My question is always: what are you building? You need to tell the AI what to build. What if it does it in a way that isn't what you want, or makes the buttom blue instead of red, or any number of other decisions?

AI can write the code, but not tell you what code you want it to write. In other words, how long are your specs? Either the LLM decides "whatever" or you have massive amounts of documentation to coordinate.

We still need to decide what to build, and some of the how. That is not automate-able, yet everyone seems to gloss over that bit.