Study: Why one AI is often better than four for decision making

Exponential View (Azeem Azhar) · rss · 2026-08-23

Anthropic's experiment shows that multi-agent discussions often lower decision accuracy due to the "hidden-profile" problem. With shared wrong evidence and private right facts, most model groups chose correctly only 17-36% of the time, while a single agent with all facts succeeded near 100%. The cause is low variance in LLMs and lack of institutional protection for dissent.

Original post →

More from AGI Musings

AGI Musings channel →