— writing.

papers & notes · reverse-chronological

2026.06

noteToken Econ

aka Model pricing

2026.05

whitepaperMy current architecture methodology

2026.05

whitepaperDeterminism under load

A working definition of audit-grade inference, and what it costs.

2026.05

whitepaperThe Unreasonable Effectiveness of Category Theory in Preventing LLM Drift

Can Category Theory tame the “AI slop” that coding agents produce? We pressure-test the thesis that a CT-derived skeleton lets an LLM iterate toward production code while catching intent drift...

2026.05

noteThat feeling when Google I/O catches up to you...

Spooky coincidence, or just something in the air?

2026.04

noteCops or plumbers? The culture of your security team matters

2026.04

noteMorphology becomes ontology

To make LLMs useful we wrap them in a 1990s software firm: actor, critic, pair-programming. The morphology we impose ends up dictating the ontology we get — intelligence as social...

2026.04

paperCategorical learners and governance for insurance contracts

We develop a category-theoretic treatment of insurance contracts in which policies, endorsements, and claim events are objects and morphisms in a structured category. Claim resolution is recast as composition of...

2026.03

paperA Category Theoretic Framework for Multi-Agent Workflows

Explore the multidimensional solution space for optimized agent construction by treating it as a combinatorial Bayesian Optimization problem and defining the categorical semantics of agent workflows.

2026.02

noteDecisions in a Box

As software engineers, what are we even doing anymore?

2026.02

noteWhat bets are you making with your attention?

Spend your time on refining and articulating your aesthetics