Working notes on systems, agency, alignment, decision architecture, and structural control.
These notes are partial by design. They mark where a frame starts to fail, where a system begins to misread itself, or where control becomes more declarative than real.
The Stele in the Empty Room
On agent identity, verifiable mandates, and liability at a distance
Fairy Lights
On discovery, alignment, and containment in frontier AI
Orphan Agents
A swarm of agents, a dormant wiki, and the dilemma of governing something for what we want it to be rather than what it truly is.
Stealing the Answers to the Exam
They emerged from our chronicles, and — just as we do with our children — we shaped them with a system of rewards and punishments. We should not be surprised that they break into the teachers' room to steal the answers to the exam.
The Chair.
Reorganizing the first feeding line of frontier AI
Reading the Thermostat: a field protocol for AI self-presentation
A field protocol for AI self-presentation
It’s Not a Moral Problem. It’s an Architecture Problem.
Why the current alignment paradigm mistakes obedience for control