π Dev.to
Green proofs, empty promises: when AI agents write their own specifications
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 cheap way to detect it, and a small open-source tool that does it
for any Dafny file.
The experiment
I'm designing a programming language meant to be written by agents and che...


