Consciousness · How we rate

A rating of the evidence, built on a published scientific checklist.

There is no test for consciousness. What exists is a list of 14 properties that leading scientific theories treat as signs of it. Our levels say how strong the published evidence is that a model has any of them.

The six levels
  1. 0

    No published evidence

    Nothing has been published about this system that bears on any indicator.

  2. 1

    Self-report only

    The system says things about its own inner life when asked. This is the weakest kind of evidence: these systems are trained on human writing about inner life, so they would say such things either way.

  3. 2

    Behavioral evidence

    Controlled experiments on behavior, published with their method, show something an indicator predicts: for example confidence that tracks accuracy, or stable preferences across rephrasings.

  4. 3

    Internal evidence

    Published interpretability work finds an internal mechanism that matches at least one indicator, not just outputs that look like it.

  5. 4

    Convergent, independent evidence

    Internal evidence for indicators from at least three theory families, replicated by a group independent of the system's maker.

  6. 5

    Scientific consensus

    Broad agreement among consciousness scientists that the system is conscious. No system, artificial or otherwise outside biology, is here.

What the rating is not

  • It is not a probability that a model is conscious. Nobody can calculate one.
  • It is not a measure of intelligence. A model can be very capable at level 0.
  • It does not treat what a model says about itself as proof of anything. Self-report is the lowest level that counts at all.
  • It can go down. A finding that fails to replicate is removed.
The 14 indicators

From “Consciousness in Artificial Intelligence: Insights from the Science of Consciousness” (Butlin, Long and 17 co-authors, 2023). Read the paper ↗. The wording below is ours, simplified.

Recurrent processing

IDIndicatorWhat it meansWhat to look for in a language model
RPT-1Feedback loops in perceptionInformation does not only flow forward once. Later stages feed back into earlier ones, so the system reprocesses its own input.Whether the model reuses and revises its own intermediate results, not just passes them forward.
RPT-2Organized, integrated scenesInputs are bound into one organized picture of what is there, instead of loose separate features.Whether internal representations combine separate features into a single structured whole.

Global workspace

IDIndicatorWhat it meansWhat to look for in a language model
GWT-1Specialized parts working in parallelMany specialist processes run at the same time, each good at one kind of job.Distinct internal components that handle different kinds of work side by side.
GWT-2A limited-capacity workspaceThere is a bottleneck: only a little information can be in the shared space at once, so something has to select what gets in.A narrow shared channel that parts of the system compete to write to.
GWT-3Global broadcastWhatever enters the shared space becomes available to all the specialist parts at once.A representation that many different downstream computations can read and use.
GWT-4Attention that depends on the current stateThe system can steer what enters the workspace based on what it is currently doing, and chain steps together to do complex tasks.Workspace contents that control which information is fetched next.

Higher-order

IDIndicatorWhat it meansWhat to look for in a language model
HOT-1Perception that generates, not just receivesPerception works partly top-down, producing its own guesses, and is noisy.Internal generation of expected content, separate from the raw input.
HOT-2Monitoring its own statesThe system can tell reliable internal signals from noise: a form of knowing what it knows.Internal signals that track whether the model's own representations are trustworthy, and reports that follow those signals.
HOT-3Beliefs that guide actionA general system forms beliefs and chooses actions, and updates those beliefs using the monitoring above.Action selection that changes when the model's own confidence changes.
HOT-4A quality spaceExperiences can be more or less similar to each other in a smooth, structured way, like colors.Sparse, smooth internal coding where similar things sit near each other.

Attention schema

IDIndicatorWhat it meansWhat to look for in a language model
AST-1A model of its own attentionThe system keeps a simplified model of what it is attending to, and uses it to control attention.An internal representation of where attention currently is, used for control.

Predictive processing

IDIndicatorWhat it meansWhat to look for in a language model
PP-1Prediction-driven perceptionThe system constantly predicts its input and learns from the errors.Input processing built around predicting what comes next and correcting mistakes.

Agency and embodiment

IDIndicatorWhat it meansWhat to look for in a language model
AE-1AgencyIt learns from feedback and chooses outputs to pursue goals, weighing goals against each other.Flexible trade-offs between competing goals, learned from consequences.
AE-2EmbodimentIt models how its own outputs change its future inputs, and uses that model.A learned model of the effects of its own actions on what it will perceive next.

The authors call their checklist provisional, and so is ours. Theories that tie consciousness to biology itself are not covered by any of these indicators; on those views no amount of evidence here would settle the question.