Text Compression Gets Weirdly Efficient With LLMs

August 27, 2023 by Donald Papp 65 Comments

It used to be that memory and storage space were so precious and so limited of a resource that handling nontrivial amounts of text was a serious problem. Text compression was a highly practical application of computing power.

Today it might be a solved problem, but that doesn’t mean it doesn’t attract new or unusual solutions. [Fabrice Bellard] released ts_zip which uses Large Language Models (LLM) to attain text compression ratios higher than any other tool can offer.

LLMs are the technology behind natural language AIs, and applying them in this way seems effective. The tradeoff? Unlike typical compression tools, the lossless decompression part isn’t exactly guaranteed when an LLM is involved. Lossy compression methods are in fact quite useful. JPEG compression, for example, is a good example of discarding data that isn’t readily perceived by humans to make a smaller file, but that isn’t usually applied to text. If you absolutely require lossless compression, [Fabrice] has that covered with NNCP, a neural-network powered lossless data compressor.

Do neural networks and LLMs sound far too serious and complicated for your text compression needs? As long as you don’t mind a mild amount of definitely noticeable data loss, check out [Greg Kennedy]’s Lossy Text Compression which simply, brilliantly, and amusingly uses a thesaurus instead of some fancy algorithms. Yep, it just swaps longer words for shorter ones. Perhaps not the best solution for every need, but between that and [Fabrice]’s brilliant work we’re confident there’s something for everyone who craves some novelty with their text compression.

[Photo by Matthew Henry from Burst]

Self-Hosted Chatbot Focuses On Privacy

July 30, 2023 by Bryan Cockfield 6 Comments

Large language models (LLMs) have been all the rage lately, assisting from all kinds of tasks from programming to devising Excel formulas to shortcutting school work. They’re also relatively easy to access for the most part, but as the old saying goes, if something on the Internet is free the real product is you (and your data). Luckily there are ways of hosting LLMs on your own to avoid your personal data getting harvested, as well as taking advantage of open-source solutions, but building these systems takes a little bit of effort. [Stephen] and a team from Mozilla walk us through this process and show us a number of options currently available.

Working from the ground up, the group first decides on hosting, which (unsurprisingly) involves using Mozilla hosting services. The choice of runtime environment was a little bit more challenging. The project was time constrained, so they looked at two options here: Hugging Face and llama.cpp. Eventually deciding to move forward with llama.cpp largely due to its ability to run on more consumer-oriented hardware (especially Apple silicon) and the fact that it doesn’t need a powerful GPU, the next task was to choose the model. Settling on the LLaMa model that Facebook recently open-sourced, this model works well with the runtime environment and is essentially the only one that does.

From there, the team at Mozilla wanted to make sure their chat bot would be able to provide other Mozilla employees with information more readily pertinent to their jobs, so they trained their model with some internal Mozilla data as well as other more generic information. This doesn’t mean the job is done, though, there are a number of other factors that went in to designing this system before it was finally complete. Even then, since they built this in a week it’s not perfect; there are some issues with non-permissive licensing of some of the components and many of the design choices may not have been ideal. It’s impressive what’s out there if you’re hosting your own system, though, and while this might be a little more advanced for a self-hosted project, take a look at some other more beginner-friendly projects you can try if you’re just starting out on the self-hosted path.

The Right Benchmark For GPT

July 29, 2023 by Elliot Williams 41 Comments

Dan Maloney wanted to design a part for 3D printing. OpenSCAD is a coding language for generating 3D objects. ChatGPT can write code. What could possibly go wrong? You should go read his article because it’s enlightening and hilarious, but the punchline is that it ran afoul of syntax errors, but also gave him enough of a foothold that he could teach himself enough OpenSCAD to get the project done anyway. As with many people who have asked the AI to create some code, Dan finds that it’s not as good as asking someone who knows what they’re doing, but that it’s also better than nothing.

And this is where I start grumbling. When you type your desires into the word-follower machine, your alternative isn’t nothing. Your alternative is to fire up a search engine instead and type “openscad tutorial”. That, for nearly any human endeavor, will get you a few good guides, written by humans who are probably expert in the subject in question, and which are aimed at teaching you the thing that you want to learn. It doesn’t get better than that. You’ll be up and running with your design in no time.

Indeed, if you think about the relevant source material that the LLM was trained on, it’s exactly these tutorials. It can’t possibly do better than the best of them, although the resulting average tutorial might be better than the worst you’ll find. (Some have speculated on what happens when the entire Internet is filled with these generated texts – what will future AIs learn from?)

In Dan’s case, though, he didn’t necessarily want to learn OpenSCAD – he just wanted the latch designed. But in the end, he had to learn enough OpenSCAD to get the AI code compiling without error. He spent an hour learning OpenSCAD and now he’s good to go on his next project too.

So the next time you hear someone say that they got an answer back from a large language model that wasn’t perfect, but it was “better than nothing”, think critically if “nothing” is really the right benchmark.

Do you really want to learn nothing? Do you really have no resources to get started with? I would claim that we have the most amazing set of tutorial resources the world has ever known at our fingertips. Compared to the ability to teach millions of humans to achieve their own goals, that makes the LLM party tricks look kinda weak, in my opinion.

ChatGPT, The Worst Summer Intern Ever

July 26, 2023 by Dan Maloney 71 Comments

Back when I used to work in the pharma industry, I had the opportunity to hire summer interns. This was a long time ago, long enough that the fresh-faced college students who applied for the gig are probably now creeping up to retirement age. The idea, as I understood it, was to get someone to help me with my project, which at the time was standing up a distributed data capture system with a large number of nodes all running custom software that I wrote, reporting back to a central server running more of my code. It was more work than I could manage on my own, so management thought they’d take mercy on me and get me some help.

The experience didn’t turn out quite like I expected. The interns were both great kids, very smart, and I learned a lot from them. But two months is a very tight timeframe, and getting them up to speed took up most of that time. Add in the fact that they were expected to do a presentation on their specific project at the end of the summer, and the whole thing ended up being a lot more work for me than if I had just done the whole project myself.

I thought about my brief experience with interns recently with a project I needed a little help on. It’s nothing that hiring anyone would make sense to do, but still, having someone to outsource specific jobs to would be a blessing, especially now that it’s summer and there’s so much else to do. But this is the future, and the expertise and the combined wisdom of the Internet are but a few keystrokes away, right? Well, maybe, but as you’ll see, even the power of large language models has its limit, and trying to loop ChatGPT in as a low-effort summer intern leaves a lot to be desired.

Continue reading “ChatGPT, The Worst Summer Intern Ever” →

Text-to-Speech Model Can Do Music, Background Noises, And Sound Effects

July 24, 2023 by Donald Papp 8 Comments

Bark is a universal text-to-audio model that can not only create realistic speech, it can incorporate music, background noises, and sound effects. It can even include non-speech sounds like laughter, sighs, throat clearings, and similar elements. But despite the fact that it can deliver such complex results, it’s important to understand some of the peculiarities.

The model takes a prompt and generates the resulting sound from scratch. Results might sometimes be unexpected.

Bark is not a conventional text-to-speech program, and how it works has a lot more in common with large language model AI chatbots. This means that results can deviate from expectations, and outputs aren’t necessarily going to be studio-quality speech. As the project’s README points out, “(generated outputs can) be anything from perfect speech to multiple people arguing at a baseball game recorded with bad microphones.” That being said, there is some support for voice presets as a way to help guide the model with some consistency.

Bark was designed by a company called Suno for research purposes and is available under the MIT License. It can be installed and run locally, and has some demos available as well as an online implementation.

The ability to install and run Bark locally is promising territory for incorporating it into projects. And should you be more interested in speech-to-text instead, don’t forget about this plain C/C++ implementaion of AI-powered speech recognition.

Bridging A Gap Between LLMs And Programming With TypeChat

July 22, 2023 by Bryan Cockfield 33 Comments

By now, large language models (LLMs) like OpenAI’s ChatGPT are old news. While not perfect, they can assist with all kinds of tasks like creating efficient Excel spreadsheets, writing cover letters, asking for music references, and putting together functional computer programs in a variety of languages. One thing these LLMs don’t do yet though is integrate well with existing app interfaces. However, that’s where the TypeChat library comes in, bridging the gap between LLMs and programming.

TypeChat is an experimental MIT-licensed library from Microsoft which sits in between a user and a LLM and formats responses from the AI that are type-safe so that they can easily be plugged back in to the original interface. It does this by generating JSON responses based on user input, making it easier to take the user input directly, run it through the LLM, and then use the output directly in another piece of code. It can be used for things like prototyping prompts, validating responses, and handling errors. It’s also not limited to a single LLM and can be fairly easily modified to work with many of the existing models.

The software is still in its infancy but does hope to make it somewhat easier to work between user inputs within existing pieces of software and LLMs which have quickly become all the rage in the computer science world. We expect to see plenty more tools like this become available as more people take up using these new tools, which have plenty of applications beyond just writing code.

ChatGPT V. The Legal System: Why Trusting ChatGPT Gets You Sanctioned

May 29, 2023 by Maya Posch 66 Comments

Recently, an amusing anecdote made the news headlines pertaining to the use of ChatGPT by a lawyer. This all started when a Mr. Mata sued the airline where years prior he claims a metal serving cart struck his knee. When the airline filed a motion to dismiss the case on the basis of the statute of limitations, the plaintiff’s lawyer filed a submission in which he argued that the statute of limitations did not apply here due to circumstances established in prior cases, which he cited in the submission.

Unfortunately for the plaintiff’s lawyer, the defendant’s counsel pointed out that none of these cases could be found, leading to the judge requesting the plaintiff’s counsel to submit copies of these purported cases. Although the plaintiff’s counsel complied with this request, the response from the judge (full court order PDF) was a curt and rather irate response, pointing out that none of the cited cases were real, and that the purported case texts were bogus.

The defense that the plaintiff’s counsel appears to lean on is that ChatGPT ‘assisted’ in researching these submissions, and had assured the lawyer – Mr. Schwartz – that all of these cases were real. The lawyers trusted ChatGPT enough to allow it to write an affidavit that they submitted to the court. With Mr. Schwartz likely to be sanctioned for this performance, it should also be noted that this is hardly the first time that ChatGPT and kin have been involved in such mishaps.

Continue reading “ChatGPT V. The Legal System: Why Trusting ChatGPT Gets You Sanctioned” →