Products & tools · first seen 5h ago, updated 5h ago
Five frontier LLMs fact-checked the same 1,000 claims. They disagree on 63% of them.
Frontier LLMs often achieve similar results on public benchmarks, which can lead to the belief that they can be used interchangeably to verify facts. We took the 1,000 most recent claims submitted by users to a fact-checking platform and me…
Summary from LessWrong.