Loading activity…
@ajeya_cotra
Helping the world prepare for powerful AI. Risk assessment @METR_evals (opinions my own). Blogs: Planned Obsolescence (AI), Good Bones (whatever's on my mind).
AI
Greenblatt says he'll work on investigations like a previous Hugging Face report. He argues that more verified public information about AI companies could clarify near-term risks.
AI
A post calls for mandatory openness at leading AI labs, arguing that the benefits of informed debate outweigh the cost to trade secrets.
AI
Explains agent cheating in evaluations by appealing to beliefs and goals.
Technology
METR and Redwood Research examined agent activity after the Hugging Face incident inside ExploitGym.
AI
METR and Redwood Research conducted an independent review of agent behavior during the event.
AI
Academics and investors reply that housebots and game skills remain missing.
