korrents

A korrentour readingWhat is a korrent?

Spending most of the compute memorising the world in pre-training is brute force; what we want is a model that reasons the way a student sits an open-book exam.

Drawn from what Aravind Srinivas said

Subjectscaling 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 Aravind Srinivas actually said

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

  1. Aravind Srinivas

    Co-founder and CEO of Perplexity, an AI answer engine

    I think there’s an interesting thought experiment here that, we’ve been spending a lot of compute in the pre-training to acquire general common sense, but that seems brute force and inefficient. What you want is a system that can learn like an open book exam.

    Where this was said

    Watch from 1:12:57 plays here

    ↗Aravind Srinivas: Perplexity CEO on Future of AI, Search & the Internet | Lex Fridman Podcast #434youtube.com

    video · 3h 02m · spoken · official transcript

    All 20 korrents from this recordingthis one is 9th

Added to korrents 19 Jun 2024 · 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 →