Martin Kleppmann argues that AI will make formal verification more accessible in software development. With advances in large language models, the process of writing proof scripts is becoming easier, potentially lowering costs and increasing the reliability of AI-generated code. As formal methods gain traction, the focus will shift to accurately defining specifications.

This article discusses the impact of AI on formal verification, highlighting both its potential and limitations. It explains the challenges of creating formal specifications for most software and critiques the reliability of autoformalization and proof assistants in the verification process.