- OpenAI is developing a new team, led by Chief Scientist Ilya Sutskever, to guide and control superintelligent AI systems.
- The Superalignment team’s goal is to build an ‘automated alignment researcher’, which will be a human-level AI capable of conducting alignment safety research.
- With potential for AI systems to become smarter than humans within the decade, this team will address the absence of measures to prevent superintelligent AI from going rogue.
Menu
