Foundational Research Institute

From H+Pedia
Jump to: navigation, search

The Foundational Research Institute studies cooperative strategies for reducing risks of astronomical future suffering (s-risks). For instance, some of their research has been on suffering-focused AI safety; unlike other AI safety research, this focuses on preventing the worst (dystopian) outcomes rather than ensuring that the best possible (utopian) outcomes are realized.[1]

External links

References

  1. Suffering-focused AI safety: Why "fail-safe" measures might be our top intervention