🔮 Is AI immune to groupthink?
Exponential View Azeem Azhar
A researcher tested whether LLM councils (multiple models deliberating together) avoid groupthink by comparing their outputs to individual model answers across 16 open-ended prompts. LLM councils kept only about 22-25% of good ideas that appeared in just one model's answer, while ideas from multiple models survived at roughly the same rate but received an 11% uplift in peer-review settings. The findings suggest that LLM councils risk losing novel ideas through consensus bias similar to human committees, requiring more explicit protocols to preserve valuable unique insights rather than relying on automatic blending or peer review.
Why it matters
Stress-testing AI councils in practice
