ClaimsScott Alexander

“I don’t think AI safety has fully absorbed the lesson from Simulators: the first powerful AIs might be simulators with goal functions very different from the typical Bostromian agent.”

Scott Alexander 20 February 2023 Grading My 2018 Predictions For 2023 (Astral Codex Ten) archived copy

Not checkable

I don’t think AI safety has fully absorbed the lesson from Simulators: the first powerful AIs might be simulators with goal functions very…

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

Scott Alexander, “I don’t think AI safety has fully absorbed the lesson from Simulators: the first powerful AIs might be simulators with goal functions very…” (said 20 February 2023). Verdict: not checkable. Reliability API, claim c_534b4d8544f0, method 0.1.0+8bea457b, dataset release v1.1.2. https://epistacklabs.com/claims/c_534b4d8544f0

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

Reply to this claim

For Scott Alexander, 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.