ClaimsEliezer Yudkowsky

“This is sufficient on its own, even ignoring many other items on this list, to trash entire categories of naive alignment proposals which assume that if you optimize a bunch on a loss function calculated using some simple concept, you get perfect inner alignment on that concept.”

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

Not checkable

This is sufficient on its own, even ignoring many other items on this list, to trash entire categories of naive alignment proposals which…

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, “This is sufficient on its own, even ignoring many other items on this list, to trash entire categories of naive alignment proposals which…” (said 10 June 2022). Verdict: not checkable. Reliability API, claim c_bed73b42b010, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_bed73b42b010

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.