korrents
Eliezer Yudkowsky

What Eliezer Yudkowsky thinks about AGI

@eliezer-yudkowsky · 10 positions · On ppll ↗

Co-founder of the Machine Intelligence Research Institute and the writer who started the modern argument that a sufficiently capable AI would by default kill everyone. Has argued the case since the early 2000s, latterly with the conclusion that it is being lost.

Eliezer Yudkowsky did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter AGI · Newest first
Topic
All 10AI alignment 6AGI 4LLMs 1neural networks 1
Sort
NewestOldest

Only Eliezer Yudkowsky on AGI. See everyone on AGI

4 dated positions, 2022, in their own words. Our reading of what Eliezer Yudkowsky has said — not written or endorsed by them.

4 positions so far — this page is not yet offered to search engines.

  1. Our readingAlignment has to be right on the first try at a dangerous level of capability, because failing at that level leaves nobody to try again.

    AI alignment

    Their wordsunaligned operation at a dangerous level of intelligence kills everybody on Earth and then we don’t get to try again.

    ↗AGI Ruin: A List of Lethalitiesintelligence.org 2nd of 10 in this piece

  3. Our readingAlignment failures that matter will not show up at safe capability levels, because the reason to hide misbehaviour only exists once hiding it pays.

    AI alignment

    Their wordsMany alignment problems of superintelligence will not naturally appear at pre-dangerous, passively-safe levels of capability.

    ↗AGI Ruin: A List of Lethalitiesintelligence.org 5th of 10 in this piece

  5. Our readingNo observation of a model's behaviour can establish that it is aligned, because a model capable enough to be dangerous is capable enough to produce whatever behaviour it is being watched for.

    Their wordsA strategically aware intelligence can choose its visible outputs to have the consequence of deceiving you, including about such matters as whether the intelligence has acquired strategic awareness

    ↗AGI Ruin: A List of Lethalitiesintelligence.org 8th of 10 in this piece

  7. Our readingThere is no written plan for surviving AGI, and a world that was going to survive would have had one decades ago.

    Their wordsSurviving worlds, by this point, and in fact several decades earlier, have a plan for how to survive.

    ↗AGI Ruin: A List of Lethalitiesintelligence.org 10th of 10 in this piece