> I use AI for sure, but only on things that I can easily verify is correct

Where did I say I was struggling, I stated a preference, I even stated lived experience with using a coding agent and a chat based LLM interface and have a preference for the chat based version.

I don’t struggle to use modern tooling, I pointed out that the analogy is terrible and how my lived experience proves that, I do use LLMs in anger daily for coding tasks, I just don’t treat them like interns.

Many time the points I used indicate that what I am doing is not in the training set, when you work on hard problems you run into edge cases a little more reliably than when you don’t.

Stop defending a man you don’t know on the internet, his words defend him well enough and I can hope he just stops using that analogy because it is fundamentally flawed, which is the point of my comments. The rest of his comment makes perfect sense and is the way I use LLMs and have to work around their idiosyncrasies anyway.