Yeah obviously, and that’s the difference between “vibe coding” and “LLM assisted”

“self host an open model”. My dude, you need pretty beefy hardware to run a slow and shit model that won’t even compare to the 0.33x models you get with a copilot subscription.

“Sure you can leave, but this will end the stream marathon, the three of us will lose money over it, and our community will be quite upset with you. But yeah, you can leave. Alright.”