korrents

Our readingWhat is a korrent?

Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs.

Drawn from what Jeff Dean said

What these subjects mean

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

AI agents Agents beyond the editor: software that acts on your behalf, and what independence it should be given.

What Jeff Dean actually said

  1. Jeff Dean Chief Scientist at Google DeepMind and Google Research
    Um, and that's a very very useful general technique is you know inference time compute to perform search over plausible ways of solving the problem that can get much much higher performance or much more reliability in longunning agent flows.

    Watch from 24:10 plays here

    ↗Jeff Dean: The 1% Rule for Building in AIyoutube.com

    30 Jul 2026 · video · 57m · spoken · machine transcript

    All 22 korrents from this recordingthis one is 11th

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

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

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map