korrents
Buck Shlegeris

What Buck Shlegeris thinks about AI agents

@buck-shlegeris · 8 positions · On ppll ↗

CEO of Redwood Research, where he works on AI control: making sure a powerful model cannot cause a catastrophe even if it is misaligned and trying to.

Buck Shlegeris 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 AI agents · Newest first
Topic
All 8AI alignment 8AI agents 2AGI 1cybersecurity 1LLMs 1
Sort
NewestOldest

Only Buck Shlegeris on AI agents. See everyone on AI agents

2 dated positions, 2024, in their own words. Our reading of what Buck Shlegeris has said — not written or endorsed by them.

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

  1. Our readingRisk from a scheming model should be managed the way insider security risk is: assume some of them are compromised and stay safe anyway.

    AI alignment

    Their wordsWe're advocating that companies handle risk from scheming models in a similar way–striving to ensure that they'll be safe even if their alignment efforts fail to prevent models from scheming.

    ↗The case for ensuring that powerful AIs are controlledredwoodresearch.substack.com 5th of 8 in this piece

  3. Our readingControl is a fundamentally limited approach that stops working on sufficiently powerful models, so alignment is still needed in the end.

    AI alignment

    Their wordsAI control (with only black-box techniques) seems like a fundamentally limited approach.

    ↗The case for ensuring that powerful AIs are controlledredwoodresearch.substack.com 8th of 8 in this piece