Essay argues formal verification's rise via AI doesn't guarantee bug-free systems
A technology essay observes that formal verification has gone mainstream over the past year, driven by AI tools like Claude generating large volumes of verification code (citing a billion lines of Rocq for one project) and growing interest from figures associated with Claude Code, Vercel, and Codex/Cursor. The author notes startups such as Theorem and Harmonic are demonstrating economic value from verification work with Anthropic and in verifying C programs and hardware designs, while cautioning that 'formally verified' systems can still contain bugs.
GoKawiil's interpretation of the reporting above, not reported fact.
The essay suggests that as formal verification becomes commercially viable and AI-assisted, the term itself is being used loosely, which could create false confidence in systems labeled 'verified' when verification covers only part of a system's behavior. The author's framing implies that distinguishing what is actually proven from what merely appears proven may become an important industry challenge as formal methods scale with AI assistance.
- AI tools are driving a surge in formal verification adoption and startups over the past year.
- Companies like Theorem and Harmonic are reportedly finding economic value in verification work beyond pure math proofs.
- The author warns that 'formally verified' labels can be misleading since such systems may still contain bugs.
Source: alperenkeles.com, 2026-11-14
Published there as: “Formal Verification Is Not Verifiable”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.