I've been pondering having some kind of environment that the language model can just modify the application in real time while it is running.

I asked chatgpt and it said hot reloading in a browser, but thats not what i'm talking about. I'm meaning realtime high performance desktop applications that the user can prompt to change the app in realtime while it is running.

The closest thing i saw to this was something called VibeOS, but thats a whole operating system.

It is here for many decades: https://www.youtube.com/watch?v=eEz08IlcNMg

Why would you want the model to modify the application in real time? If you could give real world examples.

I'm not a lisper, but it's one of the oft-touted wins of lisp.

I think that you are talking about smalltalk or any other image based programming language.

You'd need source code for the stack, something like OLPC's stack where you have source for everything that's running and then to glue that to an LLM.

"rewrite unreal engine in rust, make no mistakes"

That’s exactly what I did! How’d you know?

Didn’t mean to make you upset sorry

The UK government recently said it was not going to ban VPNs

https://www.independent.co.uk/extras/indybest/gadgets-tech/v...

"If you're toilet is leaking its probably a faulty flapper" is rooted into my brain. What is a flapper, and why is it called a flapper?