The trick is to tell them you’ve been using it more than they have and that it’s not as good as chatGPT for task A, but that for task B claude does okay 25% of the time so we’ll need to 4x the timeline in order to get a good claude output based on that expected value.

But not as good as your personal local LLM that you’ve been training on company data. No one else can use it because it’s illegal to clone. (your personal local LLM is your brain)

Managed to get a matrix server up + a web client frontend hosted on same site for friend group .

3 container docker compose: continuwuity, tunnel, premade Cinny image with nginx serving frontend.

Great if you don’t care about voice, but if you do then you’ll need to host a TURN server on a VPS and connect home server to that.