These comments may seem silly at a glance, like joking about using WebMD instead of going to the doctor. But if this is the kind of unhealthy over-reliance on AI that OpenAI considers “cool,” we should all be worried.
These comments may seem silly at a glance, like joking about using WebMD instead of going to the doctor. But if this is the kind of unhealthy over-reliance on AI that OpenAI considers “cool,” we should all be worried.
Nope. It works very fine most of the time. You need to be clear what you ask for and not ask for too much at a time. You say : do a script that does a small part, test it then add a new part and so on.
I mostly do this while doing another task, using my free time during compile and server deploy time to advance on my next stuff.
You can’t just ask him to do full feature and hope it works properly, that’s a recipe for disaster.
You have to think like it like working with a junior dev.