AI Control Hackathon 2026 - San Francisco - Apart Research

​AI Control Hackathon 2026 - San Francisco

​Building robust oversight mechanisms for advanced AI systems, alongside 500+ builders globally.

​The Event

​As AI systems grow more capable, the question shifts from whether they can do useful work to whether we can maintain meaningful oversight when they do. AI control research tackles this directly: building protocols that prevent bad outcomes even if an AI is actively trying to subvert safety measures. Join us at Mox for a weekend hackathon focused on building practical solutions for AI monitoring, containment, and oversight.

​Prizes & Opportunities

​Fully funded trip to ControlConf Berkeley (1st place) + Invitation to The Apart Fellowship* + $2,000 prize pool

​*Not all winning projects may receive a fellowship invitation. An invitation might also depend on other external factors like the Apart Core team's capacity to onboard new research teams.

​Co-organized with

​Redwood Research | Apart Research

​Hosted at Mox, San Francisco's research-focused community space for AI safety, frontier technology, and mission-driven work.