ClaimsEliezer Yudkowsky

“AI-boxing can only work on relatively weak AGIs; the human operators are not secure systems.”

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

Not checkable

AI-boxing can only work on relatively weak AGIs; the human operators are not secure systems.

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, “AI-boxing can only work on relatively weak AGIs; the human operators are not secure systems.” (said 10 June 2022). Verdict: not checkable. Reliability API, claim c_046cb5d83b14, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_046cb5d83b14

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.