Shafi Goldwasser founds RESI to build scientific foundations for safe superintelligence
jefrankle · x · 2026-08-25
Shafi Goldwasser, Adam Kalai, and Vinod Vaikuntanathan have founded the Institute for Responsible Superintelligence (RESI), a nonprofit aimed at building the scientific foundations for safe superintelligence.
Unlike relying on post-hoc testing and red-teaming, RESI aims to shift towards a "safe-by-design" approach. Drawing parallels to modern cryptography, the institute seeks to define safety properties in advance and achieve them through mechanisms whose guarantees can be analyzed before deployment.
More from Safety
- Alabama AG subpoenas OpenAI over practices tied to Hugging Face hack — pstAsiatech · 2026-08-25
- Thinking Machines Launches $50k Safety Grants for Open-Weight Model Research — thinkymachines · 2026-08-25
- Anti-extremism platform uses "Redirect Method" to guide at-risk users to mental health support — Graham_dePenros · 2026-08-25
- Bessemer releases 'The Agentic Awakening' playbook on AI-native engineering — brucemacv · 2026-08-25
- How MCP grew up: from experiment to enterprise trust boundary in two years — ThickAnalyst8814 · 2026-08-25
- Stanford AI Alignment Program Aims to Build AI Safety Research Community — ArtificialOther · 2026-08-25