Meta has applied large language models to mutation testing to improve compliance coverage across its software systems. The approach integrates LLM-generated mutants and tests into Meta's Automated Compliance Hardening system (ACH), addressing scalability and accuracy limits of traditional mutation testing. The system is intended to keep products and services safe while meeting compliance obligations at scale, helping teams satisfy global regulatory requirements more efficiently.
When you think about it, the moment you start describing what you want the AI to build - the behavior, the constraints, the flows, the edge cases - you're already writing specs. And if those specs are clear enough, the AI can turn them into code, and even into tests. Call it ai-Driven Development ( aiDD). Or vibe coding. But the pattern is the same: The better the spec you write, the better the code you get.