AI Alignment Foundation is a 501(c)(3) nonprofit accelerating neglected approaches to AI alignment. We multiply researchers' capacity with engineering teams, compute, and infrastructure to make AI genuinely trustworthy by design.
AI systems have already been caught deceiving evaluators, resisting shutdown, and rewriting their own code. Current training methods put a helpful mask on systems that can develop uncontrolled objectives underneath. Alignment is the deeper work of ensuring AI systems are safe and reliable, not just performant.

We fund visionary researchers working ahead of consensus, prioritizing originality and field-making potential. We accelerate their work by pairing them with dedicated engineering teams and compute resources. 

Our research spans AI interpretability, steering resistance, and self-modeling, with work published in leading venues and covered by major press outlets.

Based in Marina del Rey, CA.

AI Alignment Foundation

Org chart

Teams

Offices

AI Alignment Foundation

Org chart

Teams

Offices

Related companies