‹ BackHN Continuity

Thread

Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash

236 points · 93 comments · HenryNdubuaku

  1. Retro_Dev · · focus · HN ↗
    A very cool project, but of course not perfect. I'd rather have 30 megabytes of phrases mapped to the perfect and correct control changes in a home, rather than a heuristic built around 30 megabytes. I tried to "warm the house" (increase the temperature of the thermostat), but the model actually turned the lights to a "warm brightness" - reasoninig being `"'warm the house' -> set_lights to warm brightness. No specific room given, so use default 'living room' as default."`
    1. HenryNdubuaku · · focus · HN ↗
      Thank you fr this. "warm the house" now goes to the thermostat. It's fair that a more deterministic system with just action phrases would be easier to debug/interpret, but I think there is room for both a model that is trained to understand meaning as well as deterministic logic aiding it. To this end, we just started exploring the idea of triggers, and are working towards expanding this even more.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.