I use LLMs whenever I'm coding, and it makes mistakes ~80% of the time. If you haven't seen it make a huge mistake, you may not be experienced enough to catch them.
I use LLMs whenever I'm coding, and it makes mistakes ~80% of the time. If you haven't seen it make a huge mistake, you may not be experienced enough to catch them.
Hallucinations, no. Mistakes, yes, of course. That's a matter of prompting.
> That's a matter of prompting.
So when I introduce a bug it's the PM's fault.