Security TrustThe hard part of frontier agents is containmentAs agents become better at long-running work and computer use, the product boundary around their capabilities matters as much as the model itself.August 27 2026//1 min read#agents#ai security#cybersecurity#permissionsOpen post→
Security TrustBeing recognized as AI Security Innovator of the YearThe Hacker News Cybersecurity Stars Awards recognized me for the AI security work I have been building at Keeper.July 1 2026//2 min read#ai security#keeper#awardsOpen post→
Security TrustWinning the Opir Challenge by testing the edgesI won Wordcab's OPIR Challenge by probing where semantic guardrails get thin and where the classifier and generator diverge.June 29 2026//2 min read#opir#ai security#red teamingOpen post→