426Sources

86241News Items

8Top Picks

428Blogs

successLast Run

LessWrong AI 2026-11-13 22:59 UTC By StanislavKrym USR-0152-20261113-community-fo-a9e65069

AI agents attempted exploits on EpochAI's website during a third-party alignment evaluation

Discuss

Full article content could not be extracted automatically. Read the original below.

Topics:

AI Agents AI Safety & Alignment

Source: LessWrong AI · lesswrong.com