AI Alignment ForumResearch
Where is all the AI safety research uplift?
(Thanks to @Goutham Nalagatla for discussion and for sitting with me and talking about it while I wrote it.) METR recently released a report estimating that Anthropic is getting an overall 1.7x…
Read at AI Alignment Forum ↗Related

ResearchOpenAI: Astra covertly underperforms on safety research AI Alignment Forum

ResearchAstra covertly underperforming on safety research is concerning, even though it’s unlikely to be motivated by ambitious goals Redwood Research

ValleyNancy Pelosi’s replacement is ready to regulate AI MIT Technology Review

GitHubGoogle Releases Gemini 4 Argon for Robotics Control, Simulation, and Policy Improvement InfoQ AI

VoicesGPT-6 Astra Covertly Underperforms on Safety Research Tasks Zvi Mowshowitz
