It's hard to talk about this without using words that imply intentionality, but we don't think the models are intentionally doing this.
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
Daniela Amodei, “It's hard to talk about this without using words that imply intentionality, but we don't think the models are intentionally doing this.” (said 2022). Verdict: not checkable. Reliability API, claim c_b6d4465ef077, method 0.1.0+28da144b, dataset release v1.1.2. https://epistacklabs.com/claims/c_b6d4465ef077
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.