Live data from Hacker News

Viewing profile — scosman

scosman

HN member
Joined
Sat, Aug 13, 2011, 1:26 AM UTC
HN karma
3,946
Public activity
911 items

About scosman

No profile information was provided.

Recent public activity

  1. comment
    Comment #49205150

    many evals, but yes

  2. comment
    Comment #49174491

    We've using auto-research for harnesses and it's surprisingly powerful. It's amazing how many problems are easy to spot and fix from traces. Few key things were required to get it …

  3. comment
    Comment #49123830

    thanks, corrected! I looked at Q3

  4. comment
    Comment #49123216

    So GLM 5.2/Gemini 3.6 level intelligence for $0.28/m output. And their updated Pro model coming soon.... Plus a size you can genuinely run at home: Unsloth lossless Q8 at 162GB.

  5. comment
    Comment #49103709

    I've wired ESP32s into all my old heat pump units using ESPHome. They are more reliable and more responsive than the $400 dongle they sold with newer units.

  6. comment
    Comment #49012040

    join me in building the ideal training set for pelicans riding bicycles: https://github.com/scosman/pelicans_riding_bicycles

  7. comment
    Comment #48996156

    > IMO "end-to-end encryption" simply isn't possible In a technical sense it's absolutely possible. Owning the servers != transferring keys to the servers. Most E2E apps run both cl…

  8. comment
    Comment #48923133

    Go mobile definitely supports building libraries. It will package up an xcframework for iOS and something else for Android (I forget details). It doesn't need to be the whole app. …

  9. comment
    Comment #48902275

    small issue: xcodebuild will just randomly fail sometimes. And the solution is to... open and close Xcode. I wish this wasn't true, but it is.

  10. story
    Show HN: Biscotti – on-device meeting transcription for macOS

    https://github.com/scosman/Biscotti I got tired of Electron meeting-transcription apps that upload my private audio to a server to do transcription/summary my MacBook could do loca…

  11. comment
    Comment #48834847

    ChatGPT has had this for over a year too. This is a better model.

  12. comment
    Comment #48831273

    What's the best "run your coding agent in apple containers" setup folks have?

  13. comment
    Comment #48779240

    heh, who knows. I often give agents the motivation, which I generally helpful. Have not bothered to measure this case.

  14. comment
    Comment #48778524

    The top of my ~/.claude/CLAUDE.md: > Don't turn a one-off or area-specific comment into a durable memory without my explicit confirmation. You have a history of over-indexing on on…

  15. comment
    Comment #48738545

    Kimi K2.5 >> Haiku. Gemma 4 32b might fit the bill.

  16. comment
    Comment #48736906

    Look at Qwen for that level of intelligence.

  17. comment
    Comment #48713776

    short answer: they mostly aren't A few people are running highly quantized models with limited context windows. It's still impressive, but not the benchmark level intelligence. Ver…

  18. comment
    Comment #48710946

    I dunno. I know a lot of software engineering experts. AI isn't always right, but neither are the people, and it's getting better and better. Software is one domain where it excels…

  19. comment
    Comment #48698841

    This was copying many screens, composing layouts and many strings. not a "general look and feel" or one off utility string. Others found parts of the code copied (exact variable na…

  20. comment
    Comment #48690465

    They copied strings, and visual design. Both of which are work, both of which are covered by copyright.

  21. comment
    Comment #48685176

    Short segments of popular works sure. Many UI pages with identical layouts and copy, essentially zero chance. The agent had access to the original code at inference time.

  22. story
  23. comment
    Comment #48653853

    "ghostlygourd.com" is a S+ tier domain. Would click

  24. comment
    Comment #48639107

    It's not economic to run them locally. It's amazing for privacy, and fun hobby. But you're either looking at super slow CPU builds with $10k in RAM, $90k worth of GPUs, or a really…

  25. comment
    Comment #48609949

    anyone manage to get a point?