// 02. blog
Writing.
Engineering leadership, AI systems, and building at enterprise scale.
More Is Different: The Case Against Reductionism in AI System Design
7 min readPhilip Anderson's 1972 paper is the most important paper on emergence in 20th-century physics. Its central claim — that complex systems cannot be understood by reducing them to their components — applies with full force to the AI systems we are building right now.
EmergenceReductionismAI SystemsComplex SystemsEngineering LeadershipCritical Mass: Why Agent Systems Have Thresholds, Not Gradients
7 min readNuclear chain reactions don't scale gradually — they have a critical point. Add one neutron too many and you go from subcritical to supercritical. Agent systems have the same structure. Most teams discover this in production.
Critical MassMulti-Agent SystemsAgentic AIProduction EngineeringSystems DesignThe Ant Colony Problem: On Emergent Intelligence in Multi-Agent Systems
8 min readNo ant understands architecture. The colony does. This is not a metaphor for multi-agent AI — it's a precise description of a phenomenon we are actively building and don't fully understand.
Multi-Agent SystemsEmergent IntelligenceAgentic AIComplex SystemsEngineering LeadershipThe Perfect AI Product Team at a Startup: What I'd Build If I Were Starting Over
4 min readAfter four years building engineering teams at an AI-first company, I have a clear answer to the question I wish someone had given me in 2021: here's exactly how I'd structure the first 15 people.
Startup EngineeringAI Product TeamsOrg DesignEngineering LeadershipTeam BuildingThe Observer Effect: How Evaluating an LLM Changes What It Does
7 min readIn quantum mechanics, observation collapses the wave function. In LLMs, evaluation changes the behavior being evaluated. This isn't philosophy — it's an engineering problem with concrete production consequences.
Observer EffectLLM EvaluationAI EngineeringBenchmarkingProduction AIFrom ATS to Agentic: The Complete Evolution of the Recruiting Stack
5 min readIn five years, the recruiting technology stack has gone from system of record to intelligent pipeline. Here's the full arc — what changed, what it meant architecturally, and where it's going next.
HR TechAgentic AIRecruiting StackEngineering LeadershipAI EvolutionSpontaneous Symmetry Breaking: Why "Neutral" AI Is a Physical Impossibility
7 min readPhysics has known for 60 years that symmetric equations can produce asymmetric outcomes. LLM bias isn't a data problem or an alignment problem — it's a symmetry breaking problem. Here's why that distinction matters.
AI BiasSymmetry BreakingLLMPhysicsResponsible AIGrokking and the Critical Point: When Neural Networks Cross the Phase Boundary
7 min readGrokking isn't a curiosity — it's evidence that neural network learning is phase-transition-shaped. Here's what the physics tells us, and why it should change how we think about training, evaluation, and trust.
GrokkingPhase TransitionsNeural NetworksLLM TrainingAI Engineering