Live data from Hacker News

Viewing profile — dhorthy

dhorthy

HN member
Joined
Fri, Mar 02, 2018, 12:46 AM UTC
HN karma
1,118
Public activity
265 items

About dhorthy

building @ humanlayer.com

Recent public activity

  1. story
  2. comment
    Comment #49084895

    so wait is the finding that most of those skills reduce pass rates against SCB? wild

  3. comment
    Comment #49083596

    why would that worry you?

  4. comment
    Comment #49083594

    agree, i think the implication is that low quality code is harder to change in the future

  5. comment
    Comment #49079507

    somebody get this man a curl-pipe-bash stat

  6. comment
    Comment #49079303

    oh i really like the idea of flipping around the order of checkpoints and comparing results. Could be an interesting way to increase/decrease difficulty even i will look into how e…

  7. comment
    Comment #49079102

    Yeah I would hold that models don’t know how to simplify because most rl/benchmarks doesn’t penalize complexity

  8. comment
    Comment #49079051

    Yeah the main reason I skipped fable was because we have a ZDR with anthropic and I didn’t feel like spinning up another account to circumvent that. Next run will have fable and so…

  9. comment
    Comment #49078496

    my issue with frontier code is that it uses a model judge for quality whereas slop code bench forces a model to grapple with its own garbage code in order to receive a functionalit…

  10. comment
    Comment #49078447

    i laughed at the pelican bit its good yes the labs will always prioritize the vibeslop dopamine casino as far as I can tell - making the models useful and addictive for unsophistic…

  11. comment
    Comment #49078197

    yeah someone will have to re-run this bench on various effort levels. unfortunately it is not cheap

  12. comment
    Comment #49078037

    I agree this is an option, and the next thing on my radar is to try with a more realistic "factory-shaped" harness where you have feedback from linters and other models after each …

  13. comment
    Comment #49077863

    > - what "maintainable" is is probably some high dimensional space described by these signals; it'd probably require some human labeling to figure out where this space is this is a…

  14. comment
    Comment #49077582

    yes sol is still my daily driver for most coding tasks I did find opus 5 quite handy for general knowledge work and visual design, without the cost of fable (e.g. the graphics in t…

  15. comment
    Comment #49077412

    no i'm spinning those up at some point this week. here's the first few prompts I used (claude opus 5 as the research orchestrator), (these were interspersed with lots of tools and …

  16. comment
    Comment #49077190

    i hope that is because you hate slop and not because you write it

  17. comment
    Comment #49077161

    yeah this was just a start - the fastest cheapest thing we could try for a brand new model. I'm hoping to do some more work with sol/fable in the mix as well as exploring more lang…

  18. story
  19. comment
    Comment #49044068

    the one good thing about the current ios version is that it is the best it will ever be from this point forward. all future versions will be worse

  20. comment
    Comment #49031395

    I agree this rocks I do this almost daily

  21. comment
    Comment #49031112

    yes well said

  22. comment
    Comment #49030566

    don't forget the andon cord

  23. comment
    Comment #49030450

    i humbly disagree - horizontal means touching one plane of the stack across, vertical means cutting down through it and touching multiple layers https://en.wikipedia.org/wiki/Verti…

  24. comment
    Comment #49030420

    i did a write up on fable while it was out - it can do big refactors, but it does not know what to change without human steering. For that, you need humans to know what to ask for.…

  25. comment
    Comment #49030087

    its the optimizing utilization instead of overall throughput all over again. eli goldratt talked about this in the 1970s[1]. we still haven't learned 1 - https://en.wikipedia.org/w…