Live data from Hacker News

Viewing profile — tidbeck

tidbeck

HN member
Joined
Wed, Jun 16, 2021, 7:30 AM UTC
HN karma
31
Public activity
25 items

About tidbeck

No profile information was provided.

Recent public activity

  1. comment
    Comment #49071552

    Comparing to Opus 5: Claude Opus 5 (Uncached Input $5/M Cached Input $0.50/M Output $25/M) but you also pay a premium on Cache write 25% for 5m and 100% for 1h.

  2. story
  3. comment
    Comment #48975143

    On Max plans, premium seats on Team plans, and premium seats on legacy seat-based Enterprise plans, Fable 5 will be a standard part of your plan.

  4. story
  5. comment
    Comment #48848349

    Guess it is efficient for attention.

  6. comment
    Comment #48809908

    Related to this, for our use case, setting thinking to high instead of low made tasks complete faster and cheaper (Gemini 3.0 flash). Other aspects are caching, often at 0.1X cost,…

  7. story
  8. comment
    Comment #48758539

    I really like this but feels like it does not really work on a Swedish keyboard layout (macOS), cannot input '$'. Tried both Alt+4 (how you actually input '$') which works in vim a…

  9. comment
    Comment #47984524

    While the accessibility tree is great in many aspects it has its own limitations for example when it comes to stacked views or lazy loading outside the viewport.

  10. comment
    Comment #46078194

    Looking at the examples on the front page it reminds me even more about Parse.

  11. comment
    Comment #45991863

    The Reuters article title is "Fabric made of Stone" (as it is made of coal and limestone), that is why it came to mind.

  12. comment
    Comment #45990722

    This makes me think about Vinylon[1] and this article from Reuters[2] [1] https://en.wikipedia.org/wiki/Vinylon [2] https://www.reuters.com/investigates/special-report/northkor...

  13. comment
    Comment #45804734

    Got a https://en.wikipedia.org/wiki/Leisure_Suit_Larry#Leisure_Sui... vibe from it.

  14. comment
    Comment #45772289

    What kind of tasks do you use it for?

  15. story
    Ask HN: Should we include our tech stack when talking about AI coding tools?

    I’ve noticed that when people share how well (or poorly) an LLM works for them, they rarely mention what stack they’re using. From my experience, the language, framework — and even…

  16. comment
    Comment #45643298

    How does this compare to https://huggingface.co/ibm-granite/granite-docling-258M in performance and how they work?

  17. comment
    Comment #45628293

    That is why I like the idea of having as much of the documentation as possible in code. Tests that describe how things are supposed to work, infrastructure as code the describes th…

  18. comment
    Comment #45533418

    Still seem to be down, a link for status updates: https://status.claude.com/incidents/6xlfx3mrb8ct

  19. comment
    Comment #45126002

    I have (Firefox on macOS), still easy to miss.

  20. comment
    Comment #44222622

    This is different from the Minimum Deployment, which I current have set to iOS 12.0 in Xcode 16.2.

  21. comment
    Comment #43857356

    Could you maybe make use of Simon Willsons [LLM lib/app]( https://github.com/simonw/llm )? It has great LLM support (just pass in the model to use) and records everything by defaul…

  22. comment
    Comment #41947044

    https://devenv.sh/ and Dev Containers are not the same thing.

  23. comment
    Comment #33544769

    I also prefer native clients so I have been using the https://mimestream.com/ beta and it has been working great for me.

  24. comment
    Comment #27941532

    Vimium (for Firefox at least) supports custom search engines so you can do: og my-search 'o' for open and 'g ' to select Google as search engine.

  25. comment
    Comment #27525887

    I had the same issue but your comment made me look up if there is something to do about it. Both things are possible https://github.com/ohmyzsh/ohmyzsh#getting-updates