Mostly I use it to write unit tests (just dislike production code that is not exactly as I want). So there is a testing rule for all files in the test folder that lays out how they should be done. The agent writing the tests may miss some due to context bloat but the reviewer has a fresh context window and only looks at those rules. So it does result in some simpler code.

LLMs miss very important concepts, like the concept of a fact. There is no "true", just consensus text on the internet given a certain context. Like that study recently where LLMs gave wrong info if there was the biography of a poor person in the context.

A roomba was twice as much as a roborock that was better.

Prusa MK4S is 720 EUR, the arguably better Bambu Lab A1 is 260 EUR.

A turnip is female, the fishmongers wife is neutral, a boy is male, a girl is neutral, the wife is female. Plural of Tür is Türen plural of Öffnung is Öffnungen, plural of Vogel is Vögel plural of Fenster is.. Fenster.

Hundreds of unspoken rules regarding word order, some verbs that can be separated and others cannot.. Completely random.

And good luck even being able to hear the difference between spucken and spuken if your language doesn't have long vs. short vowels.