In 92% of DeFi exploits AI security review flags underlying problem

[bearjaws]

The problem with AI security review is that it will often find dozen of non-issues that have to be investigated.

[GustavHartz]

Performance has gotten a lot better the last 6 months, at a level where we almost don't see it anymore at Cecuro.ai. PoC generation and multiple validation agents debating validity is the key differentiator. This is an ok paper on the topic https://arxiv.org/abs/2511.02780