[–] 3 points 13 hours ago

I don’t use Joplin, but I do use an iOS app called “Synctrain” to sync my Obsidian vault with my server running Syncthing. It has worked extremely well for a couple years. The only “issue” is the iOS app appears slow to respond (30 seconds or so until the server is listed as “online”).

  • source
  • [–] 2 points 1 week ago (2 children)

    Genuine question: Am I missing something? I use Ubuntu and never use the Snap store. I only use the apt repository to install applications I find online. What is the advantage of Flathub over my current setup?

  • source
  • parent
  • context
  • [–] 8 points 5 months ago (1 child)

    Super good! Been using T2-Linux (Mint) for a year now and it’s been great. I had to fiddle with the WiFi but everything else works as expected. My work computer died, so I used it as a work laptop for several months with no issues. It pretty much refuses to run any games on Steam, but mine is a MacBook Air and I don’t think its specs would do much in that regard anyways.

  • source
  • [–] [S] 1 point 6 months ago

    Nice! These are great suggestions, and I apologize for any incorrect terminology in my post. To clarify, the vanilla / default Home Assistant can get the forecast correct every time. I just want that model to take the wheel when simple commands come through and then an LLM takes the wheel when asked random questions unrelated to home automation.

  • source
  •  

    I mostly understand the dilemma, but I want to see if someone has better success with their AI assistant. I use the Ollama integration and set up a conversation model. However, the default Home Assistant AI knows to use the home forecast entity whenever I ask about the weather. Whether I also set up an AI task model, toggle “control Home Assistant” on or off, or toggle “perform local commands” on or off - the Ollama models do not reference the home forecast the way the default Home Assistant can. I thought maybe keeping default commands on would enable this ability while answering all other queries with the Ollama LLM. I just want a smarter AI. Any suggestions?