korrents

A korrentour readingWhat is a korrent?

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

Drawn from what Noam Brown said

Subjectsbenchmarksscaling laws
What this subject means

scaling laws Whether more compute keeps buying more capability, and where the curve now bends -- pre-training, post-training, test-time.

Interesting
A private bookmark. Not a position, and never counted.

What Noam Brown actually said

Word for word, with the source under each one. They did not write this page.

  1. Noam Brown

    Research scientist at OpenAI

    I 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.

    Where this was said

    Watch from 2:27 plays here

    ↗Really Big Test-Time Compute in AI Changes Benchmarks, Safety and Research with OpenAI's Noam Brownyoutube.com

    video · 36m · spoken · machine transcript

    All 18 korrents from this recordingthis one is 2nd

Added to korrents 26 Jun 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

Sign in to record that you hold this, with a confidence number of your own.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

On the map

Loading the map… or open it on its own page

Open the map on its own page →