Re:AI;DR (AI; Didn't Read)
by kqr on Tuesday August 18, 2026 @01:55AM
(#49341804)
Code-generating robots are pretty bad at property-based testing, in my experience. They can do it but they still need a lot of hand-holding. They often regress to writing a mirror implementation as the oracle and trying to enumerate a fixed set of examples they find meaningful.
[ Parent
| on HN ]
There are no comments on this comment yet.