Live data from Hacker News

Viewing profile — lopopolo

lopopolo

HN member
Joined
Thu, Jan 12, 2012, 1:58 PM UTC
HN karma
671
Public activity
143 items

About lopopolo

Software engineer | Senior Staff Software Engineer at Brex | Artichoke Ruby

https://hyperbo.la | https://www.artichokeruby.org

Recent public activity

  1. comment
    Comment #48964779

    You can read the receipts in the linked source material yourself. I’ve also read and signed off on every word in this anthology. Try it before you knock it? But yes, 100% of the co…

  2. comment
    Comment #48964767

    The models are very good now so the feedback cycle on these meta adjustments is much tighter. Yesterday I was able to one shot a Liquid Glass, HIG-compliant and localized DICOM ima…

  3. comment
    Comment #48964700

    Basically yea. It is the only way to learn how to outrun your priors on what “high ambition” looks like. The labor that goes into implementation is an uncapped resource now.

  4. comment
    Comment #48964633

    And to address your broader question, yes this is a form of RSI and to me a vastly superior approach to fine tuning since it allows adopting new model releases without throwing any…

  5. comment
    Comment #48964622

    Your example is super amenable to vibing some tests. As an example, I’ve been able to ban `number` from representing a duration by walking the AST in a linter to fail if var or par…

  6. comment
    Comment #48964524

    Your “really cheap” agents can’t be so cheap that they do not have good tool calling skills. But! Using bigger models to put guardrails in place as static verifiers allows lower co…

  7. comment
    Comment #48964518

    Glad to hear it! Good luck, have fun. The agents tend to do a pretty good job incorporating these ideas. This was an unexpected thing we learned when publishing the initial harness…

  8. comment
    Comment #48963784

    Hi folks, author here and also author of the seminal OpenAI blog on this topic. Let me know how I can help you all let it rip.

  9. story
  10. story
  11. story
  12. comment
    Comment #29975045

    The mruby VM as used in Artichoke uses Artichoke's Rust implementations of `String`, `Symbol`, and `Array` (and many other core classes, these ones just happen to be used by the VM…

  13. comment
    Comment #29973929

    Hi, Artichoke author here. I feel very blessed to have Artichoke be mentioned in this ticket on Ruby's bug tracker. If y'all are interested to follow along, @artichokeruby on Twitt…

  14. story
  15. story
  16. story
  17. comment
    Comment #28429854

    The compiler does have a lint to force being explicit about unsafe in the way you describe. It is an allow by default lint called `unsafe_op_in_unsafe_fn`.

  18. story
  19. story
  20. story
  21. comment
    Comment #26128318

    Whimsical - https://whimsical.com/

  22. comment
    Comment #26127352

    For now Artichoke leans on mruby’s parser, but I’m looking forward to using https://github.com/lib-ruby-parser/lib-ruby-parser which is a Rust port of MRI’s parse.y.

  23. comment
    Comment #26126803

    Code size in an embedded context is one use case for the modularity here. Another is limiting access of Ruby code to the host system. For example, one may wish to use Artichoke in …

  24. story
  25. comment
    Comment #25610544

    Here's a permalink: https://github.com/artichoke/artichoke/blob/939fffc015255736...