Live data from Hacker News

Viewing profile — bionhoward

bionhoward

HN member
Joined
Sun, Sep 02, 2018, 6:42 AM UTC
HN karma
1,018
Public activity
710 items

About bionhoward

https://github.com/bionicles/tree_plus/blob/main/README.md

Recent public activity

  1. comment
    Comment #48562154

    It’s amazing how much Python punishes you for modularizing your code

  2. comment
    Comment #48103575

    I’m heavy into rust and never really use golang, but one big benefit of go over rust is compile times are significantly quicker, which could be more fun if you’re running CI checks…

  3. comment
    Comment #47784739

    Yeah it’s a coding beast if you get it dialed in right

  4. comment
    Comment #47305213

    gotta admit i groaned a bit at this because it would make rust more complicated, but on my 2nd read i realized: - some things (compile time bounds checking tensor shapes) are hard …

  5. comment
    Comment #47282222

    Anthropic is not trustworthy for this because they force every Claude Code user to agree to a noncompete while also opting them in to model training. That means, by default, every …

  6. comment
    Comment #47241936

    surprisingly accurate! Is Gary the AI equivalent of the “nothing ever happens” guy?

  7. comment
    Comment #47052765

    genius, great idea and follow through, please keep it up, this could improve the ML industry tremendously, maybe some einops inspired interface for this would be good?

  8. comment
    Comment #47029343

    building this openclaw thing that competes with openai using codex is against the openai terms of service, which say you can't use it to make stuff that competes with them. but the…

  9. comment
    Comment #47018905

    signal should just add better API / bot stuff and then we could all use that. there's no way OpenAI would be trustworthy for this; slack certainly isn't

  10. comment
    Comment #46726068

    found a bug searching for "collagen": Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node. Something broke. We're working on it, but in th…

  11. comment
    Comment #46600921

    Yes! The paywalled SQL documents are a big annoyance

  12. comment
    Comment #46579547

    Yup, I’ve been crowing about these customer noncompetes for years now and it’s clear Anthropic has one of the worst ones. The real kicker is, since Claude Code can do anything, you…

  13. comment
    Comment #46551558

    Why act like it’s a mystery when the Claude Code repo clearly explains: > When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejec…

  14. comment
    Comment #46404663

    Would SRAM make weight updates prohibitive vs DRAM?

  15. comment
    Comment #46370514

    Gemini is absolutely not Gryffindor since it auto-opts users into training AI on their codebases without informed consent

  16. comment
    Comment #46134537

    Anthropic also has legal terms that say no one is allowed to use the service for anything work related, but nobody seems to care

  17. comment
    Comment #46134494

    Cursor still wins over Claude Code because Cursor has privacy mode

  18. comment
    Comment #46134320

    I think it’s more about deciding how much to think about stuff and not a model router per se. 5 and 5.1 get progressively better calibrated reasoning token budgets. Also o3 and “re…

  19. comment
    Comment #45969362

    model provider CLIs are a trap, less freedom of choice, less privacy, way more prohibitions buried in the fine print

  20. comment
    Comment #45806020

    Good reason to use Cursor, you can insta-switch to whatever model you want and even run diverse models from different providers at the same time. If one of em isn’t working then yo…

  21. comment
    Comment #45598764

    And here I thought it was a pedantic word for “data box”

  22. comment
    Comment #45597407

    Is using these terminal agents with customer noncompete and no privacy questionable when cursor has the same models and privacy mode?

  23. comment
    Comment #45552968

    The point is it’s sucking your data into some amorphous big brother dataset without explicitly asking you if you want that to happen first. Opt out AI features are generally rude, …

  24. comment
    Comment #45356370

    Rust for everything, I could explain but it would get rude

  25. comment
    Comment #45356167

    Rust feels easy for me, could it be we’re just used to what we use more? Anyway, it’s all pretty easy, what’s the use arguing which of multiple easy things is easiest?