SmolLM2(simonwillison.net)

86 points by edward 2 years ago | 20 comments

Training open-source LLMs on ChatGPT output is a really bad idea.(gist.github.com)

82 points by laprise 3 years ago | 41 comments

A simulation of me: fine-tuning an LLM on 240k text messages(edwarddonner.com)

165 points by eddonner 2 years ago | 104 comments

It’s infuriatingly hard to understand how closed models train on their input(simonwillison.net)

288 points by simonw 3 years ago | 189 comments

Backprop Alternative: Augmented Lagrangian Predictive Coding(pub.sakana.ai)

102 points by guld 1 month ago | 34 comments

Show HN: Building an LLM from Scratch in TypeScript(book.humanexperiences.io)

27 points by baraa_ 12 days ago | 2 comments

An online book guiding readers through building a large language model from scratch in NodeJS and TypeScript, covering dataloaders, embeddings, and attention.