korrents
Ryan Greenblatt

What Ryan Greenblatt thinks about reinforcement learning

@ryan-greenblatt · 26 positions · On ppll ↗

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.

Filter reinforcement learning · Newest first
Topic
All 26AI alignment 13scaling laws 5AGI 2AI agents 2Anthropic 2recursive self-improvement 2reinforcement learning 2AI and jobs 1mathematics 1
2 more topics
politics 1robotics 1
Sort
NewestOldest

Only Ryan Greenblatt on reinforcement learning. See everyone on reinforcement learning

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 readingToday's RL environments are better than 2024's because we learned what to build and put AI labour on building it, not because labs hired more human experts.

    Their wordsthe reason why RL environments today are much better than they were in like you know 2024 is not that much because um we have hired way more human experts to make RL environments and is instead much more because we better know what how RL like what RL environments we even want to make and and like how we should structure them and also we're using huge amounts of AI labor to build RL environments.

    ↗Ryan Greenblatt – What happens once AI can automate AI research?youtube.com 6th of 26 in this recording

  3. Our readingIf whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see.

    Their wordsOne concern you might have is there are like large categories of reward hacks which humans can't detect well and which we consistently fail to detect and which consistently get reinforced and then this category is sufficient to cause the most natural behavior for the AI to learn to be like cheat when the humans can't find out

    ↗Ryan Greenblatt – What happens once AI can automate AI research?youtube.com 23rd of 26 in this recording