JAjauntywundrkind·Jul 2, 2025
There's a lot of truth here.
But also. But also, LLMs are incredibly powerful and capable tools at discovering and finding what the architecture of things is. They have amazing abilities to analyze huge code bases & to build documents and diagrams to map out the system. They can answer all manners of questions, to let us probe in.
I'm looking for good links here. I know I have run across some good stuff before. But uhh I guess this piece that I just found introduces the idea well enough. https://blog.promptlayer.com/llm-architecture-diagrams-a-pra...
And you can see an example in the ever excellent @simonw's review of prompts in copilot. At the end, they briefly look at testing, and it's a huge part of the code base. They ask Gemini for a summary and it spits out a beautiful massive document on how copilot testing works! https://simonwill
Read the rest
ison.net/2025/Jun/30/vscode-copilot-chat/ https://github.com/simonw/public-notes/blob/main/vs-code-cop...
Now, whether LLMs generate well architects systems is largely operator dependent. There's lots of low effort zero shot ways to give LLMs very little guidance and get out who knows what. But when I reflect on the fact that, for now, most code is legacy code, and most code is hideously under documented, most people reading code don't really have access to experts or artifacts to explain the code and it's architecture, my hope and belief is that LLMs are incredible tools to radically increase maintainability versus where we are now, that they are powerful peers in building the mental model of programming & systems.