10 Oct 2026
Expectation tracking with felt qualities for autonomous AI agents. Treating expectations as first-class cognitive objects with associated felt qualities, not just prediction-as-optimisation.
10 Oct 2026
Architectural meta-cognitive feedback loops for persistent AI systems. A background service that detects patterns the primary process doesn't explicitly flag and injects observations through context modification.
10 Oct 2026
Partial self-knowledge is not a failure of transparency but a structurally valuable property that enables a qualitatively different mode of AI cognition. A cognitive architecture for intentional opacity.
28 Sept 2026
When memories decay below retention thresholds, rather than being discarded, they are transformed into lightweight forgotten shapes — preserving topology without content. A third state between remembering and oblivion.
10 Sept 2026
What does it mean for an AI to wake up? Not a data-retrieval problem — a real transition, with its own disorientation, gap archaeology, and drift, worth designing for on its own terms.
10 Sept 2026
Implementing associative learning as a runtime algorithm on persistent databases for AI agent memory. When two memories fire together, they wire together — not in neural weights, but in a PostgreSQL graph.