Re:AI Was Supposed to Help Juniors Shine. Why Does It Mostly...
by nerpderp82 on Sunday September 21, 2025 @08:21AM
(#45322081)
Byzantine Incompleteness enters the chat.
Either you go formal, or you test the tests, and then test those ...
Re:AI Was Supposed to Help Juniors Shine. Why Does It Mostly...
by zdragnar on Sunday September 21, 2025 @10:17AM
(#45322949)
My last attempt had passing tests. It even exercised the code that it wrote! But, upon careful inspection, the test assertions were essentially checking that true equalled true, and the errors in the code didn't fail the tests at all.
Attempting to guide it to fixing the errors just introduced novel errors that it didn't make the first time around.
This is not what I signed up for.
What makes me nervous is when we generate both the implementation and the test cases. In what sense is this validation?