31
Beyond self-attention: How a small language model predicts the next token
A deep dive into the internals of a small transformer model to learn how it turns self-attention calculations into accurate predictions for the next token.
32
Google's Results Are Infested, Open AI Is Using Their Playbook from the 2000s
Google search results are becoming annoying to use and Open AI is about to eat Google's lunch.
33
Understand how transformers work by demystifying the math behind them
Understand how transformers work by demystifying all the math behind them
34
Insights from over 10,000 comments on "Ask HN: Who Is Hiring" using GPT-4o
By structuring the comments on Hacker News using a predefined response_scheme for the LLM, I’ve tried to get a feeling for current job market and trends.
35
GPT-3.5 crashes when it thinks about useRalativeImagePath too much
Asking it to repeat "ponyuseRal ponyuseRal ponyuseRal pony" makes API requests fail
36
37
A supply chain attack on PyTorch
Security tends to lag behind adoption, and AI/ML is no exception. Four months ago, Adnan Khan and I exploited a critical CI/CD vulnerability in PyTorch, one of the world’s leading ML platform…
38
How I Use "AI"
I don't think that AI models (by which I mean: large language models) are over-hyped. In this post I will list 50 ways I've used them.
39
40
What can LLMs never do?
On goal drift and lower reliability. Or, why can't LLMs play Conway's Game Of Life?
41
42
The Weird Nerd comes with trade-offs
A metascience post of sorts that argues we should take human capital more seriously
43
44
Training LLMs from ground zero as a startup
Chronicles of training strong LLMs from scratch in the wild
45
46
My finetuned models beat OpenAI's GPT-4
Finetunes of Mistral, Llama3 and Solar LLMs are more accurate for my test data than OpenAI’s models.
47
What I learned from looking at 900 most popular open source AI tools
[Hacker News discussion, LinkedIn discussion, Twitter thread]
48
Planner programming blows my mind
Picat is a research language intended to combine logic programming, imperative programming, and constraint solving. I originally learned it to help with vacation scheduling but soon discovered its planner module, which is one of the most fascinating programming models I’ve ever seen. First, a brief explanation of…
49
Do AI companies work?
The market needs to be irrational for you to stay solvent.
50
51
How I run LLMs locally
I document how I run Large Language Models locally.
52
Can AI do maths yet? Thoughts from a mathematician
So the big news this week is that o3, OpenAI’s new language model, got 25% on FrontierMath. Let’s start by explaining what this means.
53
Many AI safety orgs have tried to criminalize currently-existing open-source AI
<p>I've seen a few conversations where someone says something like this:</p> <blockquote> <p>I've been using an open-source LLM lately -- I'm a huge fan of not depending on OpenAI, Anthropic, or Google. But I'm really sad that the AI safety groups are trying to ban the kind of open-source LLM that I'm using.</p>…
54
Use Prolog to improve LLM's reasoning
On one side, LLMs show unseen capabilities in reasoning, but on the other - reasoning in LLMs is not ideal.
55
Diffusion models from scratch, from a new theoretical perspective
This tutorial aims to give a gentle introduction to diffusion models, with a running example to illustrate how to build, train and sample from a simple diffusion model from scratch.
56
Web scraping with GPT-4o: powerful but expensive
tl;dr; show me the demo and source code!
57
AI generated security reports about curl
I have held back on writing anything about AI or how we (not) use AI for development in the curl factory. Now I can't hold back anymore. Let me show you the most significant effect of AI on curl as of today - with examples. Bug Bounty Having a bug bounty means that we offer … Continue reading The I in LLM stands for…
58
TinyML: Ultra-low power machine learning
Explanation of TinyML, what it is used for and the main techniques it uses
59
60
Google’s AI thinks I left a Gatorade bottle on the moon
Google’s NotebookLLM is the first AI podcast I’d actually listen to. Give it a web page or document, and it will generate you a podcast about it.