ClaimsEliezer Yudkowsky

“Many alignment problems of superintelligence will not naturally appear at pre-dangerous, passively-safe levels of capability.”

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

Not checkable

Many alignment problems of superintelligence will not naturally appear at pre-dangerous, passively-safe levels of capability.

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, “Many alignment problems of superintelligence will not naturally appear at pre-dangerous, passively-safe levels of capability.” (said 10 June 2022). Verdict: not checkable. Reliability API, claim c_3120942dc618, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_3120942dc618

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.