liven things up. In this, he’s taken the whole persistence of vision display concept and literally spun up something very cool:
a tiny volumetric “electric candle” display
.
As he relates the story, the idea came upon him on a night out at the pub, which somehow led to the idea of an electric candle. Something on the scale of a tea light would fit [mitxela]’s fascination with
very small and very interesting circuits
, so it was off to the races. Everything needed — motor, LIR2450 coin cell, RP2040, and the vertical matrix of LEDs — fits into the footprint of the motor, which was salvaged from a CD drive. To avoid the necessity of finding or building a tiny slip-ring, he instead fixed everything to the back of the motor and attached its shaft to a Delrin baseplate.
The 8×10 array of surface-mount LEDs stands atop the RP2040 with the help of some enameled magnet wire, itself a minor bit of circuit sculpture. There’s also a 3D-printed holder for a phototransistor and IR LED, which form a sensor to trigger the display; you can see [mitxela] using a finger to turn the display off and move it back and forth. It goes without saying that these things always look better in person than they do in stills or even on video, but we still think it looks fantastic. There’s also a deep dive into generating volumetric data in the write-up, as well as an unexpected foray into the fluid dynamics calculations needed to create a realistic flame effect for the candle.
All in all, this is a fantastic if somewhat fragile project. We love the idea of putting this in a glass enclosure to make it look a little like a Nixie tube, too.
Thanks to [Cutout], [Aaron], and [htky] for the near-simultaneous tips on this one. | 13 | 9 | [
{
"comment_id": "6704535",
"author": "Curious George’s uglier cousin",
"timestamp": "2023-12-03T18:52:00",
"content": "That is so cool.mega kudosNow do a spinning video screen where AI takes a 2d FaceTime call and changes it to 3d and presto – talk to your friend’s hologram.",
"parent_id": null,... | 1,760,372,085.840153 | ||
https://hackaday.com/2023/12/03/wolfenstein-3d-clone-makes-arduboy-debut/ | Wolfenstein 3DClone Makes Arduboy Debut | Tom Nardi | [
"Games",
"handhelds hacks"
] | [
"Arduboy",
"wolfenstein"
] | The 8-bit Arduboy isn’t exactly a powerhouse by modern gaming standards, or even really by old school standards for that matter. But for the talented developers that produce software for the system, that’s just part of the challenge. To date the monochromatic handheld has seen miniaturized takes on many well-known games, with several taxing the hardware beyond what most would have assumed possible.
But the latest entry into this catalog of improbable software,
WolfenduinoFX
, is easily the most technically impressive. As the name implies, this is a “demake” of 1992’s iconic
Wolfenstein 3D
. It features 10 levels based on the original game’s shareware release, with the enemies, weapons, and even secret rooms lovingly recreated for the Arduboy’s 128 x 64 OLED display.
Arduboy FX Mod-Chip
Now, those of you who have experience working with the ATMega32u4 microcontroller at the heart of the Arduboy might think this is impossible…and you’d be right. The only way developer [James Howard] was able to pull this feat off was by leveraging the extended flash memory offered by the Arduboy FX.
This upgrade, which was developed in conjunction with the community, allows the handheld to hold hundreds of games by loading them from an SPI flash chip. For
WolfenduinoFX
, that flash chip is used to hold graphical assets for the game that would otherwise be too large to fit on the MCU alone.
When we looked at the Arduboy FX back in 2021
, it was clearly a must-have upgrade, so it’s no wonder that the newest version of the handheld has the capability built-in. Now that games are actually requiring the expanded flash to function, it seems we’ve officially entered into a new era for the quirky little handheld that
[Kevin Bates] first sent our way nearly a decade ago
. Long live the Arduboy! | 12 | 3 | [
{
"comment_id": "6704492",
"author": "Gravis",
"timestamp": "2023-12-03T15:15:04",
"content": "It seems wasteful to include an entire MCU on the “mod-chip” and only utilize it to flash to bootloader of the old chip. They could have made it so that it can be used expressly for graphics or something ... | 1,760,372,085.895 | ||
https://hackaday.com/2023/12/03/build-a-strandbeest-replica-of-your-very-own/ | Build A Strandbeest Replica Of Your Very Own | Lewin Day | [
"Misc Hacks"
] | [
"craft",
"popsticks",
"strandbeest",
"theo jansen"
] | [Theo Jansen] is famous for his giant walking Strandbeest creations. They’re elegant, impressive, and powered by nature, and their walking mechanism is a thing of beauty. If you’ve ever wanted to build your own,
[Antonio Garcia] has just the guide to get you started on the smaller scale.
Unlike so many other builds today, this one features some good old fashioned craft techniques. The build uses popsicle sticks for the legs, what appear to be toothpicks for the joints, and a cardboard box for the main body. A small brushed DC motor is used for propulsion to keep things easy, which runs off a few AA batteries. It’s a gearmotor, which gives it plenty of torque to propel the walking mechanism without undue strain.
It may not be powered by nature, and it may not be taller than most humans, but it’s still got an appealing gait and it still inspires us with its design. If you want to learn more, go ahead and take a gander
at [Theo Jansen’s] own designs and see what you can pick up
. Video after the break. | 1 | 1 | [
{
"comment_id": "6704580",
"author": "The Commenter Formerly Known As Ren",
"timestamp": "2023-12-03T22:23:59",
"content": "Strandbeest, is that what has become of Barbara?B^)",
"parent_id": null,
"depth": 1,
"replies": []
}
] | 1,760,372,085.782479 | ||
https://hackaday.com/2023/12/03/simple-chemistry-to-metallize-and-etch-silicon-chips/ | Simple Chemistry To Metallize And Etch Silicon Chips | Dan Maloney | [
"chemistry hacks"
] | [
"acetic acid",
"etching",
"glucose",
"peroxide",
"photoresists",
"piranha",
"ptfe",
"silicon",
"silver",
"teflon",
"Tollen's reagent",
"vinegar"
] | We’ve been eagerly following [ProjectsInFlight]’s stepwise journey toward DIY semiconductors, including all the ups and downs, false leads, and tedious optimizations needed to make it possible for the average hacker to make chips with readily available tools and materials.
Next up is
metallization
, and spoiler alert: it wasn’t easy. In a real fab, metal layers are added to chips using some form of deposition or sputtering method, each of which needs some expensive vacuum equipment. [ProjectsInFlight] wanted a more approachable way to lay down thin films of metal, so he turned to an old friend: the silver mirror reaction. You may have seen this demonstrated in high school chemistry; a preparation of
Tollen’s reagent
, a mix of sodium hydroxide, ammonia, and silver nitrate, is mixed with glucose in a glass vessel. The glucose reduces the reagent, leaving the metallic silver to precipitate on the inside of the glass, which creates a beautiful silvered effect.
Despite some issues, the silvering method worked well enough on chips to proceed on, albeit carefully, since the layer is easily scratched off. [ProjectsInFlight]’s next step was to find an etchant for silver, a tall order for a noble metal. He explored piranha solutions, which are acids spiked with peroxide, and eventually settled on plain old white vinegar with a dash of 12% peroxide. Despite that success, the silver layer was having trouble sticking to the chip, much preferring to stay with the photoresist when the protective film was removed.
The solution was to replace the photoresist’s protective film with Teflon thread-sealing tape. That allowed the whole process from plating to etching to work, resulting in conductive traces with pretty fine resolution. Sure they’re a bit delicate, but that’s something to address another day. He’s come a long way from
his DIY tube furnace
used to put down
oxide layers
, and suffering through the search for
oxide etchants
and exploring
photolithography methods
. It’s been a fun ride so far, and we’re eager to see what’s next.
Thanks to [Måns Almered] for the tip. | 5 | 3 | [
{
"comment_id": "6704496",
"author": "Gravis",
"timestamp": "2023-12-03T15:28:10",
"content": "Impressive but I certainly hope he improves the process. However, I think I would have gone with making a a sputtering machine because it can easily be reused for many different things and doesn’t require ... | 1,760,372,085.943247 | ||
https://hackaday.com/2023/12/02/adding-cellular-connectivity-to-the-hackaday-supercon-badge/ | Adding Cellular Connectivity To The Hackaday Supercon Badge | Lewin Day | [
"Misc Hacks"
] | [
"2023 Hackaday Supercon",
"badge",
"cellular data"
] | Did you manage to make it down to Hackaday Supercon 2023? Maybe you did, and maybe you had a great time hacking away on the badge. [Dan] and ex-Hackaday alumnus [Mike Szczys] certainly did, with the guys from Golioth
adding cellular connectivity to the hardware and developing a community art project.
The badge was hooked up over I2C to a Golioth Aludel Mini, which is a prototyping platform featuring a Sparkfun nRF9160 cellular modem. A custom Micropython implementation was compiled for the badge so that the badge could act as an I2C peripheral to be queried by the Aludel Mini. The sketch app on the badge was tweaked to allow the small pictures it created to be be uploaded to a cloud site called Badgecase, programmed in Rust. Amusingly, it turns out the sketch app uses a rectangular workspace, though you only see a circular section of it on the Supercon badge’s awesomely round display.
Much of the hack is happening off-board from the badge itself, but it’s a neat piece of work that shows how easy cellular connectivity is to implement these days. We’ve seen some other great feats with the Vectorscope badge, and it looked great if you happened to
3D print a case for it, too.
Video after the break. | 1 | 1 | [
{
"comment_id": "6704498",
"author": "Gravis",
"timestamp": "2023-12-03T15:36:00",
"content": "Ouch! $25 per chip. It’s a neat chip but it’s not $25-per-chip neat.",
"parent_id": null,
"depth": 1,
"replies": []
}
] | 1,760,372,085.981318 | ||
https://hackaday.com/2023/12/02/honey-i-ate-the-camera/ | Honey, I Ate The Camera | Jenny List | [
"classic hacks"
] | [
"camera",
"fuji instax",
"instant camera"
] | We like cameras here at Hackaday. We like them a lot. But until now that liking has never extended to liking their taste. A build from [Dmitri Tcherbadji] could change all that though, and he’s created
a working Fuji Instax Square camera made from gingerbread
.
To look at, it’s a straightforward box camera, albeit one made from sheets of gingerbread stuck together with what looks like icing. The film rests in an off-the-shelf development unit but the rest is edible, including unexpectedly the lens which is made of sugar glass. The photos it returns are definitely somewhat cloudy, but that it works at all is a significant feat.
While it’s an unconventional choice it’s clear that gingerbread, or at least a baked material similar to it, could become a useful tool in a maker’s arsenal. In this case it’s light-proof, but were instantly curious about how well a moulded piece of dough might hold its shape when baked. He reports the gingerbread expanding in the oven, however we’re guessing that tuning the quantity of raising agent could help.
Home-made cameras have featured here many times, but Instax seems to pop up most often
as a hacked in replacement for obsolete Polaroid packs
. | 17 | 12 | [
{
"comment_id": "6704395",
"author": "ScubaBearLA",
"timestamp": "2023-12-03T03:21:55",
"content": "I’m reminded of the old Russian proverb: “The marvel is not that the bear dances well, but that the bear dances at all.”",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"commen... | 1,760,372,086.219134 | ||
https://hackaday.com/2023/12/02/mozilla-lets-folks-turn-ai-llms-into-single-file-executables/ | Mozilla Lets Folks Turn AI LLMs Into Single-File Executables | Donald Papp | [
"Artificial Intelligence"
] | [
"ai",
"binaries",
"llama",
"LLM",
"local AI"
] | LLMs (Large Language Models) for local use are usually distributed as a set of weights in a multi-gigabyte file. These cannot be directly used on their own, which generally makes them harder to distribute and run compared to other software. A given model can also have undergone changes and tweaks, leading to different results if different versions are used.
To help with that, Mozilla’s innovation group have released
llamafile
, an open source method of turning a set of weights into a single binary that runs on six different OSes (macOS, Windows, Linux, FreeBSD, OpenBSD, and NetBSD) without needing to be installed. This makes it dramatically easier to distribute and run LLMs, as well as ensuring that a particular version of LLM remains consistent and reproducible, forever.
This wouldn’t be possible without the work of [Justine Tunney], creator of
Cosmopolitan
, a build-once-run-anywhere framework. The other main part is
llama.cpp
, and we’ve covered
why it is such a big deal
when it comes to running self-hosted LLMs.
There are
some sample binaries
available using the Mistral-7B, WizardCoder-Python-13B, and LLaVA 1.5 LLMs. Just keep in mind that if you’re on a Windows platform, only the LLaVA 1.5 will run, because it’s the only one that squeaks under the 4 GB limit on executable files that Windows has. If you run into issues, check out
the gotchas list
for troubleshooting tips. | 20 | 10 | [
{
"comment_id": "6704419",
"author": "John",
"timestamp": "2023-12-03T05:47:45",
"content": "Justine Tunney is truly a treasure. Everything she does is fascinating.",
"parent_id": null,
"depth": 1,
"replies": []
},
{
"comment_id": "6704441",
"author": "shinsukke",
"timest... | 1,760,372,086.272021 | ||
https://hackaday.com/2023/12/02/build-yourself-a-screw-propelled-robot-to-tackle-the-dirt/ | Build Yourself A Screw Propelled Robot To Tackle The Dirt | Lewin Day | [
"Robots Hacks"
] | [
"ESP-32",
"robot",
"screw drive",
"video feed"
] | Wheels and tracks are common choices for robot propulsion, but they’re not the only game in town. You can do some nifty things with long extruded screws , and they work pretty well in soft terrain.
[gokux] set about building a small robot using this propulsion method using 3D printed parts.
The build uses a Seeed Studio XIAO ESP32S3 as the brains of the operation. This provides wireless connectivity for remote control, as well as a way to get a low-latency video feed out of the robot from the OV2640 camera. The ESP32 controls a pair of brushed DC gearmotors via a DRV8833 motor driver. Each drives one of the two screws on the robot. By driving the two screws separately, the robot has simple skid steering. Two 18650 lithium-ion cells provide power for the robot, and are charged via a TP4056 battery charger module.
If you want to build a small robot that can handle soft terrain well, screw drives could be just the solution you’re looking for. They’re usually a bit slow, though, especially
for human-scale conveyances
, so don’t write off wheels or tracks
if you don’t have to.
And, of course, when your build is done, don’t forget to put it online and
tell us all about it! | 11 | 7 | [
{
"comment_id": "6704345",
"author": "Col Campbell",
"timestamp": "2023-12-02T21:47:29",
"content": "The soviets built one of these in the 60s as a nuke delivery vehicle, I believe it was codenamed “shagohod”",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "67... | 1,760,372,086.162886 | ||
https://hackaday.com/2023/12/02/update-on-the-bluffs-bluetooth-vulnerability/ | Update On The BLUFFS Bluetooth Vulnerability | Maya Posch | [
"News",
"Security Hacks"
] | [
"bluetooth",
"vulnerability"
] | As we first reported in yesterday’s weekly security post
, researchers at EURECOM have
revealed the details
(PDF,
references
) of a new man-in-the-middle (MITM) attack on Bluetooth 4.2 through 5.4, which has been assigned
CVE-2023-24023
. Like
preceding CVEs
, it concerns the session authentication between Bluetooth devices, where the attacker uses spoofed paired or bonded devices to force the use of a much shorter encryption key length.
The name of this newly discovered vulnerability is BLUFFS (Bluetooth Forward and Future Secrecy), where forward and future secrecy are important terms that refer to the protection of secure sessions against compromise in the past (forward, FoS) and future (FuS). The
CVE presentation notes
that the Bluetooth specification does not cover either FuS or FoS. In total two new architectural vulnerabilities were discovered, both of which attack the security key.
The Bluetooth SIG has
released a statement
regarding this attack method. Although serious, it would seem that the core issue is that some implementations allow for encryption key lengths below 7 octets:
Although the researchers note potential fixes and mitigations, these would need to be implemented in every affected Bluetooth controller out there — this might be a good time to re-examine in how far one relies on Bluetooth security, and what the effect of a hijacked session might be. | 14 | 4 | [
{
"comment_id": "6704349",
"author": "Gravis",
"timestamp": "2023-12-02T21:49:32",
"content": "I ponder how many medical implants have this vulnerability and no way to update the BT stack.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6705137",
"aut... | 1,760,372,086.412718 | ||
https://hackaday.com/2023/12/02/the-physics-lesson-i-keep-re-learning/ | The Physics Lesson I Keep Re-Learning | Elliot Williams | [
"Hackaday Columns",
"Rants",
"Slider"
] | [
"impedance matching",
"newsletter",
"rants",
"stick shift"
] | One of the most broadly applicable ideas I’ve ever encountered is the concept of
impedance matching
. If you’re into radio frequency electronics, you’re probably thinking that I mean getting all your circuit elements working to a common characteristic resistance for maximum power transfer. (If you’re not, you’re probably wondering what that jumble of words even means. Fear not!)
But I mean impedance matching in the larger sense. Think about driving a stick-shift automobile. In low gear, the engine has a lot of torque on the wheels, but it can’t spin them all that fast. In high, the wheels turn fastest, but there’s not enough torque to get you started from a standstill. Sometimes you need more force and less motion, other times more motion and less force. The gearbox lets you match the motor’s power to the resistance – the impedance – it’s trying to overcome.
Or think about a cello. The strings are tight, and vibrate with quite a bit of force, but they don’t move all that much. Air, which is destined to carry the sound to your ear, doesn’t take much force to move, and the cello would play louder if it moved more of it. So the bridge conveys the small, but strong, vibrations of the strings and pushes against the top of the resonant box that makes up the body of the instrument. This in turn pushes a lot of air, but not very hard. This is also why speakers have cones, and also why your ear has that crazy stirrup mechanism. Indeed, counting the number of impedance matches between Yo Yo Ma and your brain, I come up with four or five, including electrical matches in the pre-amp.
I mention this because I recently ran into a mismatch. Fans blow air either hard or in large volume. If you pick a fan that’s designed for volume, and put it in a pressure application, it’s like trying to start driving in fifth gear. It stalled, and almost no air got pushed up through the beans in my new “improved” coffee roaster, meaning I had to rebuild it with the old fan, and quick before the next cup was due.
I ran into this mismatch even though I knew there was a possible impedance issue there. I simply don’t have a good intuitive feel how much pressure I needed to push the beans around – the impedance in question – and I bought the wrong fan. But still, knowing that there is a trade-off is a good start. I hope this helps you avoid walking in my footsteps!
This article is part of the Hackaday.com newsletter, delivered every seven days for each of the last 200+ weeks. It also includes our favorite articles from the last seven days that you can see on
the web version of the newsletter
.
Want this type of article to hit your inbox every Friday morning?
You should sign up
! | 69 | 20 | [
{
"comment_id": "6704262",
"author": "Cyna",
"timestamp": "2023-12-02T15:54:55",
"content": "Sure, just look at all the Noctua case fans in use for high-pressure applications.",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6704280",
"author": "LookAt... | 1,760,372,086.519701 | ||
https://hackaday.com/2023/12/02/generating-motion-via-nitinol-wires/ | Generating Motion Via Nitinol Wires | Lewin Day | [
"Parts",
"Robots Hacks"
] | [
"hand",
"nickel",
"nitinol",
"titanium",
"wire"
] | Generally, when we’re looking to build something that moves we reach for motors, servos, or steppers — which ultimately are all just variations on the same concept. But there
are
other methods of locomotion available. As
[Jamie Matthews] demonstrates
, Nitinol wires can be another way to help get things moving.
Nitinol is a type of metal wire made of nickel and titanium that is also known as “memory wire”, because it can remember its former shape and transition back to it with a temperature change. [Jamie] uses this property to create a simple hand that is actuated by pieces of wire sourced from Amazon. This is actually a neat way to go, as it goes some way to mimicking how our own hands are moved by our tendons.
[Jamie] does a great job of explaining how to get started with Nitinol and how it works in a practical sense. We’ve seen it put to some wacky uses before, too, such as
the basis for an airless tire
. | 13 | 3 | [
{
"comment_id": "6704237",
"author": "Nick",
"timestamp": "2023-12-02T13:58:33",
"content": "Question for a wizard: can this material (or similar) oscillate between two forms at high frequency (MHz+)?",
"parent_id": null,
"depth": 1,
"replies": [
{
"comment_id": "6704246",
... | 1,760,372,086.671302 | ||
https://hackaday.com/2023/12/02/led-tester-also-calculates-resistor-for-target-voltage/ | LED Tester Also Calculates Resistor For Target Voltage | Donald Papp | [
"LED Hacks",
"Tool Hacks"
] | [
"arduino",
"current limiting",
"led",
"series resistor",
"tester"
] | [mircemk] built a
slick-looking LED tester
with a couple handy functions built in. Not only can one select a target current to put through an LED, but by providing a target voltage, the system will automatically calculate the necessary series resistor. If for example the LED is destined for 14 V, this device will not only show how the LED looks at the chosen current, but will calculate the required resistor to get the same results on a 14 V system.
The buttons on the left control the target current and the voltage of the destination system. Once an LED is connected it will light up and the display indicates the LED’s forward voltage, the LED current, and the calculated series resistor value to obtain the same result at the selected target voltage. It’s a handy way to empirically dial in LED brightness values without needing to actually set up any particular test environment.
On the inside there’s little more than a handful of passive components, an Arduino, an LCD display, and a few buttons. This kind of tool reminds us of the
highly clever component testers
that hit the hobbyist scene years ago, showing what kind of advanced tricks a modern microcontroller is capable of with the right programming. (Here’s a look at
how those work
, if you’re interested in some deeper details.)
[mircemk] demonstrates his tool in the video, embedded below. We particularly like the attention he paid to the enclosure, giving it a very functional layout. It goes to show that when designing something,
it’s never too early to consider enclosure and UI layout
. | 12 | 9 | [
{
"comment_id": "6704221",
"author": "Mr Name Required",
"timestamp": "2023-12-02T11:58:19",
"content": "Connecting alligator clips seems time-consuming and clumsy. Perhaps a two-prong socket to simply stick the LED in, like the old transistor testers of yesteryear. Or two V-slotted plates to jam t... | 1,760,372,086.571245 | ||
https://hackaday.com/2023/12/01/print-your-own-brain-lamp-from-mri-data/ | Print Your Own Brain Lamp From MRI Data | Lewin Day | [
"3d Printer hacks"
] | [
"brain",
"lamp",
"mri"
] | MRIs generally fall somewhere on the scale from boring to stressful depending on why you’re having one and how claustrophobic you get. Regardless, they’re a wonderful diagnostic tool and they’ve saved thousands if not millions of lives over the years. In a fun use of the technology,
[mandalaFractals] has shown us how to make a 3D-printed brain lamp using an MRI scan of the head.
The build starts with an off-the-shelf lamp base and a smart LED bulb as the light source, though you could swap those out as desired for something like a microcontroller, a USB power supply, and addressable LEDs if you were so inclined. The software package Slicer is then used to take an MRI brain scan and turn it into something that you can actually 3D print. It’ll take some cleaning up to remove artifacts and hollow it out, but it’s straightforward enough to get a decent brain model out of the data. Alternatively, you can use someone else’s if you don’t have your own scan. Then, all you have to do is print it in a couple of halves, and pop it on the lamp base, and you’re done!
It’s a pretty neat build. Who wouldn’t love telling their friends that their new brain lamp was an accurate representation of their own grey noodles, after all? It could be a fun gift next time Halloween rolls around, too!
Meanwhile, if you’ve got your own MRI hacks that you’ve been cooking up,
don’t hesitate to let us know! | 12 | 5 | [
{
"comment_id": "6704202",
"author": "Jonathan Wilson",
"timestamp": "2023-12-02T08:51:27",
"content": "Of course the downside to a project like this is that you need to have some negative-to-your-health medical reason to have a brain scan MRI in the first place (no-one is going to go get a scan jus... | 1,760,372,086.622171 | ||
https://hackaday.com/2023/12/01/cat-o-matic-3000-serves-your-feline-masters/ | Cat-o-Matic 3000 Serves Your Feline Masters | Kristina Panos | [
"home hacks",
"Microcontrollers"
] | [
"atmega 88",
"because cats",
"cats",
"crystal",
"feeding"
] | When you have three cats and three humans, you have one problem: feeding them on a schedule without over or under feeding them. Even if there was only one human in the equation,
the Cat-o-Matic 3000
would still be a useful tool.
Essentially, it’s a traffic light for cats — where green means you are go for feeding, and red means the cat was just fed. Yellow, of course, means the cat is either half-full or half-empty, depending on your outlook.
The brains of this operation is an ATmega88PA leftover from another project. There’s a no-name voltage regulator that steps up the two AA cells to 5 volts. Timing comes from a 32 kHz crystal that allows the microcontroller to stay in power-saving sleep mode for long periods of time.
Creator [0xCAFEAFFE] says the firmware was cobbled together from other projects. Essentially, it wakes up once per second to increment the uptime counter and then goes back to sleep. Short-pressing a button shows the feeding status, and long-pressing it will reset the timer.
Wanna make a cat status indicator without electronics?
Give flexures a try
. | 8 | 6 | [
{
"comment_id": "6704203",
"author": "kaaaaaaaaaaaaaaaang",
"timestamp": "2023-12-02T08:54:18",
"content": "This is not the real “Cat-o-Matic”, colinfurze made the real one a while ago and It also involved cats and cat-food.",
"parent_id": null,
"depth": 1,
"replies": [
{
"... | 1,760,372,086.72239 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.