Live data from Hacker News

Viewing profile — chris_st

chris_st

HN member
Joined
Tue, Nov 24, 2015, 2:13 PM UTC
HN karma
1,600
Public activity
730 items

About chris_st

No profile information was provided.

Recent public activity

  1. comment
    Comment #49084764

    I'll check that out - I loved his "The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography". Excellent introduction to cryptography.

  2. comment
    Comment #49047245

    I really liked her "Uncharted with Hannah Fry" podcast, sorry it ended.

  3. comment
    Comment #48838784

    FWIW, Cognition has all the Sonnet/Opus/Fable models, and all the GPT ones, as well as GLM, Kimi, and Gemini.

  4. story
  5. comment
    Comment #48454188

    What "non-house" harnesses have you found to work best?

  6. comment
    Comment #48427340

    Interesting to see (roughly!) what percent of each car is engine.

  7. comment
    Comment #48315107

    I have this setup, roughly, with UTM rather than orbstack. I think I have it set up safely, curious how you see it has the wrong permissions?

  8. comment
    Comment #48279039

    Another way I'm "going slower" is to have the AI implement individual sub-steps of the current task, and review each one. It's slower than having it yolo out the whole thing, but i…

  9. comment
    Comment #48277691

    Yup, just like people!

  10. comment
  11. comment
    Comment #48132910

    Nope, not better quality if you don't like the smell of cigarettes.

  12. comment
    Comment #48115644

    Please add support for the Windsurf editor as well. Thanks!

  13. comment
    Comment #48077438

    Awesome, stealing that!

  14. comment
    Comment #48077332

    And they're clearly marked as `unsafe`, so easy to find, which gives them a nice list of issues to address.

  15. comment
    Comment #48068217

    I asked Claude to tell me why something was implemented the way it was, and got an excellent response. One data point, would love to hear more examples.

  16. comment
    Comment #47961282

    ...it came as a surprise that [leaving a Petri dish out with a window open] would end up with interesting [molds] (called [penicillin]). _It was not planned at all_.

  17. comment
    Comment #47902362

    Well, to be fair, people cheat by remembering what they did last time. I think the idea here is to run the models from a "clean slate" and see how often they succeed/fail. They are…

  18. comment
    Comment #47895638

    Possibly because they just haven't been able to manufacture enough of them yet to be a viable business to others? They're fighting everyone else for foundry space and time.

  19. comment
    Comment #47710769

    But it's pretty cool that LLM bug hunting is pretty cheap... the 1-person projects can do it themselves, don't have to contract out to some huge security company.

  20. comment
    Comment #47681419

    Well, maybe not... see Simon Willison's ongoing reporting [0] on all the bug reports for `curl` people are finding with LLMs. Interesting to see them go from "DON'T GIVE US AI SLOP…

  21. comment
    Comment #47628112

    From the article: > As we noted at its September beta release, a windowed version of Tailscale’s macOS app doesn’t replace the menu bar app, but runs alongside it. It can be pulled…

  22. comment
    Comment #47578798

    Seconding Maple Mono - it's very nice.

  23. comment
    Comment #47165779

    Just out of curiosity, which version of Claude?

  24. comment
    Comment #47165732

    Good nerd stories, alas it was cancelled, so no new ones: - Uncharted with Hannah Fry Some great fiction: - Achewillow - horror, but not excessively horrible. - Desert Skies - humo…

  25. comment
    Comment #46837299

    Turns out the apps in /Application/ run as you. Problem (between keyboard and chair :-) solved.