There’s the question of how on the current paradigm you train honesty when the humans can no longer tell if the system is being honest.
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, “There’s the question of how on the current paradigm you train honesty when the humans can no longer tell if the system is being honest.” (said 30 March 2023). Verdict: not checkable. Reliability API, claim c_ad2ce37166e9, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_ad2ce37166e9
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.