Live data from Hacker News

Viewing profile — ctbellmar

ctbellmar

HN member
Joined
Mon, May 26, 2025, 11:59 AM UTC
HN karma
23
Public activity
15 items

About ctbellmar

No profile information was provided.

Recent public activity

  1. comment
    Comment #48036791

    I had the same experience with 31B. Runs well on 4090 too!

  2. story
  3. comment
    Comment #47777257

    Glad it helps. As for narrow classifiers, it's decision tree logic as you say, and best done via trial and error than over-engineering and theory. Cleverness comes from your own ex…

  4. comment
    Comment #47761582

    That's the idea - hence PlantLab, not CannaLab. Cannabis makes sense as the entry point because it's a cash crop with a big hobbyist scene, so there's enough interest to get real u…

  5. comment
    Comment #47761573

    Thanks! Yeah, the single-species focus does a lot of the work. Under the hood it's not one big model - there's a cannabis verification gate, then routing into disease vs pest vs de…

  6. comment
    Comment #47751614

    PlantLab ( https://plantlab.ai ) - AI plant health diagnosis for cannabis. It's an API, not an app [1]. Photo in, structured JSON out - condition, confidence, growth stage, nutrien…

  7. comment
    Comment #45641135

    Various AI services (e.g. Perplexity) are down as well

  8. comment
    Comment #45579409

    They sent out emails to existing customers yesterday, showing if you are above/below/at average usage. I'm above (no surprise), and I wonder if anyone on higher plans will find the…

  9. comment
    Comment #45579399

    Pawel, This looks promising! Is it for text based models only at this time (i.e. no vision/image training)?

  10. comment
    Comment #44912719

    I wrote a tool that may be just the thing for you: https://github.com/bikemazzell/skald-go/ Just speech to text, CLI only, and it can paste into whatever app you have open.

  11. comment
    Comment #44866494

    I wonder how well Augment system will play with both of these. I recall that for some time, Cursor worked really well with Claude LLMs and less so with OpenAI's offerings like GPT …

  12. comment
    Comment #44866455

    I know it's been mentioned a few times, but worth repeating: these LLMs tend to do noticeably better in their own native environments. Claude (Opus or Sonnet) in Copilot != Claude …

  13. comment
    Comment #44864424

    "Qwen3-Coder ... is the first open-source model I’ve been able to accept patches from. It isn’t by any means a Claude killer, but it feels like Claude 3.7 Sonnet, maybe even better…

  14. comment
    Comment #44864360

    I had some time for in depth experiments with it this summer and was disappointed. It gets the surface level details alright, but falls apart on any detailed work. Examples that fa…

  15. comment
    Comment #44096624

    WhatSignal, WhatsApp Signal relay, written in Go https://github.com/bikemazzell/whatsignal I'm working on a WhatsApp to Signal relay. I.e.: whenever someone sends a WA message to y…