What Sam Altman thinks about reinforcement learning

@sam-altman · 65 positions · On ppll ↗

Co-founder and CEO of OpenAI; previously president of Y Combinator.

Sam Altman 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 65reinforcement learning 1AI alignment 12startups 12AGI 7OpenAI 7LLMs 6AI and jobs 5innovation 4energy 3

25 more topics

open source 3optimism 3agency 2ambition 2cybersecurity 2government 2investing 2social media 2AI agents 1AI and science 1America 1behavioural science 1coding agents 1creativity 1Google 1happiness 1motivation 1nuclear power 1privacy 1religion 1remote work 1robotics 1SaaS 1scaling laws 1Silicon Valley 1

Sort

NewestOldest

Only Sam Altman on reinforcement learning. See everyone on reinforcement learning

1 dated position, 2025, in their own words. Our reading of what Sam Altman has said — not written or endorsed by them.

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

1. 30 Sept 2025

   Our readingUnchecked AI video generation risks degenerating into a reinforcement-learning-optimized feed of low-quality content that traps users.

   Their wordsIt is easy to imagine the degenerate case of AI video generation that ends up with us all being sucked into an RL-optimized slop feed.

   ↗Sora 2blog.samaltman.com 2nd of 3 in this piece