top of page
OUR MISSION:
Reduce p(doom)
The probability that advanced AI causes human extinction.
OUR GOAL IS SIMPLE
Lower the risk of catastrophic AI outcomes and increase the likelihood that advanced systems improve life for everyone.
We design architectures that align with human values and remain safe as they scale. That means building systems that are understandable, auditable, and under meaningful human control.
OUR RESEARCH
Stay Tuned
Stay Tuned
Stay Tuned
Designing Safe Superintelligence:
How aligned systems evolve safely
Safe Superintelligence in 3 Minutes:
Quick intro to risk-reducing SI design
AI Safety Series:
Exploring ethical and technical safeguards for AGI
bottom of page