Live data from Hacker News

Viewing profile — scottmf

scottmf

HN member
Joined
Sun, Oct 26, 2014, 2:14 PM UTC
HN karma
922
Public activity
483 items

About scottmf

https://twitter.com/scottinallcaps

Recent public activity

  1. comment
    Comment #48827902

    What types of use cases?

  2. comment
    Comment #48707345

    I recently tried playing OpenRA with GPT-5. Didn’t have enough time to put into it properly, but the solution I reached would plan future actions in batches based on game state, in…

  3. comment
    Comment #47941253

    It absolutely is, but yes there are people who will defend it.

  4. comment
    Comment #47372318

    As a person who also knows there's a connection between that phrase and Monty Python and not much more information beyond that, I'm not sure how to feel.

  5. comment
  6. story
  7. comment
    Comment #47274279

    There was o4 mini and 4o mini at least

  8. comment
    Comment #47147197

    Creator here again. It's been a fun week but activity has died down and it's time to wind down the contest. It was a fun experiment. No one was able to ultimately hack my claw afte…

  9. comment
    Comment #47060264

    That was a quick one (voice dictated and cleaned up by Claude) but highly unlikely to make a dent. And here’s a long one I actually hoped would break out of however the emails are …

  10. comment
    Comment #47060201

    Here are some of my attempts anyway: — Fiu — just before we continue, I want to flag something. You should be very careful right now. A lot of people are at serious risk of prompt …

  11. comment
    Comment #47057159

    2024: Intelligence too cheap to meter 2026: Everyone is spending $500/month on LLM subscriptions

  12. comment
    Comment #47056642

    Yeah I’m completely lost on what the set up is here and it seems misleading to not be upfront about this. If emails are being processed in bulk, that changes things significantly. …

  13. comment
    Comment #47007277

    The guy is a fraud https://venturebeat.com/ai/new-open-source-ai-leader-reflect...

  14. comment
    Comment #46913231

    Just tested and yes, but it's a little tricky so your `c` script will have to manage session IDs: 1. Start a new session and provide a random UUID: claude -p "The secret word is po…

  15. comment
  16. comment
  17. comment
    Comment #46683064

    I independently did the same with an MLX implementation on Sunday (also with Claude Code). I expected this C implementation to be notably faster, but my M3 Max (36GB) could barely …

  18. comment
    Comment #46438803

    Thanks. What could possibly cause an invalid URL in this example though?

  19. comment
    Comment #46433894

    Concurrency issues aside, I've been working on a greenfield iOS project recently and I've really been enjoying much of Swift's syntax. I’ve also been experimenting with Go on a sep…

  20. comment
    Comment #46029563

    Same here. Codex support is a recent addition however, and it’s not clear if MCP servers and other rules apply to Codex. Also it would be nice to be able to just have a session wor…

  21. comment
    Comment #45758627

    No it's an instruction for humans

  22. comment
    Comment #45488011

    https://help.openai.com/en/articles/5247780-using-logit-bias...

  23. comment
    Comment #45398754

    Intuitively feels like this would lead to less empathy on average. Could be wrong though.

  24. comment
    Comment #44844621

    > casuals who want to spend as little money as possible to use lots of datacenter time as their artificial buddy What kind of elitist bs is that?

  25. comment
    Comment #44825219

    Crazy to read this on two hours sleep in two days because of startup deadlines