Sabotage evaluations for frontier models \ Anthropic - discu.eu

Hacker News

Sabotage evaluations for frontier models https://www.anthropic.com/research/sabotage-evaluations 8 comments 20/10/2024

Linking pages

AI #87: Staying in Character - by Zvi Mowshowitz https://thezvi.substack.com/p/ai-87-staying-in-character 0 comments

Related searches:

Search whole site: site:anthropic.com

Search title: Sabotage evaluations for frontier models \ Anthropic

See how to search.

Submit link to: