
Silen Naihin
@silennai • 2,097 subscribers
Building verifiers for continuous improvement of AI @explabsai YC, AutoGPT, AI research (evals, opsd, interp)
Videos

Excited to open source our world-model-harness! `wmh` makes it easy to go from agent traces -> faithful replication of your production environment Basically, an LLM pretends to be a Docker container but 5x faster Below is a comparison running 8 SWE-bench tasks
Silen Naihin13,523 görüntüleme • 26 gün önce
Daha fazla içerik yok.