corp-drone
mikcl.bearblog.devยท20h
GPT-5 prompting guide
cookbook.openai.comยท1d
SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges
arxiv.orgยท10h
Run-time Steering Can Surpass Post-Training: Reasoning Task Performance
lesswrong.comยท13h
Loading...Loading more...