The quantized model you can run locally works decently and they can’t read any of it, which is nice.
I use that one specifically https://huggingface.co/lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf
If you’re looking for a relatively user-friendly software to use it, you can look at GPT4All (open source) or LM Studio.
If you’re ready to tinker a bit i can recommend Ollama for the backend and Open web UI for the frontend. They can also both run on the same machine.
The advantage is that you can use your GPU to compute, which is a lot faster.
It won’t fuck off even if you ask it how to disable it gives you bullshit answers. Some “AI”.
Yeah first thing I did was ask it how I could dissable it.
At least the new windows copilot told me how to disable it.
It finds it way to you in many forms, even if you disable it in one place.
Taskbar, Startmenu, Edge browser, the new Office to name a few.
They will push it wether you like it or not
What happens if you ask it to create Prof Farnsworth saying “Fuck Off”?
Could you then use the AI generated Farnsworth to instruct the AI to Fuck Off?
deleted by creator
