It’s basically a form of self-play. You’re training the model against itself.
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
Dario Amodei, “It’s basically a form of self-play. You’re training the model against itself.” (said 11 November 2024). Verdict: not checkable. Reliability API, claim c_2659ff1bf147, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_2659ff1bf147
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.