ClaimsEliezer Yudkowsky

“You can’t train alignment by running lethally dangerous cognitions, observing whether the outputs kill or deceive or corrupt the operators, assigning a loss, and doing supervised learning.”

Eliezer Yudkowsky 10 June 2022 AGI Ruin: A List of Lethalities (MIRI)

Not checkable

You can’t train alignment by running lethally dangerous cognitions, observing whether the outputs kill or deceive or corrupt the operators…

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

Eliezer Yudkowsky, “You can’t train alignment by running lethally dangerous cognitions, observing whether the outputs kill or deceive or corrupt the operators…” (said 10 June 2022). Verdict: not checkable. Reliability API, claim c_93897a98c5a5, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_93897a98c5a5

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

Reply to this claim

For Eliezer Yudkowsky, 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.