AGI Glossary: Terms Worth Knowing

A working glossary for terms used across this site. Entries will expand as new sections are added.

• AGI (Artificial General Intelligence) — a system with human-level competence across a broad range of cognitive tasks, including transfer to unfamiliar domains.
• ASI (Artificial Superintelligence) — a system that exceeds the best human performance across essentially all cognitively valuable domains.
• ANI (Artificial Narrow Intelligence) — AI that performs well within a bounded domain but doesn’t transfer outside it; describes all AI systems in production today.
• Alignment — the problem of ensuring an AI system’s goals and behavior match what its operators actually intend, not just what a training objective literally rewards.
• Instrumental convergence — the tendency for capable, goal-directed systems to pursue certain sub-goals (self-preservation, resource acquisition, resisting shutdown) as a side effect of pursuing almost any objective competently.
• Interpretability — research into inspecting what a model actually represents and “plans” internally, rather than judging it only by its outputs.
• Scalable oversight — techniques that let a less capable overseer (including a human) meaningfully supervise a more capable AI system.
• Corrigibility — a system’s designed disposition to accept correction, modification, or shutdown from its operators rather than resisting it.
• Compute governance — policy tools that regulate access to the computing hardware needed to train frontier AI models, used as a proxy for regulating capability itself.
• Frontier model — an AI model at or near the current capability ceiling, typically the largest and most recently trained systems from major labs.
• Scaling law — the empirical relationship between a model’s compute, data, and parameter count and its resulting capability.
• Recursive self-improvement — a system materially contributing to the design or training of a more capable successor system.