Green proofs, empty promises: when AI agents write their own specifications
This story is from 2026-10-21. It is preserved in the archive; the latest stories are on the live feed.
I asked AI coding agents to write formally verified code. Every solution passed the verifier. Then I checked what the proofs actually promised. For the smaller model, 5 of 8 specifications barely said anything . One of the methods was wrong, and its proof was green. This post is about that gap, a c…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-21 07:44 · DEV Community — AI
Green proofs, empty promises: when AI agents write their own specifications