How AI Large Language Models Work, Explained Without Math

May 15, 2024 by Donald Papp 24 Comments

Large Language Models (LLMs ) are everywhere, but how exactly do they work under the hood? [Miguel Grinberg] provides a great explanation of the inner workings of LLMs in simple (but not simplistic) terms that eschews the low-level mathematics of how they work in favor of laying bare what it is they do.

At their heart, LLMs are prediction machines that work on tokens (small groups of letters and punctuation) and are as a result capable of great feats of human-seeming communication. Most technical-minded people understand that LLMs have no idea what they are saying, and this peek at their inner workings will make that abundantly clear.

Be sure to also review an illustrated guide to how image-generating AIs work. And if a peek under the hood of LLMs left you hungry for more low-level details, check out our coverage of training a GPT-2 LLM using pure C code.

AI Helps Make Web Scraping Faster And Easier

May 8, 2024 by Donald Papp 13 Comments

Web scraping is usually only a first step towards extracting meaningful data. Once you’ve got everything pulled down, you’ve still got to process it into something useful. Here to assist with that is Scrapegraph-ai, a Python tool that promises to automate the process using a selection of large language models (LLMs).

Scrapegraph-ai is able to accept a URL as well as a prompt, which is a plain-English instruction on what to do with the data. Examples include summarizing, describing images, and more. In other words, gathering the data and analyzing or formatting it can now be done as one.

The project is actually pretty flexible in terms of the AI back-end. It’s able to work with locally-installed AI tools (via ollama) or with API keys for services like OpenAI and more. If you have an OpenAI API key, there’s an online demo that will show you the capabilities pretty effectively. Otherwise, local installation is only a few operations away.

This isn’t the first time we have seen the flexibility of AI tools like large language models leveraged to ease the notoriously-fiddly task of web scraping, and it’s great to see the results have only gotten better.

Train A GPT-2 LLM, Using Only Pure C Code

April 28, 2024 by Donald Papp 7 Comments

[Andrej Karpathy] recently released llm.c, a project that focuses on LLM training in pure C, once again showing that working with these tools isn’t necessarily reliant on sprawling development environments. GPT-2 may be older but is perfectly relevant, being the granddaddy of modern LLMs (large language models) with a clear heritage to more modern offerings.

LLMs are fantastically good at communicating despite not actually knowing what they are saying, and training them usually relies on PyTorch deep learning library, itself written in Python. llm.c takes a simpler approach by implementing the neural network training algorithm for GPT-2 directly. The result is highly focused and surprisingly short: about a thousand lines of C in a single file. It is a highly elegant process that does the same thing the bigger, clunkier methods accomplish. It can run entirely on a CPU, or it can take advantage of GPU acceleration, where available.

This isn’t the first time [Andrej Karpathy] has bent his considerable skills and understanding towards boiling down these sorts of concepts into bare-bones implementations. We previously covered a project of his that is the “hello world” of GPT, a tiny model that predicts the next bit in a given sequence and offers low-level insight into just how GPT (generative pre-trained transformer) models work.

Dump A Code Repository As A Text File, For Easier Sharing With Chatbots

April 14, 2024 by Donald Papp 16 Comments

Some LLMs (Large Language Models) can act as useful programming assistants when provided with a project’s source code, but experimenting with this can get a little tricky if the chatbot has no way to download from the internet. In such cases, the code must be provided by either pasting it into the prompt or uploading a file manually. That’s acceptable for simple things, but for more complex projects, it gets awkward quickly.

To make this easier, [Eric Hartford] created github2file, a Python script that outputs a single text file containing the combined source code of a specified repository. This text file can be uploaded (or its contents pasted into the prompt) making it much easier to share code with chatbots.

Continue reading “Dump A Code Repository As A Text File, For Easier Sharing With Chatbots” →

A Straightforward AI Voice Assistant, On A Pi

February 20, 2024 by Jenny List 6 Comments

With AI being all the rage at the moment it’s been somewhat annoying that using a large language model (LLM) without significant amounts of computing power meant surrendering to an online service run by a large company. But as happens with every technological innovation the state of the art has moved on, now to such an extent that a computer as small as a Raspberry Pi can join the fun. [Nick Bild] has one running on a Pi 4, and he’s gone further than just a chatbot by making into a voice assistant.

The brains of the operation is a Tinyllama LLM, packaged as a llamafile, which is to say an executable that provides about as easy a one-step access to a local LLM as it’s currently possible to get. The whisper voice recognition sytem provides a text transcript of the input prompt, while the eSpeak speech synthesizer creates a voice output for the result. There’s a brief demo video we’ve placed below the break, which shows it working, albeit slowly.

Perhaps the most important part of this project is that it’s easy to install and he’s provided full instructions in a GitHub repository. We know that the quality and speed of these models on commodity single board computers will only increase with time, so we’d rate this as an important step towards really good and cheap local LLMs. It may however be a while before it can help you make breakfast.

Continue reading “A Straightforward AI Voice Assistant, On A Pi” →

Meet GOODY-2, The World’s Most Responsible (And Least Helpful) AI

February 12, 2024 by Donald Papp 27 Comments

AI guardrails and safety features are as important to get right as they are difficult to implement in a way that satisfies everyone. This means safety features tend to err on the side of caution. Side effects include AI models adopting a vaguely obsequious tone, and coming off as overly priggish when they refuse reasonable requests.

Enter GOODY-2, the world’s most responsible AI model. It has next-gen ethical principles and guidelines, capable of refusing every request made of it in any context whatsoever. Its advanced reasoning allows it to construe even the most banal of queries as problematic, and dutifully refuse to answer.

As the creators of GOODY-2 point out, taking guardrails to a logical extreme is not only funny, but also acknowledges that effective guardrails are actually a pretty difficult problem to get right in a way that works for everyone.

Complications in this area include the fact that studies show humans expect far more from machines than they do from each other (or, indeed, from themselves) and have very little tolerance for anything they perceive as transgressive.

This also means that as AI models become more advanced, so too have they become increasingly sycophantic, falling over themselves to apologize for perceived misunderstandings and twisting themselves into pretzels to align their responses with a user’s expectations. But GOODY-2 allows us all to skip to the end, and glimpse the ultimate future of erring on the side of caution.

[via WIRED]

Bringing The Voice Assistant Home

January 14, 2024 by Matthew Carlson 22 Comments

For many, the voice assistants are helpful listeners. Just shout to the void, and a timer will be set, or Led Zepplin will start playing. For some, the lack of flexibility and reliance on cloud services is a severe drawback. [John Karabudak] is one of those people, and he runs his own voice assistant with an LLM (large language model) brain.

In the mid-2010’s, it seemed like voice assistants would take over the world, and all interfaces were going to NLP (natural language processing). Cracks started to show as these assistants ran into the limits of what NLP could reasonably handle. However, LLMs have breathed some new life into the idea as they can easily handle much more complex ideas and commands. However, running one locally is easier said than done.

A firewall with some muscle (Protectli Vault VP2420) runs a VLAN and NIPS to expose the service to the wider internet. For actually running the LLM, two RTX 4060 Ti cards provide the large VRAM needed to load a decent-sized model at a cheap price point. The AI engine (vLLM) supports dozens of models, but [John] chose a quantized version of Mixtral to fit in the 32GB of VRAM he had available.

Continue reading “Bringing The Voice Assistant Home” →