generative AI

10 Articles

USB Stick Hides Large Language Model

February 17, 2025 by 25 Comments

Large language models (LLMs) are all the rage in the generative AI world these days, with the truly large ones like GPT, LLaMA, and others using tens or even hundreds of billions of parameters to churn out their text-based responses. These typically require glacier-melting amounts of computing hardware, but the “large” in “large language models” doesn’t really need to be that big for there to be a functional, useful model. LLMs designed for limited hardware or consumer-grade PCs are available now as well, but [Binh] wanted something even smaller and more portable, so he put an LLM on a USB stick.

This USB stick isn’t just a jump drive with a bit of memory on it, though. Inside the custom 3D printed case is a Raspberry Pi Zero W running llama.cpp, a lightweight, high-performance version of LLaMA. Getting it on this Pi wasn’t straightforward at all, though, as the latest version of llama.cpp is meant for ARMv8 and this particular Pi was running the ARMv6 instruction set. That meant that [Binh] needed to change the source code to remove the optimizations for the more modern ARM machines, but with a week’s worth of effort spent on it he finally got the model on the older Raspberry Pi.

Getting the model to run was just one part of this project. The rest of the build was ensuring that the LLM could run on any computer without drivers and be relatively simple to use. By setting up the USB device as a composite device which presents a filesystem to the host computer, all a user has to do to interact with the LLM is to create an empty text file with a filename, and the LLM will automatically fill the file with generated text. While it’s not blindingly fast, [Binh] believes this is the first plug-and-play USB-based LLM, and we’d have to agree. It’s not the least powerful computer to ever run an LLM, though. That honor goes to this project which is able to cram one on an ESP32.

Continue reading “USB Stick Hides Large Language Model” →

Preventing AI Plagiarism With .ASS Subtitling

January 25, 2025 by 55 Comments

Around two years ago, the world was inundated with news about how generative AI or large language models would revolutionize the world. At the time it was easy to get caught up in the hype, but in the intervening months these tools have done little in the way of productive work outside of a few edge cases, and mostly serve to burn tons of cash while turning the Internet into even more of a desolate wasteland than it was before. They do this largely by regurgitating human creations like text, audio, and video into inferior simulacrums and, if you still want to exist on the Internet, there’s basically nothing you can do to prevent this sort of plagiarism. Except feed the AI models garbage data like this YouTuber has started doing.

At least as far as YouTube is concerned, the worst offenders of AI plagiarism work by downloading the video’s subtitles, passing them through some sort of AI model, and then generating another YouTube video based off of the original creator’s work. Most subtitle files are the fairly straightfoward .srt filetype which only allows for timing and text information. But a more obscure subtitle filetype known as Advanced SubStation Alpha, or .ass, allows for all kinds of subtitle customization like orientation, formatting, font types, colors, shadowing, and many others. YouTuber [f4mi] realized that using this subtitle system, extra garbage text could be placed in the subtitle filetype but set out of view of the video itself, either by placing the text outside the viewable area or increasing its transparency. So now when an AI crawler downloads the subtitle file it can’t distinguish real subtitles from the garbage placed into it.

[f4mi] created a few scripts to do this automatically so that it doesn’t have to be done by hand for each one. It also doesn’t impact the actual subtitles on the screen for people who need them for accessibility reasons. It’s a great way to “poison” AI models and make it at least harder for them to rip off the creations of original artists, and [f4mi]’s tests show that it does work. We’ve actually seen a similar method for poisoning data sets used for emails long ago, back when we were all collectively much more concerned about groups like the NSA using automated snooping tools in our emails than we were that machines were going to steal our creative endeavors.

Thanks to [www2] for the tip!

Continue reading “Preventing AI Plagiarism With .ASS Subtitling” →

Using AI To Help With Assembly

November 7, 2024 by 30 Comments

Although generative AI and large language models have been pushed as direct replacements for certain kinds of workers, plenty of businesses actually doing this have found that using this new technology can cause more problems than it solves when it is given free reign over tasks. While this might not be true indefinitely, the real use case for these tools right now is as a kind of assistant to certain kinds of work. For this they can be incredibly powerful as [Ricardo] demonstrates here, using Amazon Q to help with game development on the Commodore 64.

The first step here was to generate code that would show a sprite moving across the screen. The AI first generated code in all caps, as was the style at the time of the C64, but in [Ricardo]’s development environment this caused some major problems, so the code was converted to lowercase. A more impressive conversion was done in the next steps, as the program needed to take advantage of the optimizations found in the Assembly language. With the code converted to 6502 Assembly that can run on the virtual Commodore, [Ricardo] was eventually able to show four sprites moving across the screen after several iterations with the AI, as well as change the style of the sprites to arbitrary designs.

Although the post is a bit over-optimistic on Amazon Q as a tool specifically for developers, it might have some benefits over other generative AIs especially if it’s capable at the chore of programming in Assembly language. We’d love to hear anyone with real-world experience with this and whether it is truly worth the extra cost over something like Copilot or GPT 4. For any of these generative AI models, though, it’s probably worth trying them out while they’re in their early stages. Keep in mind that there’s a lot more than programming that can be done with some of them as well.

Hackaday Links Column Banner

Hackaday Links: September 1, 2024

September 1, 2024 by 21 Comments

Why is it always a helium leak? It seems whenever there’s a scrubbed launch or a narrowly averted disaster, space exploration just can’t get past the problems of helium plumbing. We’ve had a bunch of helium problems lately, most famously with the leaks in Starliner’s thruster system that have prevented astronauts Butch Wilmore and Suni Williams from returning to Earth in the spacecraft, leaving them on an extended mission to the ISS. Ironically, the launch itself was troubled by a helium leak before the rocket ever left the ground. More recently, the Polaris Dawn mission, which is supposed to feature the first spacewalk by a private crew, was scrubbed by SpaceX due to a helium leak on the launch tower. And to round out the helium woes, we now have news that the Peregrine mission, which was supposed to carry the first commercial lander to the lunar surface but instead ended up burning up in the atmosphere and crashing into the Pacific, failed due to — you guessed it — a helium leak.
Continue reading “Hackaday Links: September 1, 2024” →

What If The Matrix Was Made In The 1950s?

June 9, 2024 by 30 Comments

We’ve noticed a recent YouTube trend of producing trailers for shows and movies as if they were produced in the 1950s, even when they weren’t. The results are impressive and, as you might expect, leverage AI generation tools. While we enjoy watching them, we were especially interested in [Patrick Gibney’s] peek behind the curtain of how he makes them, as you can see below. If you want to see an example of the result first, check out the second video, showing a 1950s-era The Matrix.

Of course, you could do some of it yourself, but if you want the full AI experience, [Patrick] suggests using ChatGPT to produce a script, though he admits that if he did that, he would tweak the results. Other AI tools create the pictures used and the announcer-style narration. Another tool produces cinematographic shots that include the motion of the “actors” and other things in the scene. More tools create the background music.

Continue reading “What If The Matrix Was Made In The 1950s?” →

Wrencher-2: A Bold New Direction For Hackaday

April 1, 2024 by 44 Comments

Over the last year it’s fair to say that a chill wind has blown across the face of the media industry, as the prospect emerges that many content creation tasks formerly performed by humans instead being swallowed up by the inexorable rise of generative AI. In a few years we’re told, there may even be no more journalists, as the computers become capable of keeping your news desires sated with the help of their algorithms.

Here at Hackaday, we can see this might be the case for a gutter rag obsessed with celebrity love affairs and whichever vegetable is supposed to cure cancer this week, but we continue to believe that for quality coverage of the latest and greatest in the hardware hacking world, you can’t beat a writer made of good old-fashioned meat. Indeed, in a world saturated by low-quality content, the opinions of smart and engaged writers become even more valuable. So we’ve decided to go against the trend, by launching not a journalist powered by AI, but an AI powered by journalists.

Announcing Wrencher-2, a Hackaday chat assistant in your browser

Wrencher-2 is a new paradigm in online chat assistants, eschewing generative algorithms in favour of the collective expertise of the Hackaday team. Ask Wrencher-2 a question, and you won’t get a vague and made-up answer from a computer, instead you’ll get a pithy and on-the-nail answer from a Hackaday staffer. Go on – try it! Continue reading “Wrencher-2: A Bold New Direction For Hackaday” →

Generative AI Now Encroaching On Music

March 22, 2024 by 62 Comments

While it might not seem like it to a novice, music turns out to be a highly mathematical endeavor with precise ratios between chords and notes as well as overall structure of rhythm and timing. This is especially true of popular music which has even more recognizable repeating patterns and trends, making it unfortunately an easy target for modern generative AI which is capable of analyzing huge amounts of data and creating arguably unique creations. This one, called Suno, does just that for better or worse.

Unlike other generative AI offerings that are currently available for creating music, this one is not only capable of generating the musical underpinnings of the song itself but can additionally create a layer of intelligible vocals as well. A deeper investigation of the technology by Rolling Stone found that the tool uses its own models to come up with the music and then offloads the text generation for the vocals to ChatGPT, finally using the generated lyrics to generate fairly convincing vocals. Like image and text generation models that have come out in the last few years, this has the potential to be significantly disruptive.

While we’re not particularly excited about living in a world where humans toil while the machines create art and not the other way around, at best we could hope for a world where real musicians use these models as tools to enhance their creativity rather than being outright substitutes, much like ChatGPT itself currently is for programmers. That might be an overly optimistic view, though, and only time will tell.