Hacker Newsnew | past | comments | ask | show | jobs | submit | rarpa's commentslogin

> There is genuine research into latent space monitoring and interpretation

That's great but the sentiment that CoT isn't useful for monitoring doesn't seem to be shared by mech interp researchers like Nanda.

Also: https://arxiv.org/abs/2507.11473



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

Search: