ChatGPT vs. open source on harder tasks(github.com)

114 points by andy_xor_andrew 3 years ago | 48 comments

Microsoft rewrote Q# compiler in Rust(github.com)

53 points by avestura 3 years ago | 38 comments

Microsoft Python Driver for SQL Server(github.com)

64 points by kermatt 1 year ago | 25 comments

Show HN: Lance – Alternative to Parquet for ML data(github.com)

55 points by chop 3 years ago | 14 comments

Show HN: Prompts as WASM Programs(github.com)

180 points by mmoskal 2 years ago | 34 comments

Independent Guest Virtual Machine (IGVM) File Format(github.com)

20 points by ingve 9 months ago | 2 comments

CatalaLang/catala: Programming language for law specification(github.com)

420 points by gorenb 3 years ago | 251 comments

GitHub repository for Catala, a programming language for literate programming of law specifications, such as tax and benefits legislation.

AI Agent Guidelines for CS336 at Stanford(github.com)

480 points by prakashqwerty 4 months ago | 148 comments

A CLAUDE.md file in Stanford CS336's assignment repository giving guidelines for AI coding assistants working with students on the course.

Train Your Own LLM from Scratch(github.com)

376 points by kristianpaul 5 months ago | 43 comments

GitHub repository by angelos-p providing code and docs for training your own large language model from scratch.

Type Server Protocol(github.com)

127 points by adamnemecek 2 hours ago | 86 comments

GitHub-hosted specification document for Microsoft's Type Server Protocol, a JSON-RPC protocol built on LSP conventions for querying Python type analysis data.

Heretic: Automatic censorship removal for language models(github.com)

705 points by melded 11 months ago | 339 comments

GitHub repository for Heretic, an AGPL-licensed tool for fully automatic censorship removal (abliteration) in transformer language models.

Training LLMs from ground zero as a startup(yitay.net)

360 points by swyx 2 years ago | 92 comments

Yi Tay's blog post on the experience of training large language models from scratch at a startup (Reka), covering compute, infrastructure, and lessons learned.