2026-05-28 12:52 UTC
"For 67% of real fact-checks, top AI models don't agree on the answer."
"34% of claims involve ... substantive disagreement on the answer, not just a calibration shift."
https://lenz.io/research/llm-disagreement
Replies (1)
-
@jacomyma@mas.to 2026-05-28 12:54
Link from Hacker News. Discussion there FYI: https://news.ycombinator.com/item?id=48307887