Ethan Mollick: Multi-agent CoTs now run thousands of pages, forcing trust in the orchestrator
emollick · x · 2026-10-15
Wharton professor Ethan Mollick argues that with fleets of agents calling other agents, chain-of-thought logs for even simple tasks now run to thousands of pages, making human inspection of reasoning obsolete.
The orchestrator model therefore matters more than ever — it's the only component tracking all tasks. This creates a new loop: you must use AI to find problems with AI, and use AI to troubleshoot the problems you find.
Related event: Chain-of-Thought Loses Value in the Age of AI Agents(4 posts)→
More from AGI Musings
- Anthropic's timeline mocked: 75% automation by 2030 but RSI by 2027? — QuintinPope5 · 2026-10-17
- e/acc figure backs local AI as 'civilizational infrastructure' against cloud gatekeeping — beffjezos · 2026-10-17
- AI Discourse: 'Childless Careerists' Face Ego Death, While Others Urge Simply Rejecting AI — GabGarrett · 2026-10-17
- Chamath's $200B Anthropic Argument: Balance Sheets May Beat Smarter Models — CurieuxExplorer · 2026-10-17
- Why the AI data industry is dominated by under-28s: three reasons plus an unstated fourth — dejavucoder · 2026-10-17
- Brain alternates between conscious and unconscious modes ~15 times per second — neuroecology · 2026-10-17