Live data from Hacker News

Viewing profile — EugeneOZ

EugeneOZ

HN member
Joined
Wed, Mar 21, 2012, 8:44 PM UTC
HN karma
2,654
Public activity
2,145 items

About EugeneOZ

https://jamm.dev

https://twitter.com/eugeniyoz

https://www.upwork.com/users/~01d95397aacaef6e88

http://careers.stackoverflow.com/oz

https://www.linkedin.com/in/newmanoz/

Recent public activity

  1. comment
    Comment #49142370

    [flagged]

  2. comment
    Comment #49137125

    > You can still see what you’re billed on the Spending page. No, you can not: https://www.pasteboard.co/dNXUdT-h8Giy.png If you want to say that "admin can" - it doesn't matter, I'…

  3. story
  4. comment
    Comment #49065861

    “Physically accurate” indeed raises the bar significantly. You’ve already done great work here. That said, the feedback seems to come from someone who spent considerable time analy…

  5. comment
    Comment #49057032

    And now your CLAUDE.md is only good for Claude 5 models, not previous ones.

  6. comment
  7. comment
    Comment #49056966

    > Then: Give Claude rules > Now: Let Claude use judgement No, it should follow my rules exactly. I don't care what code examples it was trained on - it will either write code the w…

  8. comment
    Comment #48945605

    Why we should waste 46 minutes instead of briefly looking at charts for 20 seconds? To pay their ads? No, thanks.

  9. comment
    Comment #48945588

    Any benchmark where Sol is better than Fable at coding is ridiculous.

  10. comment
    Comment #48888656

    The article is titled "Why Vanilla JS," but the takeaway seems to be "here are the custom abstractions I wrote."

  11. comment
    Comment #48851079

    GPT 5.6 Sol is a token hog. After implementing the task, it started some "reviews" I didn't ask for - they consumed 19.5M and 11.9M tokens, while the task itself was below 5M token…

  12. comment
    Comment #48817545

    If for 2% of users a webpage will not look as awesome as intended (it's not guaranteed that it will be broken), that's ok. It's not poisoning - it's a 98% chance of getting a top m…

  13. comment
    Comment #48551892

    Start fixing the unfixable and doing the undoable things ;)

  14. comment
    Comment #48353374

    2 comments in total there

  15. comment
    Comment #48271793

    Doesn't look like a sport car. From above it actually looks like a phone. The main thing is that the charging port isn’t on the bottom.

  16. comment
    Comment #48261329

    > Ask it if a microservices architecture makes sense for your three-person team and it’ll explain why microservices are an excellent choice If you ask it to be fair and non-biased …

  17. comment
    Comment #48161112

    [flagged]

  18. comment
    Comment #47881877

    If you think that you can just silently modify the model without any announcements and only react when it doesn't go through unnoticed, then be 100% sure that your clients will che…

  19. comment
    Comment #47881767

    > people didn't understand to use /effort to increase intelligence, and often stuck with the default -- we should have anticipated this UI is UI. It is naive to expect that you bui…

  20. comment
    Comment #47775022

    Absolutely awesome, thank you, Lewis!

  21. comment
    Comment #47715405

    > Skills are great for pure knowledge and teaching an LLM how to use an existing tool. But for giving an LLM actual access to services, the Model Context Protocol (MCP) is the far …

  22. comment
  23. comment
  24. comment
    Comment #47513646

    There are open-source alternatives: https://mochi1ai.com/ https://wan.video/ and others. There are free to use tools also.

  25. comment
    Comment #47513542

    This market will not be abandoned, and other tools already exist: https://klingai.com/global/ https://aistudio.google.com/models/veo-3 https://runwayml.com