AI needs feedback just the same as humans. I would think of AI like a human that’s of average cleverness, but has a huge breadth of knowledge and basically infinite time and patience. They are going to be decent at assembly but they’re still going to make mistakes just like humans.
Using a language like Rust that has a lot of static correctness checks gives a higher quality result for AI, just like it does for humans.
AI doesn’t need feedback – you’re supposed to write “make no mistakes”. Why are you worrying about “static correctness checks” when AI can just write flawless assembly?
Assuming that’s a genuine question…
AI needs feedback just the same as humans. I would think of AI like a human that’s of average cleverness, but has a huge breadth of knowledge and basically infinite time and patience. They are going to be decent at assembly but they’re still going to make mistakes just like humans.
Using a language like Rust that has a lot of static correctness checks gives a higher quality result for AI, just like it does for humans.
AI doesn’t need feedback – you’re supposed to write “make no mistakes”. Why are you worrying about “static correctness checks” when AI can just write flawless assembly?