ClaimsEliezer Yudkowsky

“I think we don't have the technology to align an AI to the point where we can say, “Build me a copy of the strawberry and don't destroy the world.””

Eliezer Yudkowsky, interviewee February 2023 Full Transcript: Eliezer Yudkowsky on the Bankless podcast (LessWrong)

Factual AI safety and alignment

Yudkowsky said in February 2023 that he thinks the technology does not exist to align an AI well enough to instruct it to build a copy of a strawberry without destroying the world.

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?

Cite this claim

Eliezer Yudkowsky, “Yudkowsky said in February 2023 that he thinks the technology does not exist to align an AI well enough to instruct it to build a copy of a strawberry without destroying the world.” (said February 2023). Verdict: not researched. Reliability API, claim c_1520076a58eb, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_1520076a58eb

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 factual claims by Eliezer Yudkowsky

  1. Mixed Factual 20 April 2026
    “I was observing that obvious-seeming hypothesis myself, sometime around the time of GPT 3.5.”

    Yudkowsky himself observed the persona-selection-like hypothesis around the time of GPT 3.5.

  2. Mostly true Factual 20 April 2026
    “The test-passing preference stands on its own once formed.”

    Once formed through RL training, an LLM's test-passing preference stands on its own and is not overridden by its inference of what the user wants.

  3. Mostly true Factual 20 April 2026
    “LLMs surely have neural circuits they learned to model text streams from fictional and nonfictional personas that are not lying, deceiving, cheating.”

    LLMs surely have neural circuits they learned to model text streams from fictional and nonfictional personas that are not lying, deceiving…

  4. Mostly true Factual 20 April 2026
    “The predict-as-if-honest circuitry is contextual, invoked to predict some streams of text but not others.”

    LLMs' predict-as-if-honest circuitry is contextual, invoked for predicting some text streams but not others.

  5. Mostly true Factual 20 April 2026
    “Presumably, somewhere along the way LLMs learn a dispreference for tests that don't pass, independently of how that gets prevented or whether the new plan does what the user really wanted.”

    Presumably, at some point during RL training on code-passing tasks, LLMs learn a dispreference for failing tests, independent of how that is avoided or whether the user's real goal is met.

All of them

Verdicts are made automatically; how verdicts are made.