alt Hacker Newsgenuine question, let us say you took the source code of every single engine you see here and feed it to all the 10000 llms and ask them to analyze the code, optimize every function the best way they see fit, make architectural changes as and when they see appropriate, what do you think will be the result from cutting edge models?
Considering the relatively limited context window even on the latest models, the output would likely be incoherent mess. Sure, you could make the LLM go through the code in easily digestible chunks (file by file) but to get any groundbreaking optimization, it would need to have the context of the entire project to properly understand the architecture. (IMO that is, I'm not an expert)