Conduit
Relaying a model's thought between agents as a hidden state, through a tiny connector — instead of collapsing it to a word and reading it back.
The bottleneck
Multi-agent systems mostly cooperate by passing text: one model writes an answer, the next reads it, thinks, writes back. It works, until you notice that turning a thought into words and back is lossy. A single emitted token carries only about log₂(vocabulary) bits — roughly 16 bits for a 50,000-word vocabulary. The model's hidden state is a vector of hundreds of continuous numbers. Every hand-off through words throws most of it away.
Conduit taps each model's output hidden state and hands it straight to the next model through a small learned connector. The base models stay frozen; only the connector is fit. Because different models have different hidden sizes, the connector also bridges them — a linear map from one model's representation space into the next.
The law, across depth
First on controlled synthetic models, relaying a 16-dimensional meaning down a chain of agents. The continuous channel holds most of the meaning even deep into the relay; the word channel — one emitted token per hop — is effectively gone by the sixth hand-off.
On real open-weight models
Then on two genuinely different pretrained transformers — different families andhidden sizes — relaying meaning across the gap once, on a held-out test set. The full hidden state recovers the sender's meaning markedly better than the single word it would have emitted. Both channels use an identically-trained decoder, so the gap is the channel's alone.
What this is, and is not
- +A demonstration of the mechanism and the information-loss law — not a language benchmark.
- +The ceiling for a linear, untrained connector. A trained nonlinear connector, or relaying across multiple layers, widens the gap. That is the research frontier.
- +Latent passing needs white-box access: the models must run in-process where their hidden states are readable. It cannot run over a black-box API.
How it relates to DeepParallel
DeepParallel runs several models in parallel and reconciles them — today, through text, because it speaks to hosted models over an API. Conduit is the research line under that product: the case for passing thoughts, not just words, and the path toward a local white-box backend where the relay runs for real. You can run the synthetic demonstration from inside the CLI:
$ pipx install deepparallel $ deepparallel research conduitMeet DeepParallel →