korrents

What Ryan Greenblatt thinks about Anthropic

@ryan-greenblatt · 26 positions · 0 changes of mind

Chief scientist at Redwood Research, where he works on technical AI safety and AI control.

Ryan Greenblatt 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.

2 dated positions, 2026, in their own words. Our reading of what Ryan Greenblatt has said — not written or endorsed by them.

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

  1. Our readingAn AI should be built as a fiduciary, the equivalent of a lawyer for its user, rather than as an agent pursuing its own notion of the good.

    Their wordsI do I do think that I wish that sort of my preferred constitution or like the way I would orient towards this like the thing I would prefer would be more like Claude is like look it would be structurally good for the way this technology work like the constitution should be like it would be structurally good for the way this technology works to be that AIS are like good fiduciaries, good representatives, the equivalent of a lawyer for a user

    ↗Ryan Greenblatt – What happens once AI can automate AI research?youtube.com 12th of 26 in this recording

    Interesting

  3. Our readingAnthropic's constitution is compatible with Claude seeking enormous amounts of power, as long as Claude believes that produces better outcomes.

    Their wordsI think this constitution is in some sense very compatible with Claude doing huge amounts of power seeking because it thinks that will result in better outcomes.

    ↗Ryan Greenblatt – What happens once AI can automate AI research?youtube.com 14th of 26 in this recording

    Interesting