atallahw

We got access to OpenAI's RFT API with GPT5 and tried to see how good we could get it at one-shot Triton kernel generation. Some key decisions/observations: 1. tool use instead of multi-turn rl 2. skip SFT altogether 3. dataset curation was more important than dataset scale 4. reward hacks detection must be robust 5. models are getting a lot better at this

What did the account did the email actually come from? Was it legit from legal and he just submitted the request or was it a real spoofing

This was fun to work on. LLMs for writing kernels still has a long way to go. Its honestly a little surprising how decent they are now. I guess I've been pretty consistently "surprised" by codegen for a while now (meaning the last two years)