ClaimsDario Amodei

“A serious moral accounting on AI can't trust their self-reports, since we might accidentally train them to pretend to be okay when they aren't.”

Dario Amodei 18 February 2025 The Urgency of Interpretability (darioamodei.com) archived copy

Not checkable

A serious moral accounting on AI can't trust their self-reports, since we might accidentally train them to pretend to be okay when they…

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

Dario Amodei, “A serious moral accounting on AI can't trust their self-reports, since we might accidentally train them to pretend to be okay when they…” (said 18 February 2025). Verdict: not checkable. Reliability API, claim c_24cc98083125, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_24cc98083125

This claim is in dataset release v1.1.2, with the same verdict.

Reply to this claim

For Dario Amodei, or someone speaking for them: a correction or counter-evidence. Replies are read before anything is shown; an approved reply shows your name, role, date, statement and link. Your email address is never shown and is deleted 30 days after the decision (privacy).

Verdicts are made automatically; how verdicts are made.