Usman Anwar

@usmananwar391

Deep Learning & AI Safety @Cambridge_uni

following
followers

New paper explores evaluation awareness and monitoring latent beliefs through chain-of-thought

A coauthor shares the paper and links to an arXiv page and a related blog post.

2 Sources, 20d ago, first seen 20d ago

Sharing AI safety training environments rather than banning open source

The proposal asks leading AI companies to share training environments built around pro-prosperity and pro-democratic values, without requiring them to share models or computing power.

53 Sources, 17d ago, updated 17d ago

Featured in

New paper explores evaluation awareness and monitoring latent beliefs through chain-of-thought

Sharing AI safety training environments rather than banning open source

Featured in

New paper explores evaluation awareness and monitoring latent beliefs through chain-of-thought

Sharing AI safety training environments rather than banning open source