Live data from Hacker News

Viewing profile — jswny

jswny

HN member
Joined
Fri, Oct 09, 2015, 5:24 AM UTC
HN karma
1,510
Public activity
350 items

About jswny

Site: j1.io Email: joe [at] j1.io

[ my public key: https://keybase.io/jswny; my proof: https://keybase.io/jswny/sigs/pUFgX77M84hK-jJjciHEYOD7rL-iywoxAtKO-gALkT8 ]

Recent public activity

  1. comment
    Comment #49010291

    Does anyone do TLA style distributed systems verification with Lean? Curious the experience there and how well supported it is

  2. comment
    Comment #48957908

    Unfortunately I’ve used Claude and GPT models for a long time in a variety of harnesses and I agree with you and I think it’s the compaction. For some reason, codex compaction is l…

  3. comment
    Comment #48890947

    I agree with some of Kelley’s takes, but the issue is the tone. Does anyone think that if Bun had been rewritten from Rust to Zig that a member of the Rust core team would have wri…

  4. comment
    Comment #48789232

    What’s the advantage of that for building?

  5. comment
    Comment #48165152

    Why not WASM?

  6. comment
    Comment #47881006

    Codex is fully open source…

  7. comment
    Comment #47801875

    You want to use the model that is potentially giving your data to the government vs the one that’s openly rejecting that partnership?

  8. comment
    Comment #47383564

    Package a skill with your CLI itself and give users instructions on how to install the skill properly. That allows the agent to read the instructions in a context efficient way whe…

  9. comment
    Comment #47383555

    Plenty of MCPs require you to install and run them locally, like I said remote MCP has a real advantage over CLI tho

  10. comment
    Comment #47381251

    MCP loads all tools immediately. CLI does not because it’s not auto exposed to the agent, got have more control of how the context of which tools exist, and how to deliver that con…

  11. comment
    Comment #47381210

    MCP is fine, particular remote MCP which is the lowest friction way to get access to some hosted service with auth handled for you. However, MCP is context bloat and not very good …

  12. comment
    Comment #47083986

    Can you explain what’s so different about pro? I’ve used everything frontier model and had Pro a while ago but it seemed to just be the same models served faster at the time.

  13. comment
    Comment #46881363

    How do you get sub agents to work?

  14. comment
    Comment #46744737

    That’s just spawning multiple parallel explore agents instructed to look at different things, and then compiling results That’s a pretty basic functionality in Claude code

  15. comment
    Comment #46743282

    What’s the point of having a public GitHub repo with PRs enabled if they will never merge any of them?

  16. comment
    Comment #46743235

    How do you know/toggle which API path you are using?

  17. comment
    Comment #46740238

    How does this work for other models that aren’t OpenAI models

  18. comment
    Comment #46449003

    Ah I think it’s because I was testing with an external library in the top level TOML metadata

  19. comment
    Comment #46440807

    The problem is that only Deno can type check single file scripts. Otherwise with Node and Bun you need a project to use tsc. Python can type check single file scripts (even with PE…

  20. comment
    Comment #46440795

    I wish this was faster, in my tests it’s about 200ms startup consistently on my M4 MacBook. Otherwise very cool

  21. comment
    Comment #46440644

    Bun has a lot of this built in, plus Bun shell

  22. comment
    Comment #46428904

    Not memory, I just instruct it to freely experiment with temporary scripts and artifacts in a specific folder. This helps it organize temporary things it does like debugging script…

  23. comment
    Comment #46428327

    Can you give an example of how beads would be used by Claude to do something it otherwise couldn’t? I can’t quite tell what it is useful for

  24. comment
    Comment #46428299

    I also specifically instruct Claude how to use a globally git ignored scratch folder “tmp” in each repo. Curious what your approach is

  25. comment
    Comment #46365487

    Very interesting project! I have 2 questions: 1. How has it been working with ACP? Is it anywhere near feature parity with Claude code’s native interface? 2. I see your repo is wri…