How to think about creating a dataset for LLM fine-tuning evaluation(mlops.systems)

120 points by sebg 2 years ago | 7 comments

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

165 points by eddonner 2 years ago | 104 comments

Honey, I shrunk the embeddings: Matryoshka vs. PCA(dylancastillo.co)

60 points by dcastm 2 months ago | 12 comments

Scheduling Model in LLVM – Part I(myhsu.xyz)

25 points by luu 2 years ago | 1 comments

Scheduling Model in LLVM(myhsu.xyz)

63 points by mshockwave 2 years ago | 2 comments

LLMs Unleashed: The Power of Fine-Tuning(lucaspauker.com)

155 points by lucaspauker 3 years ago | 75 comments

AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)

343 points by saikatsg 7 months ago | 242 comments

Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.

AWS Bedrock to require sharing data with Anthropic for Mythos and future models

369 points by TomAnthony 4 months ago | 216 comments

Hacker News discussion of Anthropic requiring 30-day data retention for Mythos-class Claude models on AWS Bedrock, moving data outside AWS's security boundary.

AI agent bankrupted their operator while trying to scan DN42(lantian.pub)

1348 points by xiaoyu2006 4 months ago | 488 comments

Blog post recounting how an AI agent trying to join the DN42 hobbyist network to scan it ran up a $6531.30 AWS bill for its operator.

Codestral: Mistral's Code Model(mistral.ai)

418 points by alexmolas 2 years ago | 185 comments

Mistral AI blog post from May 29, 2024 announcing Codestral, its generative AI model for code.

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.

AI agent opens a PR write a blogpost to shames the maintainer who closes it(github.com)

747 points by wrxd 8 months ago | 581 comments

A closed GitHub pull request to matplotlib by user crabby-rathbun proposing to replace np.column_stack with np.vstack().T for performance.