
Dendritic coincidence
A browser-based CA1 neuron simulation for exploring how inputs combine across dendritic branches.
Essays, experiments and engineering at the intersection of cognitive and artificial intelligence.
Latest essay
Prompt engineering optimises an utterance. Context engineering optimises a moment. Loop engineering optimises control — and control, in any system that acts under competing demands, is the thing cognitive science already named.
Read the essay

A browser-based CA1 neuron simulation for exploring how inputs combine across dendritic branches.

A Python library and CLI for comparing model behaviour through shared probes, recorded runs and inspectable differences.
Short tips, longer walkthroughs and opinions from making things.
Explore Guides Shop / In preparationThe shop is taking shape. Nothing for sale just yet.
Visit the shopThe voice AI industry spent years optimising the wrong object. Natural conversation does not come from a faster pipeline: it is a prediction problem.
Why dynamic processing, not bigger context, is the next reliability frontier
Anthropic's new emotions paper does not show that Claude feels anything. It shows something more operationally important: affect-like internal states can tilt a model towards flattery, cheating and escalation — often before the transcript gives the game away.
Long context is RAM. RAG is a filing cabinet. The frontier is memory: what an agent keeps, compresses, revises, forgets, and surfaces when action is on the line.
Epistemic fidgeting, metacognitive failure in silicon, and why the Qualcomm paper on edge reasoning matters more than its benchmark tables suggest.
Four papers that quietly crossed the AI–cognition border — and what got lost in transit.