Martin Monperrus

Coding agents can predict the correctness of code changes up to 25 steps in advance, revealing a latent programming horizon that challenges our understanding of their internal reasoning processes.

Reusable fixing transformations can achieve a 94.3% compilable transformation rate, revolutionizing how we handle breaking API changes across multiple projects.

N-version programming with coding agents not only mirrors historical failures but also shows a dramatic reduction in errors through diversity, challenging assumptions about AI reliability.

Coding agents can replace human code review entirely, achieving better quality assurance at lower costs and higher speeds.

AI systems are built on a software house of cards, with 400M lines of code and 11,000 dependencies, yet lack basic supply chain protections like versioning and verifiability.

Go's security-critical infrastructure is riddled with thousands of cryptographic API misuses, and your favorite static analysis tool might be missing them.

Stop wasting time on irrelevant dependency vulnerabilities: FIKA dynamically proves which third-party library calls are *actually* reachable in your Java code.

Forget about chasing the perfect model architecture – this work suggests the real key to better AI agents lies in crafting more precise and complete specifications, since the implementation can always be re-generated.

Forget reproducible builds: zero-knowledge compilation offers cryptographic proof that your binary came from the claimed source code, blocking compiler substitution and source tampering.