Hacker News new | past | comments | ask | show | jobs | submit login

Yes! This seems to be a really neat combination of 2010's Bayesian cleverness / Tenenbaumian program search approaches with the LLMs as merely sources of high-dim conditional distributions. I knew people were experimenting in this space (like https://escholarship.org/uc/item/7018f2ss) but didn't know it did so well wrt these new benchmarks.



Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: