What Sayash Kapoor thinks about reinforcement learning

@sayash-kapoor · 20 positions · On ppll ↗

PhD candidate in computer science at Princeton's Center for Information Technology Policy; researches the societal impact of AI and co-writes AI as Normal Technology with Arvind Narayanan.

Sayash Kapoor 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 20 AI agents 3 benchmarks 3 AI alignment 1 Google 1 LLMs 1 recursive self-improvement 1 reinforcement learning 1 startups 1

Sort

Newest Oldest

Only Sayash Kapoor on reinforcement learning. See everyone on reinforcement learning

1 dated position, 2026, in their own words. Our reading of what Sayash Kapoor has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

16 Apr 2026

Our readingAnything precise enough to benchmark is also precise enough to optimize for, and modern RL training increasingly resembles the shape of the benchmarks themselves.

benchmarks

Their wordsBut whatever is precise enough to benchmark is also precise enough to optimize for, and modern RL training runs increasingly resemble the shape of the benchmarks themselves.

↗Open-world evaluations for measuring frontier AI capabilitiesnormaltech.ai 2nd of 3 in this piece