Live data from Hacker News

Viewing profile — flux3125

flux3125

HN member
Joined
Sun, Jan 26, 2025, 3:14 PM UTC
HN karma
159
Public activity
69 items

About flux3125

No profile information was provided.

Recent public activity

  1. comment
    Comment #49032287

    > If OpenAI had done this, the attack would not have happened But then how would they market their product?

  2. comment
    Comment #48617363

    And now he's part of the confusing comment section lol

  3. comment
    Comment #48577877

    Max 60 bucks a month. More than that and I'd just move to local qwen 35b or some other cheaper model on openrouter.

  4. comment
    Comment #48525726

    This reminds me of Coconut Simulator

  5. comment
    Comment #48412890

    Sorry, I forgot to add "on Linux" at the end. Still, that's a nice one!

  6. comment
    Comment #48412314

    I'm curious if there's a program that uses a simple detection model for UX components to locate clickable areas. This would allow for global navigation similar to VimiumC

  7. comment
    Comment #48397483

    It's called Time Series Forecasting

  8. comment
    Comment #48375431

    They'll not only do it, but they'll also wrap it in a huge fat rounded border

  9. comment
    Comment #48311597

    > It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked Until it does. A simple curl request to a compromised website could inject a mal…

  10. comment
    Comment #48106691

    > Don't listen to him That's the idea

  11. comment
    Comment #48084049

    You're absolutely right!

  12. comment
    Comment #48065672

    At least it doesn't know my age Oh wait

  13. comment
    Comment #48065548

    [flagged]

  14. comment
    Comment #47838252

    Point 2 is so true, I definitely find myself spending more time reading code vs writing it. LLMs can teach you a lot, but it's never the same as actually sitting down and doing it …

  15. comment
    Comment #47804715

    I was (positively) surprised that this didn't involve any AI.

  16. comment
    Comment #47798813

    Code quality and IDEs aren't going anywhere, especially in complex enterprise systems. AI has improved a lot, but we're still far from a "forget about code" world.

  17. comment
    Comment #47794118

    They are okay for vibe coding throw-away projects without spending your Anthrophic/OAI tokens

  18. comment
    Comment #47793557

    You ARE the training data

  19. comment
    Comment #47790442

    I stopped using Ollama a couple of months ago. Not out of frustration, but because llama.cpp has improved a lot recently with router mode, hot-swapping, a modern and simple web UI,…

  20. comment
  21. comment
  22. comment
    Comment #47790090

    > so llama-swap can load Just in case you haven't seen it yet, llama.cpp now has a router mode that lets you hot-swap models. I've switched over from llama-swap and have been happy…

  23. comment
    Comment #47757236

    In my experience if you're coding or doing something that requires precision, quantizing the kv cache is definitely not worth it. If you're just chatting or doing less precise thin…

  24. comment
    Comment #47719494

    > but with people throwing money behind it, there’s a plan to extract value from the user base from day one. They'll start injecting ads in your commit messages, forcing you to sub…

  25. comment
    Comment #47694938

    Finally Claude Code can now control Claude Code