Look Here, Then Decide
Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs
Most AI vulnerability research relies on very large, expensive models reasoning through code one file at a time. We asked a different question: can a small, fast model help find real vulnerabilities at scale, if the system around it is designed well? The answer was yes. A model small enough to run on a desktop computer, guided by tools that decide where to look, helped search more than 4,000 open source projects, and the campaign confirmed 187 memory-safety findings.
