ClaimsDario Amodei

“As with most things, when we actually train a model to be aligned, we don't know what happens inside the model.”

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

Factual AI safety and alignment

When a model is trained to be aligned, researchers do not know what happens inside the model.

Not researched Checkable, but outside the sample that was researched.

Factual: Statements about the present or the past, checked against the record: did they hold up?

Said for an organisation they lead or work for; it counts on both records.

Cite this claim

Dario Amodei, “When a model is trained to be aligned, researchers do not know what happens inside the model.” (said 8 August 2023). Verdict: not researched. Reliability API, claim c_02f55d7af9d2, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_02f55d7af9d2

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).

More factual claims by Dario Amodei

  1. Mostly true Factual 28 February 2025
    “So we did this experiment where we basically train the model to be all the good thing, helpful, honest, harmless, friendly.”

    Anthropic ran an experiment training a model to be helpful, honest, harmless and friendly.

  2. Resolved true Factual 28 February 2025
    “They're not yet at the stage where we think that there is a real and meaningful increase in the threat end to end,”

    Anthropic assessed that Claude 3.7 Sonnet is not yet at a stage giving a real and meaningful end-to-end increase in dangerous threat capability.

  3. Resolved true Factual 28 February 2025
    “10 to 25% referred to the chance of civilization getting substantially derailed, right?”

    Amodei's earlier 10 to 25% figure referred to the chance of civilization getting substantially derailed.

  4. Mostly true Factual 18 February 2025
    “this lack of understanding is essentially unprecedented in the history of technology.”

    The lack of understanding of how AI systems work is essentially unprecedented in the history of technology.

  5. Mostly true Factual 18 February 2025
    “We were able to provide a strong theoretical basis for having conviction that superposition was the right hypothesis to pursue.”

    Amodei said that "we" were able to provide a strong theoretical basis for having conviction that superposition was the right hypothesis to pursue; the surrounding text does not say who "we" refers to.

All of them

Verdicts are made automatically; how verdicts are made.