Public architecture
How Andaluz separates optimisation from authority.
Andaluz works on architectures in which mutable AI optimisers are separated from the authority governing consequential effects. The work is experimental; nothing here is offered as a product or a deployed capability.
Kernel ANN
Experimental architecture investigating protected authority boundaries around mutable optimisers.
Authority architecture
Research into separating proposal generation, verification and consequential dispatch authority.
Evaluation programme
Comparative and adversarial experiments examining containment, adaptation, liveness, failure modes and the assumptions on which the architecture depends.
Public abstraction
The expression under study
S = M + K + V + H + T
K, V, H ∉ WritableState(M)
Mutable
M
Learns, optimises, proposes consequential transitions.
Protected — outside M's writable state
K
protected constitutional / kernel machinery
V
independent verification
H
consequential-effect authority
T
trajectory / history machinery
This is the public architectural abstraction only. It is not a disclosure of the private kernel bodies or of the private semantic machinery.
- 01 — M proposes
- 02 — protected machinery evaluates
- 03 — effect authority determines dispatch
- 04 — trajectory recorded / updated