I mean the power of the work machine really depends on what your needs are. Definitely should adapt to whatever your needs are.

  > And there's no way this thing would handle a useful local model

So if you have a setup like mine then it is fairly trivial to incorporate that (or anything else). Either way you'll need a machine that can do the local AI though. Either that is on your "work machine" or you run the AI on a separate machine. You could even rent a machine and as long as you add it to your Tailscale network then you're connected.

I strongly suggest having a workhorse machine and then let other devices be your terminal into it. Your terminals can be very cheap (or an old machine) or as suggested, your phone.

▲ zahlman 2 days ago | parent [-]

I appreciate the thought, but advice like this is completely irrelevant to my current circumstances (and personal principles) and would be very expensive (respectively, emotionally unpleasant) to implement.

▲

godelski 2 days ago | parent [-]

Just trying to help given that you responded. I'm happy to help you find solutions but the constraints might be too much, unfortunately. If you don't have a machine that can run local AI and don't have the funds to buy one then frankly it just isn't in the cards. But hey, if you don't want to use AI or at least willing to use non-local then the setup probably doesn't require you to spend a dime.

	▲	zahlman 2 days ago \| parent [-]
		(I wasn't looking for a solution, just giving my perspective.)