So large language models will change their preferences as they get smarter.
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, “So large language models will change their preferences as they get smarter.” (said 6 April 2023). Verdict: not checkable. Reliability API, claim c_f9439a59535b, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_f9439a59535b
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.