korrents

Our readingWhat is a korrent?

Models hallucinate because in their training data questions like "who is X" are always answered confidently, so they imitate that confident style.

Drawn from what Andrej Karpathy said

LLMs

What Andrej Karpathy actually said

  1. Andrej Karpathy Founding member of OpenAI and former director of AI at Tesla
    the model statistically imitates is training set in the training set the questions of the form who is blah are confidently answered with the correct answer and so it's going to take on the style of the answer and it's going to do its best

    Watch from 1:22:40 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 3rd

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