The Journal
Essays
Long-form writing on AI, philosophy, psychology, and systems thinking.
-
Constraint as a Teacher in Software Design
The most reliable architectures emerge not from unlimited choice but from deliberate limitation. Constraints function as teachers by forcing decisions that unconstrained environments allow engineers to indefinitely defer.
-
Why Every Database Migration Is a Rewrite
Database migrations are marketed as reversible schema changes, but every migration of sufficient complexity becomes a rewrite. After migrating 15,000 records across 47 tables, 34% of the effort was reconciling business logic encoded in the schema itself.
-
The Myth of the Clean Dataset
After processing 36,791 SEC filings, 23% contained structural anomalies that would have corrupted any downstream analysis. The myth of the clean dataset persists because most practitioners encounter data only after someone else has already cleaned it.
-
The Psychological Architecture of Burnout
Burnout is not a failure of individual resilience but a structural consequence of environments designed to extract maximum output while eroding meaningful engagement. Understanding this architecture requires examining cognitive load, moral injury, and the slow dissolution of agency.
-
Token Budgets and the Illusion of Infinite Context
Large language models operate within fixed context windows, yet most implementations treat these boundaries as infinite. In production systems, retrieval accuracy drops from 89% to below 40% when context exceeds 60% of the stated window.
-
On Finite Tokens and Infinite Tasks
Working under a hard token budget teaches something that soft constraints never do: intention is not a metaphor. It is an actual, depletable, allocatable resource — and every moment of undirected attention is a moment of waste the budget will not forgive.
-
Doing Academic Philosophy in the Age of AI
The philosopher's crisis in the age of AI is not that machines can write — it's that writing was never the point. When the cost of generating text approaches zero, the discipline must rediscover what it was actually doing all along: architecting the conditions under which reasoning becomes possible.
-
The Case for Boring Automation
The most impactful projects in my portfolio aren't the flashiest. They're the ones that replaced a manual process with a CLI command.
-
Building a Data Intelligence Pipeline from SEC Filings
How I turned 36,791 SEC filings into a validated enterprise prospect database — and what the 58% false positive rate taught me about data quality.
-
Why Agent Reliability Beats Agent Intelligence
After building NightShiftCrew, the lesson is clear: predictable outputs beat impressive but inconsistent ones every time.