ClaimsEliezer Yudkowsky

“I have various friends who report”

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

Factual AI policy and governance

Friends of Eliezer Yudkowsky report that OpenAI researchers are very worried about AI risk in private but say they cannot be that worried in public.

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

Private reports from friends about private statements by OpenAI researchers can't be independently verified.

Cite this claim

Eliezer Yudkowsky, “Friends of Eliezer Yudkowsky report that OpenAI researchers are very worried about AI risk in private but say they cannot be that worried in public.” (said February 2023). Verdict: own records only. Reliability API, claim c_949971e65948, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_949971e65948

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.