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
Verdicts are made automatically; how verdicts are made.