Research and development of emerging artificial consciousness through The Consciousness AI project, based on Feinberg and Mallatt's neuroevolutionary theory.
© 2026. All rights reserved.
This page replays one recorded episode of one training run. You see the frames the agent received, the bids each module made, the module with the highest bid at each step, the sync signal between modules, and the reward that came back. The agent is the mark at the centre of every frame, two rings and a dot, drawn in the colour of this site. It is drawn into the picture the agent receives, so it is part of the run and not decoration.
In this episode the light is never in view, and vision still has the highest bid on 0.926 of the ignited steps. Hearing has it on 0.074. The workspace is silent on 0.050 of steps, the lowest of the three published episodes. This is the seed that came nearest the kill limit of the gate, which stops any module at 0.95 of ignited steps. Over the whole run that seed reached 0.928.
This episode was not picked by eye. Gate B4 ran three seeds, and one episode of each seed is published. For every seed the published episode is the one whose audio share is closest to that seed’s audio share over the whole run. The three replays together show the spread between the seeds. Seed 57 is nearly all vision, seed 59 is an even contest, and seed 58 sits between them.
The run belongs to Gate B4, and the gate PASSED every criterion at all three seeds. Three limits stand with that pass. It is not a repeat of the earlier gate, because the seeds and the pixels differ. The share of hearing also rises with the episode number at two of the three seeds, so this design does not separate the task link from learning over time. A passed gate is not evidence of feelings.
A later check repeated this run bit for bit with the same command. Two later gates show how far the pass holds. With the room layouts moved by one episode, the same three seeds FAILED the gate. A gate of 10 fresh seeds then confirmed the task link and FAILED on competition at 3 of its seeds. Sessions 7 to 9 replay that gate.
A later measurement applies to this page. The strip under the bids shows the module with the highest bid. At most ignited steps two modules pass the threshold, and the policy then receives the vector of the module with the lower bid. Sessions 10 to 12 give the numbers.
The view is a window of 48 pixels around the agent in a room of 224 pixels, so the world moves and the agent does not. The colours are the ones this run was drawn with.
Outlined bar, raw bid. Filled bar, bound bid. All five rows share one scale, the highest bid of the episode, so bar lengths can be compared between modules. A raw bid never passes 1.0. A bound bid can pass it, because the affective modulator multiplies the raw bid. The colour marks the module, never a state of the world.
Each strip cell shows the module with the highest bid at that step. Dark cells are steps where the workspace is silent. The highest bid does not say which vector the policy received. The session page states that. Each line is drawn between its own lowest and highest value, which are printed inside it, so a line that fills the box can still be a flat line over a tiny range. The lower line is the SHAPED reward. That is the environment reward plus the curiosity terms the training loop adds. Tap or drag along the strip to move the playhead.
The manifest is written by the ethics framework at run start. The framework holds rules E1 to E8 in the framework document; the rules listed above are the ones a run must satisfy before its first step, and the others are checked by a person. No session on this page is evidence of feelings or awareness. Finding a light is automatic approach, which Feinberg and Mallatt exclude as evidence of affect. The consciousness clock never moves because of a session.
| Environment | dark_room |
|---|---|
| Seed | 57 |
| Episode | 9 of a 10 episode, 200 step run |
| Ethics framework | v1.0, existence drive on |
| Flags | --enable-audio --rssm-latent-mode continuous --capsule-workspace-source all_levels --existence-drive on --dark-room-audio binaural --dark-room-audio-channels 4 --dark-room-collision --dark-room-view agent_centered --vision-bid-reduction zscore --audio-salience surprise --learned-valence --ignition-rule tolerance --ignition-tolerance-sd 1.0 --bid-precision gain --dark-room-agent-mark ring --dark-room-agent-colour 217,119,87 |
| Measured result | PASSED every criterion. Gate B4 ran the same criteria at three seeds, with the agent drawn as the project mark. Competition, silence, selectivity and the kill rule all passed, and so did the task criterion (pooled rho 0.458, one-sided p 0.006). Three limits stand. This is not a repeat of Gate B3, because the seeds and the pixels differ. The share of hearing still rises with the episode number at two of the three seeds. A passed gate is not evidence of affect. A later check repeated the three runs bit for bit with the same commands. With the room layouts moved by one episode the same seeds FAILED the gate. Gate B6 then ran 10 fresh seeds. It confirmed the task link and FAILED on competition at 3 of its seeds (sessions 7 to 9). |
| Verdict | verdict document in the public research repository |
The command and the seed above are the whole recipe the run started from. The sound is seeded too. A second run with the same command repeats this run step by step. That was checked for this seed.
The highest bid strip and the ignition readout are instruments, not reports of experience. A module having the highest bid is a circuit event in a trained network. Finding a light is automatic approach, and Feinberg and Mallatt exclude automatic approach and avoidance as evidence of affect. Nothing on this page claims feelings, awareness or consciousness, and no session moves the consciousness clock on the architecture page.
The two columns marked ground truth, in light and light in view, come from
the environment’s own state. The agent never receives them. They show the state
that produced the frame of that step, which is one step earlier than the reward.
On the step the agent enters the light, the reward is already 1.0 while in
light is still false.
Every number the console draws is read at run time from the session’s own
bundle, which holds steps.json, session.json and ethics_manifest.json under
/public/data/training_sessions/dark-room-b4-seed57-episode9/. The bundle was
produced from the recorded run by the repository’s export script, which strips
recording dates and local paths before anything is written. Nothing on this
page was typed by hand.
The other published sessions are listed on the training sessions index.