I think more systematic testing. It seems the AI is pretty good at generating tests and validating them, so really filling out the places where testing is weak. I think we could do a lot more tests for each compiler pass. For example, I think getting the AI to generate tons of programs and validate that the types the compiler infers on each variable are what we expect them to be.
3 comments
[ 2.8 ms ] story [ 21.1 ms ] threadWould love to hear from more experienced folks (on either AI or compiler-side) over what could be done better.
How do you propose to complete it?