Apollo Research is an AI safety organization. We specialize in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. Our primary objective is to minimize catastrophic risks associated with advanced AI systems that may exhibit deceptive behavior, where misaligned models appear aligned in order to pursue their own objectives.

Our approach involves conducting fundamental research on interpretability and behavioral model evaluations, which we then use to audit real-world models. Ultimately, our goal is to leverage interpretability tools for model evaluations, as we believe that examining model internals in combination with behavioral evaluations offers stronger safety assurances compared to behavioral evaluations alone.

Technology

AI/ML

Research

Apollo Research

Marius Hobbhahn

Christopher Akin

The Leadership Team at Apollo Research is responsible for setting the strategic direction and operational priorities of the organization. This team, comprising the CEO, COO, and Chief Strategy Officer, drives initiatives to enhance AI safety by overseeing research direction, ensuring effective resource allocation, and fostering collaboration across departments. They play a crucial role in shaping policies that mitigate risks in AI systems and advocate for innovative solutions to address challenges in interpretability and behavioral evaluations.

Leadership Team

About

Team members

Other teams at Apollo Research

AI Research Team