Turns out you have to be Terence Tao to know when an LLM is right or wrong
is the similar statement true for coding as well?
i.e. You have to be a good engineer to understand the well generated LLM code and a program
You don't have to be as good as the model you are overseeing, but it sure helps, otherwise you will only be able to evaluate partial claims, missing mistakes, and potentially the big picture.
Yeah, so much for AI making mathematicians obsolete.
"I imagine my work could be completed with AI assistance in a matter of days—maybe hours."
Would some one with tokens to burn mind checking that statement out and post back. Be sure to use long dashes too.