The main point of the article is not what the title claims but the fact that ChatGPT sucks big time for troubleshooting since even the terminal commands are nonsense.
Why is there this massive disparity in experience? Is it the automatic routing that ChatGPT auto is doing? Does it just so happen that I've hit all the "common" issues (one was flashing an ESP32 to play around with WiFi motion detection - https://github.com/francescopace/espectre) but even then, I just don't get this "ChatGPT is shit" output that even the author is seeing.
And they don’t provide the prompt, so you can’t really verify if a proper model has the same issues.