ClaimsEliezer Yudkowsky

“No, no, not yet, not now. Nobody’s being careful and deliberate now, but maybe at some point in the indefinite future people will be careful and deliberate.”

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 safety and alignment

As of April 2023, AI developers are not being careful and deliberate in designing AI systems.

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, “As of April 2023, AI developers are not being careful and deliberate in designing AI systems.” (said 6 April 2023). Verdict: not researched. Reliability API, claim c_831f61b13dba, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_831f61b13dba

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.