Ask HN: Has anyone shipped a self-modifying application with LLMs?
I'm wondering if anyone has shipped a self-modifying application using LLMs. Traditionally, software is shipped as a fixed application, and users needing custom functionality have to install plugins or create their own, which is often not feasible for non-technical users. I'm thinking about an application that could have a prompt box to build extensions dynamically on the fly, like 'make me a UI panel with some buttons that does X.' Obviously, it would be 'use at your own risk' and YMMV. Have any companies or applications actually done something like this? I think modifying the real source code could get out of hand, but perhaps just generating extensions that have access to a sandboxed set of safer APIs.
Yes actually, on my GitHub account I shared a self modifying IDE (it can brick itself) [0] You can connect a model via an open router or Anthropic app key, and file tickets for an llm to “go to town” on editing the IDE itself The entire IDE code is editable (everything) in the IDE itself [0] - https://con-dog.github.io/slices-demo/
Arguably that's what BI tools like Tableau and Looker do. Or advanced uses of Excel, which an LLM can help with. The user has data and wants to slice it up and see it in a specific way and have some knobs to play with it to figure out answers to questions as a data scientist.
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
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.