Show HN: TurboGPT: train 22KiB transformer in 13s

 (github.com)

34 points | by lostmsu 3 hours ago

5 comments

  • w4yai 1 minute ago
    "hn1g.txt" => not available
  • jey 1 hour ago
    At that scale it seems like you could just solve the KKT conditions directly. Exaggerating but only a little
  • vjsrinivas 32 minutes ago
    Interesting trend of labeling models after how big they are on disk vs how many learnable parameters they have.
  • pane_poker_11 19 minutes ago
    [dead]
  • fleshmonad 34 minutes ago
    Who cares. This will not get you hired. Why do these submissions get any points at all. The same people who upvote this are the ones seething AI cannot create anything new. I don't see it. Not to shit on the work that went into this.
    [-]
    • kadoban 28 minutes ago
      Jesus. Would hate to see the work you _do_ want to shit on.