Skip Navigation

Posts
5
Comments
6
Joined
3 yr. ago

  • It's done by software using an LLM, not just a raw LLM. They do only work with text, but you can get it to output the text "get_weather(mylocation)", and instead of just outputting that directly to the user, the software running on top of the LLM runs a " get_weather" function that calls some weather API. The result of that function is then output to the user.

    Any time you see an "AI" taking "actions", this is what happens in the background for every action.

  • I find Qwen3.5 is the best at toolcalling and agent use, otherwise Gemma4 is a very solid all-rounder and it should be the first you try. Tbh gpt-oss is still good to this day, are you running into any problems w it?

  • I had a similar problem, it was caused by undervoltage. Are you using the official power supply?

  • Or maybe they have the ability to make you weaker

  • Selfhosted @lemmy.world

    Fireshare: Selfhosted clip sharing with unique links

    github.com /ShaneIsrael/fireshare
  • Selfhosted @lemmy.world

    OpenBudgeteer: a selfhosted budgeting app made for Bucket Budgeting

    github.com /TheAxelander/OpenBudgeteer
  • Yep it's not near finished. This is one of those projects that's sat in my "keep an eye on it" bookmarks for a good while, I figured I'd post it to get some attention on it, because it does look very promising.

  • Selfhosted @lemmy.world

    SpacebarChat - a selfhosted, Discord-compatible communication platform

    github.com /spacebarchat/spacebarchat