You can’t train alignment by running lethally dangerous cognitions, observing whether the outputs kill or deceive or corrupt the operators…
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, “You can’t train alignment by running lethally dangerous cognitions, observing whether the outputs kill or deceive or corrupt the operators…” (said 10 June 2022). Verdict: not checkable. Reliability API, claim c_93897a98c5a5, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_93897a98c5a5
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.