I see the AI is lying, and it’s obviously just an artifact of the training process.
Not checkable An opinion, value judgement or statement with nothing to check.
Not checkable: An opinion, value judgement or statement with nothing to check. Not scored.
Cite this claim
Scott Alexander, “I see the AI is lying, and it’s obviously just an artifact of the training process.” (said 3 April 2025). Verdict: not checkable. Reliability API, claim c_251cc4ba1694, method 0.1.0+8bea457b, dataset release v1.1.2. https://epistacklabs.com/claims/c_251cc4ba1694
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
Verdicts are made automatically; how verdicts are made.