OpenAI announced Superalignment, a new alignment research team aimed at steering and controlling AI systems much smarter than humans. Co-led by chief scientist Ilya Sutskever and Jan Leike, the team would dedicate 20% of the compute OpenAI had secured to date toward solving superintelligence alignment within four years. It drew attention as a major commitment to safety research.
5July 2023
ResearchConfirmed
Superalignment team launched
Participants
Tags
- safety
- alignment
Sources
Later developments
17 May 2024 · Development
In May 2024, co-leads Ilya Sutskever and Jan Leike left OpenAI in quick succession and the Superalignment team was dissolved less than a year after its launch. Leike criticized that "safety culture and processes have taken a backseat to shiny products," and remaining members were redistributed across other teams.