xuanming zhang

🧵 1/ The rise of open-weight LLMs and platforms like HuggingFace raises interesting questions about the relationships between such models. Given a pair of models (i.e. Llama 1 vs Vicuna or Llama 3 vs Llama 2) what can we say about whether they were trained independently?

I ditched Cursor for Claude Code and it's absolutely insane 🤯 $1000s of API credits for just $100-200/month AND way better at following instructions My complete guide to 10x your coding with Claude Code:

Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team @tatsu_hashimoto @marcelroed @neilbband @rckpudi. Researchers are becoming detached from the technical details of how LMs work. In CS336, we try to fix that by having students build everything:

This world is full of heroes, and what we need to think about is how to use them for our benefit; if not, they are opponents, and what we need to do is just to do our best. Welcome to exchange and cooperate!