korrents

Our readingWhat is a korrent?

RLHF probably helps mostly because it is much easier for people to judge outputs than to produce them.

Drawn from what Andrej Karpathy said

What this subject means

reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.

What Andrej Karpathy actually said

  1. Andrej Karpathy Founding member of OpenAI and former director of AI at Tesla
    my best guess is that this is possibly mostly due to the discriminator generator Gap what that means is that in many cases it is significantly easier to discriminate than to generate for humans

    Watch from 2:58:47 plays here

    ↗Deep Dive into LLMs like ChatGPTyoutube.com

    5 Feb 2025 · video · 3h 31m · spoken · machine transcript

    All 25 korrents from this recordingthis one is 15th

Added to korrents 8 Nov 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