What's astonishing to me is how quickly people at my workplace have adopted this habit. Six months ago my manager was vociferously complaining about his boss asking him to review a lengthy document that was clearly AI generated, saying that his boss wasn't even capable of understanding the document the LLM had created. Now the majority of technical communication I get from my manager is just a transcript exported directly from ChatGPT.

Recently on a call with a junior coworker where they asked me to look at some changes they had made, they were completely unable to answer any questions that I asked on their own. The way the conversation went was: I ask a question, they type my question into a ChatGPT prompt, we read the output together and discuss whether it makes sense. This is a person I've had great discussions with in the past, and who has frequently had really good insights, but seems to have completely tapped out.

To be fair, the outputs from ChatGPT tend to be quite good. It's the inputs people give it where problems most often arise - and people seem far too eager to charge ahead with a vibe coded solution built on invalid or incomplete inputs/assumptions. And it's shocking to see how quickly and willingly people have handed over control to LLMs.