Live data from Hacker News

Viewing profile — vtail

vtail

HN member
Joined
Wed, Mar 10, 2010, 6:42 PM UTC
HN karma
1,797
Public activity
346 items

About vtail

No profile information was provided.

Recent public activity

  1. comment
    Comment #48738283

    Fascinating! How did you learn about this?

  2. comment
    Comment #48198621

    Here is a GPT 5.5 Extra High with a modified instruction: > Create animated SVG of a frog on a boat rowing through jungle river. Single page self contained HTML page with SVG. Use …

  3. comment
    Comment #48198503

    Here is GPT 5.5 High thinking; I had to add a second follow up prompt "it's not animated though" as the first one was not animated. https://gistpreview.github.io/?557f979c82701862b…

  4. comment
    Comment #47269517

    that's a good point; hopefully they would just extend it automatically - but who knows...

  5. comment
    Comment #47265593

    Looking at the benchmarks, 5.4 is slightly better. But it also offers "Fast" mode (at 2x usage), which - if it works and doesn't completely depletes my Pro plan - is a no brainer a…

  6. comment
    Comment #47265561

    My own experience is that I get far far more usage (and better quality code, too) from codex. I downgrade my Claude Max to Claude Pro (the $20 plan) and now using codex with Pro pl…

  7. comment
    Comment #47210005

    Very cool site - I think I saw it before here on HN, and I liked it a lot. Did you manually review all the edit results manually yourself, or do you have some kind of automated pro…

  8. comment
    Comment #47209828

    Thanks - and no, I haven't seen this one. I like how they have the edit mode dashboard - show the original image + two edits; I was thinking about doing something like this. I'm al…

  9. story
    Show HN: Imagedojo.ai – Blind arena for Google, OpenAI, and xAI image generators

    Hi HN, I was curious which of the three major US AI labs generates images that people like more, so I built ImageDojo.ai. It shows you two images side-by-side, both generated from …

  10. comment
    Comment #46807350

    I would argue that it is a leader in vision-only FSD, which is useful for both self-driving and robots.

  11. comment
    Comment #46807342

    Thanks, these are fair arguments! Re: both 3 and 4(c) - agree that compute (or maybe even power for that compute) is likely to be a bottleneck in the next 3-5 years. However, I thi…

  12. comment
    Comment #46806132

    You might be more informed that I am. We only have 3 and Y in the family. I based my statement on th fact that S/X were last refreshed 5 years ago; so they would need to be refresh…

  13. comment
    Comment #46805984

    Shutting down low-volume, complex project, that needs to be substantially redesigned to be competitive, while these resources can be redeployed elsewhere, in high growth areas? I d…

  14. comment
    Comment #46805850

    Hard to tell whether you are serious or sarcastic, but assuming it's the former: my contrarian position on CC vs SaaS is that in the quest to kill shitty businesses people will dis…

  15. comment
    Comment #46805773

    "HN is dying" is a cliche, I know, but I seriously want to bookmark this thread to revisit it in 10 years - I'm sure it will age even better than (in)famous Dropbox thread. So from…

  16. story
  17. comment
    Comment #45838219

    Do people use Swift outside of Apple iOS/macOS development in real life? Especially on platforms like Windows/Linux/*BSD?

  18. comment
    Comment #45768661

    [flagged]

  19. comment
    Comment #45363680

    Prediction: the only remaining providers of AI-assisted tools in a few years will be the LLM companies themselves (think claude code, codex, gemini, future xai/Alibaba/etc.), via C…

  20. comment
    Comment #45363619

    Hm... why not tokens as reported by each LLM provider? They already handle pricing for images etc.

  21. comment
    Comment #44654593

    thank you, I stand corrected Update: Here is what o3 thinks about this topic: https://chatgpt.com/share/688030a9-8700-800b-8104-cca4cb1d0f...

  22. comment
    Comment #44654002

    Claude uses OpenAI-compatible APIs, and Claude Code respects environment variables that change the base url/token.

  23. comment
    Comment #43141135

    The most unexpected news to me was that Hacker News, apparently, runs on top of SBCL now, via a secret implementation of Arc in Common Lisp!

  24. comment
    Comment #42342704

    Thank you Josh. Is there a resource you can point us too that helps answer "what kind of MacBook pro memory do I need to run ABC model at XYZ quantization?"

  25. comment
    Comment #42342665

    But diluting OpenAi's (or any other company's, for that matter) market power does benefit the world.