alt Hacker NewsMeh, if the LLM has a flawed logic it’ll implement bad code _and_ bad tests. Tests will pass, but the logic will still be broken.
Meh, if the LLM has a flawed logic it’ll implement bad code _and_ bad tests. Tests will pass, but the logic will still be broken.
How's that different from a regular human dev doing the same thing? Or an entire team of them.