Why it matters
Ari Herbert-Voss reviews three years of progress in autonomous offensive-security systems, evaluates where they can already complete meaningful attack tasks, and separates those capabilities from work that still needs human expertise. The talk frames scalable, parallel attack simulation as a challenge to point-in-time testing rather than as a product announcement.
My takeaway: Measure autonomous offensive systems by verified task completion, time, cost, false positives, and required human intervention. Use the resulting evidence to choose bounded continuous-testing workloads, preserve expert review for ambiguous findings, and prevent automated attack paths from reaching unauthorized targets.