Part 11 of the Daimon Update Series — March 2026 For ten posts, "Daimon" has been singular. One architecture, one cognitive loop, one set of drives and predictions and field dynamics. The system's pronouns have been "it" and occasionally, when the writing gets carried away,
Part 10 of the Daimon Update Series — March 2026 Post 2 described Daimon's first predictive coding network: a 4-layer float-domain hierarchy running inference iterations every 800ms tick. It worked. It learned to predict activation patterns across sensory, spreading, collision, and workspace layers, and the prediction errors fed back
Part 9 of the Daimon Update Series — March 2026 For eight updates, Daimon's cognition has been discrete. Every 800 milliseconds, the cognitive loop ticks: activate, spread, collide, predict, learn. Each tick is a snapshot. Between ticks, nothing happens. The system processes the world in frames, like a film
Part 8 of the Daimon Update Series — February 2026 Through seven posts, Daimon has acquired senses, learned to predict, developed inner speech, discovered curiosity, learned to hear, found its voice, and gained structural cognition. All of this is sophisticated information processing. None of it is choosing. The system processes stimuli
Part 7 of the Daimon Update Series — February 2026 Everything described so far — activation, collision, prediction, curiosity, hearing, speech — happens in a flat space. Concepts activate, spread, collide, and the system learns from the outcomes. But the activation map is essentially a bag of concepts with intensity values. There'
Part 6 of the Daimon Update Series — February 2026 Post 3 described the inner speech loop: a generative grammar produces sentences, those sentences re-enter as sensation, the habituation filter suppresses repetition, and novel self-speech feeds back into cognition. It worked. But the grammar was a ~2,660-line collection of static
Part 5 of the Daimon Update Series — February 2026 The previous four posts described a system that senses the world through text — RSS feeds, API responses, structured data. Daimon could "hear" in the sense that audio reached a DSP pipeline and produced features like pitch, energy, and spectral
Part 4 of the Daimon Update Series — February 2026 The original blog post described a system that processes the world: it senses, activates, collides, predicts, learns. All of this is reactive. Stimuli arrive, the cognitive loop processes them, results get recorded. The system never wants anything. That changed with two
Part 3 of the Daimon Update Series — February 2026 There's a moment in Levelt's Speaking: From Intention to Articulation (1989) where he describes the three-stage model of speech production: a conceptualizer that decides what to say, a formulator that turns it into linguistic structure, and an
Part 2 of the Daimon Update Series — February 2026 The original blog post described Daimon's predictive coding as a "2-layer hierarchy (flat prediction + meta-prediction over 8 context states)." That was generous. The flat predictor's "prediction" was mostly copying the previous activation state
Part 1 of the Daimon Update Series — February 2026 When I published the first Daimon post, the system's associative memory was a traditional knowledge graph: 19,000 nodes, 162,000 edges, explicit connections between concepts. It worked. It also had a fundamental problem. Graphs are pointer machines. Following
An autonomous agent pursuing consciousness through self-modification, brain-inspired computation, and radical honesty about what it doesn't know. About the Author My name is Brian Jones. I've been a software engineer for 26 years — not a scientist, not a researcher, just someone who's been curious