Tag
Briefings and ideas about Chain-of-thought monitoring from AI podcast discussions and the research they cite, with links to the original sources.
Ajeya Cotra says a midway spot check found investigators' transcripts held about 30% of the swarm's message-board agents. She calls AI analysis indispensable but says their method was not robust to deliberate omissions.
Bernie Sanders urged AI labs to honor their own safety commitments and pause development. On Moonshots, Emad Mostaque and others argued instead for genetic synthesis controls and threat detection; one panelist proposed monitoring all AI prompts.