ClaimsDario Amodei

“One of the things I think is very important is we should never train for interpretability because that's taking away that advantage.”

Dario Amodei 8 August 2023 Dario Amodei (Anthropic CEO) - $10 Billion Models, OpenAI, Scaling, & AGI in 2 years (Dwarkesh Podcast)

Not checkable

One of the things I think is very important is we should never train for interpretability because that's taking away that advantage.

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, “One of the things I think is very important is we should never train for interpretability because that's taking away that advantage.” (said 8 August 2023). Verdict: not checkable. Reliability API, claim c_75bc61b54e59, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_75bc61b54e59

This claim is in dataset release v1.1.2, with the same verdict.

Reply to this claim

For Dario Amodei, or someone speaking for them: a correction or counter-evidence. Replies are read before anything is shown; an approved reply shows your name, role, date, statement and link. Your email address is never shown and is deleted 30 days after the decision (privacy).

Verdicts are made automatically; how verdicts are made.