Status: Published
Rewind-Bench on Devpost
The Devpost write-up of Rewind-Bench, catching AI code repairs that only look correct, submitted to Impact Forge Summer 2026.
Writing
No posts are published on this site yet. These pieces were published elsewhere.
Status: Published
Rewind-Bench: results report
The Rewind-Bench results report: injected bugs, three agent arms, and the accepted fixes that failed once re-run on a hidden seed.