
Long Horizon Agents, State of MCPs, Meta's AI Glasses & Geoffrey Hinton is a LOVE RAT - EP99.17
This Day in AI Podcast
00:00
Anthropic Routing & Long-Horizon Execution
Hosts unpack Anthropic's routing/post-mortem and discuss 'The Illusion of Diminishing Returns' paper: model routing, degradation, and why execution over long horizons (supervisory agents, compounding errors) is the key bottleneck for autonomous agents.
Transcript
Play full episode