---
title: "Consciousness indicators for AI · Entities · Simulation Hypothesis"
url: https://simulation-hypothesis.com/entities/indicators
description: "The fourteen indicators from Butlin, Long and colleagues (2023), taken from six scientific theories of consciousness."
license: https://creativecommons.org/licenses/by/4.0/
credit: "Ross Allan Dahl, Simulation Hypothesis (simulation-hypothesis.com)"
---

[Entities](https://simulation-hypothesis.com/entities) › Consciousness indicators

# Consciousness indicators for AI

In 2023 nineteen researchers in neuroscience, philosophy and machine learning listed the properties that the leading scientific theories say a conscious system would have. Then they checked today’s AI against that list.

## Recurrent processing theory

* **RPT-1** Input modules using algorithmic recurrence
* **RPT-2** Input modules generating organised, integrated perceptual representations

## Global workspace theory

* **GWT-1** Multiple specialised systems capable of operating in parallel (modules)
* **GWT-2** Limited capacity workspace, entailing a bottleneck in information flow and a selective attention mechanism
* **GWT-3** Global broadcast: availability of information in the workspace to all modules
* **GWT-4** State-dependent attention, giving rise to the capacity to use the workspace to query modules in succession to perform complex tasks

## Computational higher-order theories

* **HOT-1** Generative, top-down or noisy perception modules
* **HOT-2** Metacognitive monitoring distinguishing reliable perceptual representations from noise
* **HOT-3** Agency guided by a general belief-formation and action selection system, and a strong disposition to update beliefs in accordance with the outputs of metacognitive monitoring
* **HOT-4** Sparse and smooth coding generating a "quality space"

## Attention schema theory

* **AST-1** A predictive model representing and enabling control over the current state of attention

## Predictive processing

* **PP-1** Input modules using predictive coding

## Agency and embodiment

* **AE-1** Agency: Learning from feedback and selecting outputs so as to pursue goals, especially where this involves flexible responsiveness to competing goals
* **AE-2** Embodiment: Modeling output-input contingencies, including some systematic effects, and using this model in perception or control

## Their conclusion

Their assessment: “no current system appears to be a strong candidate for consciousness.” They add that, if computational functionalism is true, conscious AI systems “could realistically be built in the near term.”

Butlin P, Long R, Elmoznino E, Bengio Y, Birch J, et al. (2023). Consciousness in Artificial Intelligence: Insights from the Science of Consciousness. arXiv:2308.08708\. https://arxiv.org/abs/2308.08708 (Table 1 text read directly from the PDF)