ClaimsEliezer Yudkowsky

“Fast capability gains seem likely, and may break lots of previous alignment-required invariants simultaneously.”

Eliezer Yudkowsky, author 10 June 2022 AGI Ruin: A List of Lethalities (MIRI)

Prediction AI timelines and forecasting

Fast AI capability gains seem likely and may break many previous alignment-required invariants simultaneously.

Unresolvable The public record could not settle it.

Prediction: Statements about events outside the person's control, checked once they fell due: did they come true?

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

Reasoning

Open-ended prediction about future capability gains with no deadline and vague terms.

Cite this claim

Eliezer Yudkowsky, “Fast AI capability gains seem likely and may break many previous alignment-required invariants simultaneously.” (said 10 June 2022). Verdict: unresolvable. Reliability API, claim c_b88836c2fe8f, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_b88836c2fe8f

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

Reply to this claim

For Eliezer Yudkowsky, 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 prediction claims by Eliezer Yudkowsky

  1. Mostly false Prediction 6 April 2023
    “So probably Paul’s going to win, but slight moral victory.”

    Paul Christiano will probably win his forecast disagreement with Yudkowsky on an AI getting IMO gold by 2025, with prediction-market odds then running around 30%.

  2. Mixed Prediction 5 March 2024
    “Beating GPT-4 on GI just forces OpenAI to release 4.5.”

    If a rival AI developer beats GPT-4 on general intelligence, OpenAI will be forced to release GPT-4.5.

  3. Resolved false Prediction 6 April 2023
    “The current crop of people will not try it.”

    The current AI developers will not try the alignment approach he described (filtering training data to nice examples and training on it).

  4. Resolved true Prediction 6 April 2023
    “Alignment will not be solved in a few years.”

    AI alignment will not be solved within a few years.

  5. Resolved true Prediction 6 April 2023
    “even if GPT-5 doesn’t end the world, which I agree is like more than 50% of where my probability mass lies”

    GPT-5 will not end the world, with more than 50% of Yudkowsky's probability on that outcome.

All of them

Verdicts are made automatically; how verdicts are made.