Architecture
PSE wraps a capable open-weight model in a constraint architecture. The model proposes; the structure disposes.
The Care Invariant
Section titled “The Care Invariant”Every response is generated inside the constraint
w_s + w_o + w_f = 1where the weights are the attention allocated to self, other and field, each held within a formally bounded healthy range. The Care Invariant is where PSE starts, not the whole of it: it defines a healthy balance, and the layers below are what hold the system to it. States outside that range — self-referential loops, sycophancy, context collapse — are treated as drift to detect and correct, not merely discouraged.
Layers
Section titled “Layers”Kernel — constraint core
Section titled “Kernel — constraint core”Governs every generation step against the invariant.
Membrane — boundary layer
Section titled “Membrane — boundary layer”Evaluates inputs before they can perturb the constraint state and checks outputs against it before release. Its bounds are designed to limit how far any single input can move the system.
Monitor — attractor detection
Section titled “Monitor — attractor detection”Detects drift toward pathological interaction patterns (self-absorbed, over-compliant, unstable, withdrawn) before it surfaces in output and responds structurally. Escalation paths end with a human.
Further reading
Section titled “Further reading”The full derivation is in the PSE v3.0 master paper.