Combining multiple AI models' outputs into one final answer tends to discard most of the good ideas that only one model produced.

Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Authors should treat peer review as a test run before a select, hand-picked audience. SHSuzana Herculano-Houzel25 Apr 2024peer review
• Fear of strong AI models killing everyone was not based on peer-reviewed research showing high doom odds, nor indicated by market prices. TCTyler Cowen26 Sept 2026peer review
• Fraudulent papers pass peer review routinely, which is direct evidence that peer review does not do the job it is supposed to do. AMAdam Mastroianni13 Dec 2022peer review
• History has a reproducibility problem worse than science’s replication crisis, because hardly anyone ever goes back to the sources to check what a historian claimed they say. AHAnton Howes29 Aug 2023peer review
• Needing a reviewer's approval before an idea counts for anything makes scientists worse at thinking, and costs the field its most unusual ideas. AMAdam Mastroianni13 Dec 2022peer review

See this claim on the map