Live data from Hacker News

Viewing profile — betimsl

betimsl

HN member
Joined
Wed, Aug 05, 2015, 9:28 AM UTC
HN karma
123
Public activity
267 items

About betimsl

No profile information was provided.

Recent public activity

  1. comment
    Comment #48533074

    The problem with these is the tool calling. From my experiments qwen agent almost always fails with tool calling and porting the correct config is quite tedious. Rio3.5 with Qwen c…

  2. comment
    Comment #48533013

    what a legend!

  3. comment
    Comment #48297829

    PocketBase is awesome and this thing looks awesome. One question, I could not understand if a mail provider is needed or it handles on its own?

  4. comment
    Comment #46032172

    Could you please make the book into a PDF?

  5. comment
    Comment #45681551

    Who wrote the algorithm?

  6. comment
    Comment #45681539

    More important that if it is a good programmer or not, is to be able to spot if the guy can get the job DONE.

  7. comment
    Comment #45230039

    The story is that Ken and Rob were at a diner when Ken gave structure to it and wrote the initial encode/decode functions on napkins. UTF-8 is so simple yet it required a complex m…

  8. comment
    Comment #45167443

    Right, but Intel is in no position to do that. So, they could play and put 32GB VRAM and also, why not produce one with 64GB just for kicks?

  9. comment
    Comment #44591734

    Dream phone: Underclocked Samsung25 internals, iPhone SE design/dimensions, at least 90hz OLED panel, 1 back decent camera, 1 front too. 3A battery. Preferably an extenal SD card s…

  10. comment
  11. comment
    Comment #43807117

    I think you could easily give the UI a refresh, modernize it a bit :)

  12. comment
    Comment #43766646

    It's simply not Apple's responsibility. Person's data, their responsibility. Any other way and people lose trust in Apple which BTW they protect it by any means. Trust. Instead of …

  13. comment
    Comment #43756694

    Apple’s encryption, is designed with end-to-end encryption for many types of data. Some facts: Only the user's devices hold the keys to decrypt the data. Apple cannot decrypt it, e…

  14. comment
    Comment #43574626

    Uhoh! -- The virus just spread a litl more!

  15. comment
    Comment #43495622

    Check out NVIDIAs latest releases. Paying for tokens is going to be a history in about 6 months. You run the model on your laptop. Maybe you're right about the confusion...but give…

  16. comment
    Comment #43495540

    They probably screw the patients too.

  17. comment
    Comment #43495358

    Why separate? It's not like there's limited capacity...you can have an assistant knowing all the languages at once.

  18. comment
    Comment #43493464

    You have a typo in the snippet on README.md: SchlüsselWert should be Schlüsselwert.

  19. comment
    Comment #43382830

    > [...] This is to the point where is starts to become hard for you to work without one. Why would one work without one?

  20. comment
    Comment #43338549

    > Why? Huge interest in the field. Schools unable to teach the craft properly.

  21. comment
    Comment #43289707

    Glad that I'm not the only one doing just that.

  22. comment
    Comment #43280850

    Any chance open sourcing it? :)

  23. comment
    Comment #43218205

    Material tolerances.

  24. comment
    Comment #43208736

    Running a 7b coder in laptops with 4060 is possible and with very good results. Orra looks like a very good tool to be integrated with any IDE. Take a look at this: https://github.…

  25. comment
    Comment #43203659

    I mean, local LLM, for example: can it be run with llamafile instead of cloud AI?