Live data from Hacker News

Viewing profile — baalimago

baalimago

HN member
Joined
Sun, Jul 16, 2017, 9:38 AM UTC
HN karma
1,264
Public activity
449 items

About baalimago

learning...

https://github.com/baalimago https://lorentz.app

Recent public activity

  1. comment
  2. comment
    Comment #49167477

    Next month perpetually

  3. comment
    Comment #49166790

    Give it an AI-bubble pop and these will be flooding the market.

  4. comment
    Comment #49154066

    "Prevent sub-optimal code by manually retyping compiler-generated assembly" I don't think this is a practice which will be sustainable for very long

  5. comment
    Comment #49153996

    I've gone another route when I found myself simply replying with an investigation made from an AI: Actively encouraged my coworkers to ask the knowledge-bank AI I've setup instead …

  6. comment
    Comment #49141859

    This: "(b Box[T]) Map[U any](f func(T) U) Box[U]" is the type of cognitive weight I was happy that Go avoided.

  7. comment
    Comment #49123556

    Personally I'm hoping for EU to step up a bit

  8. comment
    Comment #49121835

    New Deepseek models are like Christmas for me. Really big fan of low cost API models, noone does it better than DS. Until VRAM price is low enough to run models locally, this is th…

  9. comment
    Comment #49120289

    Looks like they will release an updated version of deepseek-v4-pro soon, which most likely will beat kimi k3 at both intelligence and cost (judging by the vast improvements to dsv4…

  10. comment
    Comment #49120154

    Very promising. So it will both keep the speed and reduced price, yet exceed performance of the quite sufficient deepseek-v4-pro? Should be extending the lead in intelligence/cost …

  11. comment
    Comment #49114163

    It seems like Europe, yet again, have to stand up for ethics, morality and try to deflect corruption. It's so tiresome.

  12. comment
    Comment #49113726

    No we kept prompts as is, just swapped model. The prompt is already quite optimized for the task. How would updating it possibly make a more intelligent model spend less tokens tha…

  13. comment
    Comment #49113548

    We swapped an internal system from gpt-5-mini to gpt-5.6-luna and saw no benefit but 4x cost. Sufficed to say: we swapped back to gpt-5-mini.

  14. comment
    Comment #49107010

    Or use a drone. I'm just being clever.

  15. comment
    Comment #49106538

    How's the upstairs looking?

  16. comment
    Comment #49021977

    Run AI locally instead of in cloud

  17. comment
    Comment #49021872

    Is this the CDOs of the AI-bubble?

  18. comment
    Comment #49011989

    "Look, guys, our model is dangerous too..!!"

  19. comment
    Comment #49005364

    I don't see how this can be any worse than normal ads. Much like how Truman finds his wife Meryl odd with her strange injections of products, the ads will become obnoxious and opaq…

  20. comment
    Comment #48994436

    Not good enough for high-end, not cheap enough to be for low-end. Next!

  21. comment
    Comment #48902444

    What's wrong with git?

  22. comment
    Comment #48888319

    Selfplugging a bit here: clai[0] sends only exacly what you want it to send. [0]: https://github.com/baalimago/clai

  23. story
  24. comment
    Comment #48857664

    Worse than GLM-5.2, much more expensive than deepseek v4. Tough bargain.

  25. comment
    Comment #48856415

    As if I wasn't apathetic enough about democracy. The only voting bill worth caring about is the one in the wallet. Then you can be the source of the corruption, instead of the sink…