ClaimsEliezer Yudkowsky

“No. I’m going on reports that normal people are more willing than the people I’ve been previously talking to, to entertain calls that this is a bad idea and maybe you should just not do that.”

Eliezer Yudkowsky, interviewee 6 April 2023 Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality (Dwarkesh Podcast) archived copy

Factual AI policy and governance

No one in government has reached out to Eliezer Yudkowsky in a way suggesting they have the broad contours of the AI risk problem right.

Own records only Only the person's or their organisation's own records speak to it, so it is not scored.

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

Reasoning

Depends on private contacts between government and Yudkowsky.

Cite this claim

Eliezer Yudkowsky, “No one in government has reached out to Eliezer Yudkowsky in a way suggesting they have the broad contours of the AI risk problem right.” (said 6 April 2023). Verdict: own records only. Reliability API, claim c_1862902df272, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_1862902df272

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.