Live data from Hacker News

Viewing profile — artursapek

artursapek

HN member
Joined
Mon, Dec 20, 2010, 12:05 AM UTC
HN karma
8,161
Public activity
3,050 items

About artursapek

art@art.cx

https://art.cx

https://revise.io

Recent public activity

  1. comment
    Comment #49222891

    Hi HN. I've been bootstrapping this project full-time for the last 12 months. Would love to get some feedback on the MCP integration! I think it's some of the best UX available for…

  2. story
  3. comment
    Comment #49218034

    These prices are not real. They already said so.

  4. comment
    Comment #49082030

    It’s an attempt to build a locomotion model. It uses a physics engine (Avian in Bevy) to animate a walking biped from first principles. An earlier version can be seen here https://…

  5. comment
    Comment #49082002

    WASD or just touch on mobile

  6. story
  7. comment
    Comment #49041443

    It's definitely not cheaper than Sonnet on my benchmark, but it's cheaper than Fable and outperforms it. Which is big IMO. https://revise.io/errata-bench

  8. story
  9. comment
    Comment #49038889

    HN users are world champions are trivializing difficult things with snarky comments

  10. story
  11. comment
    Comment #48921185

    Yep, I've been taking glycine and magnesium for years. I am not as consistent as I should be but it makes a big difference when I use them.

  12. story
  13. story
  14. comment
    Comment #48738891

    I run a proofreading benchmark that tests how well models can find and fix errors in English text. They get several passes in a simple agent loop. Sonnet 5 is definitely better tha…

  15. comment
    Comment #48727590

    haha yeah I've bet the last 12 months of my career on a .io

  16. comment
    Comment #48726693

    The .ai TLD is some tiny island with a few thousand people

  17. comment
    Comment #48702293

    Trivial to simulate basic keystrokes. But I don't think it's trivial to simulate the natural process of drafting something. There's no concrete heuristic or algorithm (yet) for jud…

  18. story
  19. comment
    Comment #48689840

    They claim extreme performance on ExploitBench, which Mythos was touted as being incredible at. https://x.com/OpenAI/status/2070555278576439306

  20. story
  21. comment
    Comment #48467706

    Fable 5 beats GPT 5.5 in my proofreading benchmark. And it does so at approximately the same total cost; it used significantly fewer turns than 5.5 https://x.com/tmuxvim/status/206…

  22. comment
    Comment #48460928

    I would expect Apple to hedge their bet on Gemini and build everything so that the model can be swapped out in the future.

  23. comment
    Comment #48453153

    I use Carplay all the time and I didn't even realize it has voice control. I just set things up on my phone and drive.

  24. comment
    Comment #48453090

    I think it's fair to say that OpenAI has at least partially won the "consumer AI" segment.

  25. comment
    Comment #48402642

    You’re not responding to anything the parent said.