CUDA Mode Keynote | Andrej Karpathy | Eureka Labs

แชร์
ฝัง
  • เผยแพร่เมื่อ 7 พ.ย. 2024

ความคิดเห็น • 18

  • @saturdaysequalsyouth
    @saturdaysequalsyouth หลายเดือนก่อน +10

    This is the same talk that was posted on Latent Space, except the audio quality is much better

  • @dj0ai
    @dj0ai หลายเดือนก่อน +7

    1:24 OMG! Andrej Karpathy lives in 2X. Me? I live in 0,75X

  • @iony_mikler
    @iony_mikler 19 วันที่ผ่านมา

    Your simulation seems to run very smooth. What is the computer you are using?

  • @eriye92
    @eriye92 15 วันที่ผ่านมา

    The GOAT

  • @ultrasound1459
    @ultrasound1459 28 วันที่ผ่านมา +1

    3:00 the goat 🐐 🙌

  • @elliptictree
    @elliptictree หลายเดือนก่อน +2

    Interesting.

  • @sizwemamba689
    @sizwemamba689 หลายเดือนก่อน

    Excellent

  • @kehindeakeredolu3525
    @kehindeakeredolu3525 หลายเดือนก่อน

    first comment

  • @IvanMalison
    @IvanMalison หลายเดือนก่อน +1

    i dont get why he's wasting his time doing this. Abstractions are good! Seems like a really strange thing to do.

    • @marshallmcluhan33
      @marshallmcluhan33 หลายเดือนก่อน +1

      Wasting time is what abstraction is all about. Slow tokens

    • @philippleser4125
      @philippleser4125 หลายเดือนก่อน +1

      No. Abstraction is not good per se. Most developers are brain washed that way. One of the reasons why Software has become bloated and sliw.Performance sucks. AK did the right thing.

    • @FamilyYoutubeTV-x6d
      @FamilyYoutubeTV-x6d หลายเดือนก่อน

      I think you have a very valid point, sir. If we want to have "AI computers", we need to have performant and fast model training, execution, inference; otherwise, they are a waste of resources and not worth the hype or money. That's not to say that some "abstraction" is not good. ML and LLMs are not traditional software (in the deterministic sense), and given their goal of wanting to either mimic or emulate intelligence, some abstraction is bound to be necessary. Abstraction is crucial in mathematics and physics, as well as science in general.

    • @ultrasound1459
      @ultrasound1459 28 วันที่ผ่านมา +1

      Abstraction = Slow Ai

    • @FamilyYoutubeTV-x6d
      @FamilyYoutubeTV-x6d 27 วันที่ผ่านมา

      @@ultrasound1459 We are intelligent and have slow areas of intelligence too. Slow AI is not the bottleneck. Planning (and reasoning) is (are) one (two) of them.

  • @dontwannabefound
    @dontwannabefound 27 วันที่ผ่านมา +11

    I’ll save you 30 mins. He basically rewrites pytorch code to train gpt2 in c in 3000 LOC. there.