AIXI formula

AIXI is the leading mathematical model of artificial superintelligence, representing the maximum theoretical limit of AI capabilities. The AI X-risk Institute models AI risk factors and safety mitigations in terms of AIXI variants, and develops the means to translate them to real AI agents. This enables rigorous testing of both the risk factors and the safety mitigations.

Why this approach

Most AI research today sits in one of two categories: methods that are fast and mathematically clean in narrow settings, and methods that are practical for frontier applications but opaque to safety analysis. Our core niche is the third corner: methods that are general enough for powerful agents and provable enough to support rigorous safety claims. Aligning a hypothetical superintelligence requires a focused effort on the latter.

Venn diagram showing Fast, General, and Provable, with AIXI at the General+Provable overlap

This framing guides how we choose projects: prioritize ideas that survive formal analysis in broad environments, then port the strongest ones to modern LLM-based agents.

Basic Science

How do AI agents work? How do they (mis)generalize? What are their incentives?

Risk Factors

Would AI agents scheme to deceive or take power? Under what conditions? Can we reliably test for this?

Safety Mitigations

Do existing safety proposals generalize in the limit of high capabilities? Does modeling this limit suggest any new safety techniques?

For technical details, see our organization’s research output.

For broader educational resources, see our learning page.