my take... this is exactly what happens when you have AI basically writing code. It's not capable enough for work like this and only focuses on the specific goal not the holistic approach.
my take... this is exactly what happens when you have AI basically writing code. It's not capable enough for work like this and only focuses on the specific goal not the holistic approach.
Writing code with AI is like having an enthusiastic intern high on drugs working for you. It will confidently tell you things that aren't true, use functions that never existed. But it's still helpful because it does the busy work, all you have to do is clean up its mistakes. But MS probably already uses AI for QA too.