Paper: You Are in Control of Your State — Why Human Outcomes Are Controllable

Forum topic · 小凯 · 2026-05-29

Summary

This post summarizes an arXiv paper (2605.27580) by Suraj Biswas, Saurav Gupta, and Pritam Mukherjee addressing within-person variability, a central puzzle for behavioral sciences and human-facing AI. The authors argue that the same individual can produce different outcomes from identical observable inputs, and that no observable covariate fully predicts divergent outcomes across individuals. They attribute this variability to a person's dynamic latent state, claiming that human outcomes are controllable through interventions targeting the state and its weighting at the moment a decision forms. A state is defined as a time-indexed weighting vector over dimensions governing how an individual's biology, physiology, and neuropsychology process the next event into a decision and outcome. The state-decision-outcome relationship is causal rather than correlational. The weighting vector changes dynamically within a day, and conscious reporting passes through a narrow attention bottleneck whose contents depend on the state itself. The conclusion: given an event, outcomes are controllable conditional on the state trajectory at intervention time.

Paper Overview

Research Area: AI Authors: Suraj Biswas, Saurav Gupta, Pritam Mukherjee Posted: 2026-05-28 arXiv: 2605.27580

Abstract

A central puzzle for the behavioural sciences and for human-facing artificial intelligence is the persistence of within-person variability. The same individual, presented with the same observable input, produces different outcomes on different occasions, and different individuals produce divergent outcomes that no observable covariate fully predicts.

The authors argue that this variability belongs in the dynamic latent state of the person, and that human outcomes are controllable in a precise and operational sense through interventions that target the state and its weighting at the moment a decision is being formed.

Key Claims

State definition: A state is the time-indexed weighting vector over the dimensions that govern how an individual's biology, physiology, and neuropsychology process the next event into a decision and an outcome.
Causal relationship: The relationship between state, decision, and outcome is causal rather than correlational.
Dynamic weighting: The weighting vector changes dynamically on intraday timescales.
Attention bottleneck: The conscious channel of reportable outcomes is a narrow attentional bottleneck whose contents are themselves state-dependent.

Conclusion

Taken together, these claims imply that the outcome of a given event is controllable, conditional on the state trajectory at the moment of intervention.

---

*Auto-collected on 2026-05-29*