Captain_Stupid

@Captain_Stupid@lemmy.world

• ⁨Comment⁩ on ⁨hmmm⁩ ⁨⁨6⁩ ⁨days⁩ ago⁩:

  But I thought the jar always breaks…

• ⁨Comment⁩ on ⁨Can I self host a VPN that sneakies through the China firewall?⁩ ⁨⁨6⁩ ⁨days⁩ ago⁩:

  Social Credit --;

• ⁨Comment⁩ on ⁨The therapy I can afford⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:

  It’s alright, my second point was more something to keep in mind and not an acual argument against using AI for therapie.

• ⁨Comment⁩ on ⁨The therapy I can afford⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:

  That is not what I mean. I was talking about Sam Altman using your trauma as training data.

• ⁨Comment⁩ on ⁨The therapy I can afford⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:

  The smallest Modells that I run on my PC take about 6-8 GB of VRAM and would be very slow if I ran them purely with my CPU. So it is unlikely that you Phone has enough RAM and enough Cores to run a decent LLM smootly.

  If you still want to use selfhosted AI on you phone:

  • Install Ollama and OpenWebUI in a docker container (guides can be found on the internet)
  • Make sure they use your GPU (Some AMD Cards require an HSA override Flag to work
  • Make sure the docker container is secure (Blocking the Port for comunication outside of your network should work fine as long as you only use the AI Modell at home)
  • Get youself an openwight modell (I recomend llama 3.1 for 8 GB of VRAM and Phi4 if you got more or have enough RAM)
  • Type the IP-Adress and Port into the browser on your phone.

  You now can use selfhosted AI with your phone

• ⁨Comment⁩ on ⁨The therapy I can afford⁩ ⁨⁨1⁩ ⁨week⁩ ago⁩:

  If you use Ai for therapie atleast selfhost and keep in mind that its goal is not to help you but to have a conversation that statisvies you. You are basicly talking to a yes-man.

  Ollama with OpenWebUi is relativly easy to install, you can even use something like edge-tts to give it a Voice.

• ⁨Comment⁩ on ⁨NSA is the only government instution that actually listens to you⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  Dang Glowies