Live data from Hacker News

Viewing profile — manmal

manmal

HN member
Joined
Thu, Dec 01, 2011, 10:21 AM UTC
HN karma
6,989
Public activity
3,574 items

About manmal

iOS developer since iOS4. Masters degree from UT Vienna.

Living near Vienna, Austria.

meet.hn/city/at-Vienna

Recent public activity

  1. comment
    Comment #49215868

    Are you using the SOTA models at very high reasoning during planning? IME that makes a LOT of a difference. I‘d also never let them just rip into the architecture, but always push …

  2. comment
    Comment #49215133

    I do spend 5x more tokens on planning and reviewing, than for implementation. But architecture is still nothing I can delegate.

  3. comment
    Comment #49206295

    > At a certain speed point, you're able to move from request -> response to a cascade of tool calling and "subagents" That also needs server class hardware though. A phone won’t ha…

  4. comment
    Comment #49206240

    I think that only works if you have checkpoints where all that reasoning can be checked against reality. Otherwise you get an army of armchair experts. LLMs are hilariously bad at …

  5. comment
    Comment #49206188

    About your first example, isn’t the butterfly effect preventing this from being useful? One agent in your simulation decides to sell, and starts an avalanche, that won’t happen in …

  6. comment
    Comment #49206147

    Problem is, there exists no judge model that will really pick the same winner that you would.

  7. comment
    Comment #49206113

    Errors compound, and making 1000 wrong decisions per hour, will not result in something useful. Maybe you‘ve tried setting up guardrails for good design or architecture at some poi…

  8. comment
    Comment #49206093

    That’s their API with extra steps, or am I missing something? That was always faster.

  9. comment
    Comment #49200109

    At this point I'm happy when things don't break randomly. However, it seems I lost an ACP session today and I'm not sure it's my own fault. Could be Zed playing tricks.

  10. comment
    Comment #49192876

    It’s not out of their domain at all IMO. I‘m only using Zed now (despite its non existent GH integration) because it works with Codex.

  11. comment
    Comment #49192873

    What I really like is that all code links it outputs, open a pane at that line.

  12. comment
    Comment #49192860

    I‘m using codex no issues, over ACP.

  13. comment
    Comment #49188534

    I use it constantly but haven’t felt the need to paste an image yet. I guess I‘m using pi and the Codex app more for that.

  14. comment
    Comment #49188093

    Their ACP integration is good (finally), at least with Codex. For when I want to be near the code, I prefer it now over TUIs or the Codex app. It feels much more immediate that way…

  15. comment
    Comment #49159548

    As a heavy pi user - this doesn’t help, for codex. The thinking traces are encrypted and you cannot move that session over to eg your local ds4. It will lack those precious thinkin…

  16. comment
    Comment #49116726

    Yes there was a generation with plastic back which fell apart. Everybody uses double sided glass now. Should be good.

  17. comment
    Comment #49106465

    Sounds like the kind of project that would have afforded a Vision Pro, right? I bet you can spot mistakes before building it, that way. Things like, oh, this room will be very dark…

  18. comment
    Comment #49088925

    Or, good that the craze for ever thinner laptops has been slowed?

  19. comment
    Comment #49074730

    Panels should do 30 years, easy. Inverters will usually fail after 15y, and with batteries it’s unknown what the current gen will do - 15y, maybe 20? Definitely get LFP.

  20. comment
    Comment #49028448

    Have you tried a virtual board, like Miro?

  21. comment
    Comment #48972277

    It would take longer to train on intercepted Fable data, no?

  22. comment
    Comment #48966251

    Read the session file of the reviewer tomorrow. Sonnet should suffice.

  23. comment
    Comment #48966240

    Fighting against the weights is often a lost cause. For any model.

  24. comment
    Comment #48875726

    > The best agentic developers are now probably exceeding 100x, doing massive rewrites of codebases that would have taken years of engineering in days I‘m not denying that you can g…

  25. comment
    Comment #48875178

    The trend to put acoustic panels or an imitation of their pattern on _everything_ is one of my pet peeves. They create some stroboscobe effect with my (not normal) vision. The resu…