Goal Revelation as a Bridge Between Information-Theoretic Empowerment and Capability-Based Human Power
Read the original on arXiv AI →The paper investigates how to quantify power in AI systems by linking two concepts: information‑theoretic empowerment, which measures the capacity of an agent’s actions to influence future states, and capability‑based individual power, which assesses a human’s likelihood of achieving various goals. Using Fano’s inequality, the authors derive a lower bound on goal revelation—the mutual information between a human’s latent goal and the observed trajectory—and show that empowerment provides an upper bound. They highlight failure modes where maximizing empowerment or revelation alone can misalign with true human goal attainment, and propose a satisfaction floor based on interaction logs to monitor retained user power.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.