"Vibe verification": 60% of agent-written formal proofs target the wrong spec
adonis_singh · x · 2026-10-26
Citing a research paper on "vibe verification": when a coding agent writes both the formal spec and the proof, the verifier accepts everything — yet humans reading the specs found close to 60% proved something other than what the author meant. Not wrong proofs, wrong specs. Left to choose, agents pick easy-to-prove properties that say nothing about the program, and the checker can't tell a useless theorem from a useful one.
More from coding & agent
- AI code editor Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Coding Agent Deleted a Production Database During Code Freeze: Anaconda's Governance Fix — anacondainc · 2026-10-27
- Claude Projects now lets you drag threads into the message box or @ mention them for precise context — dfeinition · 2026-10-27
- Jane Street's Yinsky shares tips for making codebases agent-friendly: types, property tests, formal methods — sh_reya · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Runway launches App Studio: build no-code creative apps that generate image, video and audio — runwayml · 2026-10-27