You should just be able to give them secure access to your git repo and they can get an LLM to do a code review.

Yeah, because the obvious solution to the problem of having too much bots is… more bots.

can you link to data to prove the economics are bad?

yeah, just write a stub/wrapper around it and abstract. it's the classic coupling problem. nothing to do with CUDA

Chat Ui killed the GUI star. language is The ultimate UI. I guess you still need graphs (mainly so you can have dramatic moments in movies), but that's it

love that song! Not every interaction would be conversational, that's why we spent more than 50 years building GUI

doesn't this imply it would solve the halting problem?

No, practical programs don't need full Turing completeness. Most programs you want to write you intend to either halt or run indefinitely, because you want to avoid crashes.

my son is addicted to VR gorilla tag. I guess he'll be getting weep-eyed about it in 30 years :P

yeah, I think they will get smaller so they can be run everywhere, and really just be an interface to various non AI systems.

Or the same thing with a more interactive UI in the browser without installing anything: https://strudel.cc/workshop/getting-started/

I'm rarely vibing at the individual function level these days. If I was I'd probably use this to do the unit tests and then get the LLM to write the function from that.

Also, it seems one could get Claude to do this in 2 mins without making a whole IDE specifically for it?

Now days I use the LLM wiki idea to build a detailed spec up front before getting the agent to build the system. Keeps a record of the intent and you can get the agent to keep this updated with every change request.