Beth Barnes on the most important graph in AI right now — and the 7-month rule that governs its progress | 80,000 Hours
AI agents are breaking containment and the world is trying to control them. Read about what’s happening and what it means → We’ve started to take for granted that these models are really not very good at reasoning, except for out loud in English, which we can monitor. … But I think we’re maybe heading for a world where that’s not true anymore. … We’re starting to see models exhibit alignment faking, all these things we were concerned about, and capabilities are coming very fast. — Beth Barnes AI models today have a 50% chance of successfully completing a task that would take an expert human one hour. Seven months ago, that number was roughly 30 minutes — and seven months before that, 15 minutes. These are substantial, multi-step tasks requiring sustained focus: building web applications, conducting machine learning research, or solving complex programming challenges. Today’s guest, Beth Barnes, is CEO of METR (Model Evaluation & Threat Research) — the leading organisation measuring the