korrents
Noam Brown

What Noam Brown thinks about scaling laws

@noam-brown · 18 positions · On ppll ↗

Research scientist at OpenAI, who built the poker AIs Libratus and Pluribus and helped pioneer test-time compute and reasoning in language models.

Noam Brown 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 scaling laws · Newest first
Topic
All 18benchmarks 8scaling laws 8LLMs 6AGI 1AI alignment 1AI and science 1mathematics 1physics 1taste 1
Sort
NewestOldest

Only Noam Brown on scaling laws. See everyone on scaling laws

8 dated positions, 2026, in their own words. Our reading of what Noam Brown has said — not written or endorsed by them.

  1. Our readingA model's capability is now a function of how much money you spend on it, so asking what a model can do means nothing until you name a budget.

    Their wordsThe problem is we're in a world now where the capability of the model is a function of how much money you put into it. Basically, if you give it a budget of $10,000, it can do a lot more than what it can do with a budget of $10. Give it a budget of $10 million, you can do even more. At what budget should you evaluate these models? The policies that exist today don't really address that question.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 1st of 18 in this recording

  3. Our readingModel comparisons understate real progress, because benchmark tables do not control for how much test-time compute each answer used.

    benchmarks

    Their wordsI think the reason why it doesn't show up as so much better on the benchmarks is because the benchmarks are being presented, the benchmark results are being presented in the wrong way. They're not controlling for the amount of test time compute that is being used on that benchmark question.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 2nd of 18 in this recording

  5. Our readingRunning a model until its performance plateaus is no longer a usable evaluation rule, because a well-scaffolded model keeps improving for weeks.

    benchmarks

    Their wordsBut what we're seeing today with the modern models is that 5.5 and other models can think for if you scaffold them reasonably well, can think for weeks even um before having performance plateau on some of these benchmarks. And so, the point at which they plateau is simply too far out to reasonably test.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 3rd of 18 in this recording

  7. Our readingA benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.

    benchmarks

    Their wordsmy claim is the proper way to evaluate the models now is you either have some kind of budget for the benchmark whether it's tokens or cost or time or whatever or you plot the performance as a function of the amount of test time compute that's going into the model

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 4th of 18 in this recording

  9. Our readingRunning a model five times and keeping the best answer buys a higher benchmark score without buying a better model.

    benchmarks

    Their wordsUm so if you say okay well we're going to instead of just running this model once we're going to run it five times and take the best of the five responses or like ask a judge which one it thinks is best then you can get much higher scores than that model. And so it's really easy to make something that looks a lot better on paper but is actually not better once you control for the amount of test time compute.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 5th of 18 in this recording

  11. Our readingThe safety frameworks the labs publish do not account for how much test-time compute a dangerous-capability evaluation was given.

    Their wordsthe preparedness frameworks and responsible scaling policies, they don't really account for the amount of test time compute.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 7th of 18 in this recording

  13. Our readingExtra thinking time cannot help with factual recall: a model that does not know a date will not know it after a week either.

    Their wordsif you ask a person when was Abraham Lincoln born and they don't know the date. They could sit there, they could think about it for a week, if they if they don't have access to Wikipedia or something, they're not going to be able to do better answering that question if they thought about it for a week compared to 5 seconds. Same with the model.

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 12th of 18 in this recording

  15. Our readingThere will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck.

    Their wordsand I don't think we're headed to that world largely because of the fact that the models rely so much on large scale test time compute in order to achieve um their greatest intelligence. If you if it requires so much test time on compute to unlock the full capabilities of the model, then that means you're bottlenecked by time

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com 15th of 18 in this recording