First video on writing code with LLMs I’ve seen that is actually sensible, is well aware of limitations of LLMs, and gives solid advice.

It is possible to get good results, the problem is that you yourself need to have an very good understanding of the problem and how to solve it, and then accurately convey that to the AI.
Granted, I don’t work on embedded and I’d imagine there’s less code available for AI to train on than other fields.





It’s like guiding a coked up junior who can write 5000 wpm, has read every piece of documentation ever without understanding any of it.