[tuan]

> LLMs are okay at coding, but at scale they build jumbled messes.

This reminds me of the day of Dreamweaver and the like. Everybody loved how quickly they could drag and drop UI components on a canvas, and the tool generated HTML code for them. It was great at the beginning, but when something didn't work correctly, you spent hours looking at spaghetti HTML code generated by the tool.

At least, back then, Dreamweaver used deterministic logic to generate the code. Now, you have AI with the capability to hallucinate...