Own layer · Capabilities
Stand up Center For Aisafety's own layer in a sandbox
Create a Gov Hub / Canopi stewardship container for Center For Aisafety and run the first overlay on a public page you already control. Vicariance (sandbox before scale) keeps this from becoming a population-wide experiment on day one.
Hypothesis until sources are confirmed.
Cited mission: “The internal dynamics of the ML field are not immediately obvious to the casual observer.” Own-layer work is the smallest way to extend capability without leaving that mission for a captured platform.
Primitives: community-layer, application-layer, canopi-overlay
- A Bird's Eye View of the ML Field | CAIS
- AI Safety, Ethics, and Society | CAIS
- Biosecurity and AI: Risks and Opportunities | CAIS
- Cybersecurity and AI: The Evolving Security Landscape | CAIS
- Devising ML Metrics | CAIS
- Superhuman Automated Forecasting | CAIS
- Submit Your Toughest Questions for Humanity's Last Exam | CAIS
- Josué Estrada Joins Center for AI Safety as Chief Operating Officer | CAIS
- blog · leading-ai-companies-join-white-houses-voluntary-commitment-to-enhance-ai-safety
- Representation Engineering: a New Way of Understanding Models | CAIS
