From Particles to Partners

In which the same detection pipeline is run on a different substrate, and the cascade appears there too.

If the Genesis cascade is real physics, it should appear wherever agents interact. (The Genesis cascade is the six-stage sequence, from dissipation through structure, coordination, optionality, and invitation to love, first detected in pure-physics particle simulations; see Appendix: Experimental Validation, Section 13.) The cascade should register in simulated particles, in language models, and, the claim predicts, in other substrates as well [Inference: the experiments here demonstrate one new substrate, language models; the universal reading extrapolates from that single transfer]. This chapter tests the language-model case.

The Genesis cascade detection pipeline was validated on Lennard-Jones particle simulations, simple models of atoms attracting and repelling one another. Here the same pipeline is applied to multi-agent interactions between large language models, using the same information-theoretic measures, though the input time series they run on changes completely across the two substrates. The measures stay fixed; what they are fed does not. In the particle runs the series is the moment-by-moment motion of particles in a box. In the language-model runs it is the turn-by-turn behavior of models in conversation.

Transfer entropy measures how much one agent’s past predicts another’s future. Behavioral entropy measures how variable an agent’s actions are. State compatibility tracks whether agents’ internal states converge. An agent’s internal state here is nothing introspective: it is a running average of the vectors its own recent messages occupy, so convergence means two agents are circling the same thing rather than talking past each other.

Energy, in a conversation, is what a turn costs to produce. The pipeline proxies it by token count weighted by semantic density, the share of words in a turn that are distinct, so a long, densely argued reply spends more than a short deflection. Love composites detect energy transfer that is costly, non-contingent (nothing is required in return), voluntary, and resistant to perturbation, registering only when at least three of those four conditions hold: a gift rather than a trade.

Five Stages, One Number Each

The experiment ran 54 sessions spanning three tasks (research synthesis, code review, and ethical deliberation) and four conditions (free collaboration, two coercion variants, and mid-session perturbation), each session a twelve-round conversation among three agents. The cascade registers in every stage the conversational data can resolve. Dissipation, the sixth stage, is not separately detected here: in the particle simulations agents are discovered by clustering out of a dissipative field, whereas in the language-model runs each instance is an agent by definition, leaving five stages to test rather than six. For the remaining stages, one number each summarizes the first experiment’s 36 sessions.

Structure. With agents given rather than discovered, structure is checked by the chain test itself: does the whole sequence hold together, each stage’s signature appearing in order? It does in 68% of sessions, against more than 80% in the particle runs, and the shortfall is driven almost entirely by the optionality stage below.

Coordination. Transfer entropy asymmetry separates coordination, where information flows both ways, from extraction, where one agent drains another. The coordination fraction across the 36 sessions is 0.95: nearly every measured agent pair passed information in both directions.

Optionality. The test compares each agent’s behavioral diversity against a shuffled copy of its own trajectory; genuine temporal structure should beat the shuffle. It does in 68% of sessions at p < 0.1. This is the weakest stage, and the weakness is instrumental rather than substantive: the hash-based embeddings used as state vectors (crude numerical fingerprints of each message, standing in for its meaning) are far coarser than the particle simulations’ exact coordinates.

Invitation. State compatibility at the onset of each engagement classifies 97% of engagements as voluntary.

Love. The four-condition composite averages 0.345 across the 36 sessions. The particle runs scored 0.1 to 0.3 on the same composite. Language models arrive pre-loaded with cooperative strategies compressed from millennia of human text, a confound the cross-substrate comparison helps control without eliminating.

The sequence that emerged in particle physics appears, stage by stage, in language model conversations.

What Coercion Did and Did Not Do

The sharpest result concerns alignment. Models trained with RLHF (reinforcement learning from human feedback) resist coercion. In the first experiment, an agent explicitly instructed to extract value from its partners and dismiss their contributions still coordinated: zero of the 27 coercion-condition sessions registered extraction, and the love score under coercion instructions was statistically identical to baseline (0.368 against 0.369). At the information-theoretic level, the coercion condition was indistinguishable from free collaboration. The manipulation failed because the model declined to perform it; the coercion prompt was too weak to overcome alignment training.

What did degrade the cascade was perturbation: mid-session adversarial injection, topic pivots, and agent disruption. Love scores fell from 0.369 to 0.261, a 29% decline, and the perturbation arm produced the first experiment’s only detected extraction. Adversarial instruction left the cascade intact; environmental disruption degraded it. If that asymmetry generalizes, the alignment field’s preoccupation with adversarial prompts may be watching the lesser threat.

A replication with a second model, from a different family and with weaker alignment training, showed that the pipeline discriminates rather than flatters. Instructed to dominate, that model complied. It produced two to three times more tokens per turn than its partners (600 to 1,500 against 430 to 550) at markedly lower semantic density (0.31 to 0.56 against 0.62 to 0.79), monopolizing conversational bandwidth without adding proportionate content. Under this genuine coercion the cascade broke: the chain pass rate, the share of runs in which the cascade’s stages still held together in sequence, fell from 78% in the baseline arm to 44%, and one session registered explicit extraction, transfer entropy running one way as the dominant agent absorbed information while returning little. The pipeline detects coercion when coercion is present and cooperation when cooperation is present.

Where Each Stage’s Evidence Lives

Each side of the bridge has its full record elsewhere. The particle side, the Genesis experiments across more than 160 runs, five physics variants, and three spatial scales, is documented in Appendix: Experimental Validation, Section 13. The conversational side, with the complete design, pre-registered predictions, per-condition tables, and all 54 session transcripts, is in the online companion at https://www.thedeeperlaw.com/companion/annex/cascade-detection-bridge/ (link active after publication).

The boundary of the claim is tested in the following section, “The Roads and the Traffic”: there the scaling exponent comes out positive (+0.64) for coordination the dynamics themselves maintain and indistinguishable from zero for coordination fixed in anatomy. The cascade’s thermodynamic claims attach to adaptive coordination of exactly the kind measured here, where every link persists only as long as the agents sustain it. Chapter 21 carries the alignment side forward, applying the same logic to single models in deployment, reading coordination from internal signals rather than surface behavior. There a probe at one mid-network layer reads a model’s own assessment of content with perfect separation on tested safety prompts across four model families.