human evals on small teams with PyTorch

[mangopath4]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Would rather learn from your scars than collect my own all at once.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[cozysmith]

Interesting, I hadn't tried that. The pattern around small local stacks has been pretty similar for me.

[dockworks23]

I hit almost the same issue last night.