Vibing, AI Style

April 19, 2025 by Elliot Williams 47 Comments

This week, the hackerverse was full of “vibe coding”. If you’re not caught up on your AI buzzwords, this is the catchy name coined by [Andrej Karpathy] that refers to basically just YOLOing it with AI coding assistants. It’s the AI-fueled version of typing in what you want to StackOverflow and picking the top answers. Only, with the current state of LLMs, it’ll probably work after a while of iterating back and forth with the machine.

It’s a tempting vision, and it probably works for a lot of simple applications, in popular languages, or generally where the ground is already well trodden. And where the stakes are low, as [Al Williams] pointed out while we were talking about vibing on the podcast. Can you imagine vibe-coded ATM software that probably gives you the right amount of money? Vibe-coding automotive ECU software?

While vibe coding seems very liberating and hands-off, it really just changes the burden of doing the coding yourself into making sure that the LLM is giving you what you want, and when it doesn’t, refining your prompts until it does. It’s more like editing and auditing code than authoring it. And while we have no doubt that a stellar programmer like [Karpathy] can verify that he’s getting what he wants, write the correct unit tests, and so on, we’re not sure it’s the panacea that is being proclaimed for folks who don’t already know how to code.

Vibe coding should probably be reserved for people who already are expert coders, and for trivial projects. Just the way you wouldn’t let grade-school kids use calculators until they’ve mastered the basics of math by themselves, you shouldn’t let junior programmers vibe code: It simultaneously demands too much knowledge to corral the LLM, while side-stepping any of the learning that would come from doing it yourself.

And then there’s the security side of vibe coding, which opens up a whole attack surface. If the LLM isn’t up to industry standards on simple things like input sanitization, your vibed code probably shouldn’t be anywhere near the Internet.

So should you be vibing? Sure! If you feel competent overseeing what [Dan] described as “the worst summer intern ever”, and the states are low, then it’s absolutely a fun way to kick the tires and see what the tools are capable of. Just go into it all with reasonable expectations.

Two laptops, side by side, running Llama2 in DOS.

Will It Run Llama 2? Now DOS Can

April 19, 2025 by Tyler August 20 Comments

Will a 486 run Crysis? No, of course not. Will it run a large language model (LLM)? Given the huge buildout of compute power to do just that, many people would scoff at the very notion. But [Yeo Kheng Meng] is not many people.

He has set up various DOS computers to run a stripped down version of the Llama 2 LLM, originally from Meta. More specifically, [Yeo Kheng Meng] is implementing [Andreq Karpathy]’s Llama2.c library, which we have seen here before, running on Windows 98.

Llama2.c is a wonderful bit of programming that lets one inference a trained Llama2 model in only seven hundred lines of C. It it is seven hundred lines of modern C, however, so porting to DOS 6.22 and the outdated i386 architecture took some doing. [Yeo Kheng Meng] documents that work, and benchmarks a few retrocomputers. As painful as it may be to say — yes, a 486 or a Pentium 1 can now be counted as “retro”.

The models are not large, of course, with TinyStories-trained 260 kB model churning out a blistering 2.08 tokens per second on a generic 486 box. Newer machines can run larger models faster, of course. Ironically a Pentium M Thinkpad T24 (was that really 21 years ago?) is able to run a larger 110 Mb model faster than [Yeo Kheng Meng]’s modern Ryzen 5 desktop. Not because the Pentium M is going blazing fast, mind you, but because a memory allocation error prevented that model from running on the modern CPU. Slow and steady finishes the race, it seems.

This port will run on any 32-bit i386 hardware, which leaves the 16-bit regime as the next challenge. If one of you can get an Llama 2 hosted locally on an 286 or a 68000-based machine, then we may have to stop asking “Does it run DOOM?” and start asking “Will it run an LLM?”

Continue reading “Will It Run Llama 2? Now DOS Can” →

Open Source DMR Radio

April 19, 2025 by Al Williams 4 Comments

While ham radio operators have been embracing digital mobile radio (DMR), the equipment is most often bought since — at least in early incarnations — it needs a proprietary CODEC to convert speech to digital and vice versa. But [QRadioLink] decided to tackle a homebrew and open source DMR modem.

The setup uses a LimeSDR, GNU Radio, and Codec2. There are some other open DMR projects, such as OpenRTX. So we are hopeful there are going to be more choices. The DMR modem, however, is only a proof-of-concept and reuses the MMDVMHost code to do the data link layer.

[QRadioLink] found several receiver implementations available, but only one other DMR transmitter — actually, a transceiver. Rather than use an AMBE hardware device or the potentially encumbered mbelib codec, the project uses Codec2 which is entirely open source.

There’s a lot of explanation about the data collection to prepare for the project, and then a deep dive into the nuts and bolts of the implementation. You might enjoy the video below to see things in action.

If you just want to listen to DMR, it’s easy. If Codec2 sounds familiar, it is part of M17.

Continue reading “Open Source DMR Radio” →

Restoring An Abandoned Game Boy Kiosk

April 18, 2025 by Maya Posch 8 Comments

Back in the olden days, there existed physical game stores, which in addition to physical games would also have kiosks where you could try out the current game consoles and handhelds. Generally these kiosks held the console, a display and any controllers if needed. After a while these kiosks would get scrapped, with only a very few ending up being rescued and restored. One of the lucky ones is a Game Boy kiosk, which [The Retro Future] managed to snag after it was found in a construction site. Sadly the thing was in a very rough condition, with the particle board especially being mostly destroyed.

Display model Game Boy, safely secured into the demo kiosk. (Credit: The Retro Future, YouTube)

These Game Boy kiosks also featured a special Game Boy, which – despite being super rare – also was hunted down. This led to the restoration, which included recovering as much of the original particle board as possible, with a professional furniture restore ([Don]) lending his expertise. This provides a master class in how to patch up damaged particle board, as maligned as this wood-dust-and-glue material is.

The boards were then reassembled more securely than the wood screws used by the person who had found the destroyed kiosk, in a way that allows for easy disassembly if needed. Fortunately most of the plastic pieces were still intact, and the Game Boy grey paint was easily matched. Next was reproducing a missing piece of art work, with fortunately existing versions available as reference. For a few missing metal bits that held the special Game Boy in place another kiosk was used to provide measurements.

After all this, the kiosk was powered back on, and it was like 1990 was back once again, just in time for playing Tetris on a dim, green-and-black screen while hunched half into the kiosk at the game store.

Continue reading “Restoring An Abandoned Game Boy Kiosk” →

Haircuts In Space: How To Keep Your Astronauts Looking Fresh

April 18, 2025 by Maya Posch 20 Comments

NASA astronaut Catherine Coleman gives ESA astronaut Paolo Nespoli a haircut in the Kibo laboratory on the ISS in 2011. (Credit: NASA)

Although we tend to see mostly the glorious and fun parts of hanging out in a space station, the human body will not cease to do its usual things, whether it involves the digestive system, or even something as mundane as the hair that sprouts from our heads. After all, we do not want our astronauts to return to Earth after a half-year stay in the ISS looking as if they got marooned on an uninhabited island. Introducing the onboard barbershop on the ISS, and the engineering behind making sure that after a decade the ISS doesn’t positively look like it got the 1970s shaggy wall carpet treatment.

The basic solution is rather straightforward: an electric hair clipper attached to a vacuum that will whisk the clippings safely into a container rather than being allowed to drift around. In a way this is similar to the vacuums you find on routers and saws in a woodworking shop, just with more keratin rather than cellulose and lignin.

On the Chinese Tiangong space station they use a similar approach, with the video showing how simple the system is, little more than a small handheld vacuum cleaner attached to the clippers. Naturally, you cannot just tape the vacuum cleaner to some clippers and expect it to get most of the clippings, which is where both the ISS and Tiangong solutions seems to have a carefully designed construction to maximize the hair removal. You can see the ISS system in action in this 2019 video from the Canadian Space Agency.

Of course, this system is not perfect, but amidst the kilograms of shed skin particles from the crew, a few small hair clippings can likely be handled by the ISS’ air treatment systems just fine. The goal after all is to not have a massive expanding cloud of hair clippings filling up the space station.

Robot Picks Fruit And Changes Light Bulbs With Measuring Tape

April 18, 2025 by Tyler August 9 Comments

How far can you stretch a measuring tape before it buckles? The answer probably depends more on the tape than the user, but it does show how sturdy the coiled spring steel rulers can be. [Gengzhi He et. al.] may have been playing that game in the lab at UC San Diego when they hit upon the idea for a new kind of low-cost robotic gripper.

An image of the GRIP-tape robot described in the article, showing the tape-loop fingers. — Four motors, four strips of measuring tape (doubled up)– one robot hand.

With the lovely backronym “GRIP-tape” — standing for Grasping and Rolling in Plane — you get a sense for what this effector can do. Its two “fingers” are each made of loops of doubled-up measuring tape bound together with what looks suspiciously like duck tape. With four motors total, the fingers can be lengthened or shortened by spooling the tape, allowing a reaching motion, pivot closer or further apart for grasping, and move-in-place like conveyor belts, rotating the object in their grasp.

The combination means it can reach out, grab a light bulb, and screw it into a socket. Or open and decant a jar of spices. Another video shows the gripper reaching out to pick a lemon, and gently twist it off the tree. It’s quite a performance for a device with such modest components.

At the moment, the gripper is controlled via remote; the researchers plan on adding sensors and AI autonomous control. Read all the details in the preprint, or check below the fold to watch the robot in action.

This is hardly the first time we’ve highlighted a grabby robot. We’ve seen belts, we’ve seen origami — but this is the first time we’ve seen a measuring tape. Have you seen a cool robot? Toss us a tip. We’d love to hear from you. Continue reading “Robot Picks Fruit And Changes Light Bulbs With Measuring Tape” →

A Pi-Based LiDAR Scanner

April 18, 2025 by Bryan Cockfield 30 Comments

Although there are plenty of methods for effectively imaging a 3D space, LIDAR is widely regarded as one of the most effective methods. These systems use a rapid succession of laser pulses over a wide area to create an accurate 3D map. Early LIDAR systems were cumbersome and expensive but as the march of time continues on, these systems have become much more accessible to the average person. So much so that you can quickly attach one to a Raspberry Pi and perform LiDAR imaging for a very reasonable cost.

This software suite is a custom serial driver and scanning system for the Raspberry Pi, designed to work with LDRobot LIDAR modules like the LD06, LD19, and STL27L. Although still in active development, it offers an impressive set of features: real-time 2D visualizations, vertex color extraction, generation of 360-degree panoramic maps using fisheye camera images, and export capabilities for integration with other tools. The hardware setup includes a stepper motor for quick full-area scanning, and power options that include either a USB battery bank or a pair of 18650 lithium cells—making the system portable and self-contained during scans.

LIDAR systems are quickly becoming a dominant player for anything needing to map out or navigate a complex 3D space, from self-driving cars to small Arduino-powered robots. The capabilities a system like this brings are substantial for a reasonable cost, and we expect to see more LiDAR modules in other hardware as the technology matures further.

Thanks to [Dirk] for the tip!