Research
We run a studio and a lab under the same roof. The studio builds AI systems and websites for clients. The lab is where we test the methods first: how to make agents reliable, how to evaluate them honestly, and how to ship 3D on the web without wrecking performance.
We publish what we learn in two formats. Field Notes are short, applied findings pulled straight from client and lab work. Reports are formal write-ups of structured experiments and the operating doctrine that came out of them.
Field Notes move fast. Each one captures a pattern we used on a real build, the failure modes we hit, and the rule we follow now. Reports move slower. They state a question, the method, the evidence, and what we would change next time.
Everything here comes from work we shipped or tested ourselves. No roundups, no rewrites of other people's posts. If a claim is on this page, we have run it.
All Notes & Reports
We Rebuilt 32 Pages Around One Question: Will an AI Cite This?
Generative engine optimization is structuring content so AI answer engines quote it. The page structure we rebuilt 32 articles around, and how we measure it.
Read more →We Ran Four Agentic Coding Tools Through the Same Gate
We run Claude Code, Codex, Cursor, and a local open weight model on real client work. What separates agentic AI coding tools is the harness, not the model.
Read more →We Let an Agent Run 60 Experiments on Our RAG Stack While We Slept
A worker-supervisor loop ran 60 controlled experiments on our hybrid retriever overnight and cut context tokens 23% with no accuracy loss. The waste was inside the chunks, not the ranking.
Read more →The Frontier You Can't See: Why "China Caught Up" Is Half a Myth
In summer 2026 Washington throttled America's best AI models and Anthropic's top tier went partner-only. What is measured, what is contested, and what would prove it wrong. Full paper attached.
Read more →Does an LLM Understand Credible Punishment?
We put a frontier model against a grim-trigger pricing rival and swept the odds the game continues. It cooperates exactly when game theory says it should, then leaves money on the table.
Read more →The Great Model Dump: Cheap Chinese Intelligence and Which Assumption Breaks First
Chinese open weights sit months behind the US frontier at 85 to 97 percent less. A sourced market thesis on margin compression, with the full technical report attached.
Read more →The Agents Were Innocent: Field Notes From a Red Wave
Our overnight agent wave came back all red and none of it was the agents' fault. What a broken format gate and a date time bomb taught us about judging AI-written code.
Read more →We Ran 154 Controlled Trials of Claude vs GPT. Both Scored Perfect.
A blocked full-factorial experiment pitting Claude Fable 5 against GPT-5.6 on nine proven-solvable coding tasks, blind dual-judged, with a Wilson interval on every pass rate.
Read more →Claude Fable 5 vs. GPT-5.6 Sol: A Practitioner's Field Report
Claude Fable 5 and GPT-5.
Read more →Why AI Agents Fail on Tasks They Can Actually Do
AI agents fail on real work less from weak models and more from a missing harness.
Read more →Why AI Agents Claim They're Done When They Aren't
AI agents declare victory too early because nothing outside the model checks their work.
Read more →Running AI Coding on Matt Pocock's Method, in Production
We run our AI coding pipeline on Matt Pocock's method: grill the plan, lock a spec, cut tickets, TDD, two-axis review.
Read more →Token Efficiency: Spending an AI Context Budget Wisely
Token efficiency means treating context as a budget: progressive disclosure, subagent delegation, and prompt caching cut cost per task, n...
Read more →When to Fan Out Subagents: Orchestration Patterns That Work
When fanning work out to subagents pays off, how to fan verification back in, and the failure modes that show up when orchestration is do...
Read more →How to Optimize Content for Google AI Mode Search
Google's own AI Mode usage report reveals four content signals worth optimizing for: question headings, task completion, follow-ups, and ...
Read more →How to Write Instruction Files AI Agents Actually Follow
CLAUDE.md and AGENTS.md fail the same way: they grow into an encyclopedia the agent stops reading.
Read more →Running AI Coding Agents Unattended, Without Waking Up to a Mess
Overnight AI agent loops fail the same predictable ways.
Read more →The Repo Is the Only Thing an AI Agent Actually Knows
AI agents only know what a fresh session can read from the repo itself.
Read more →Do AI Detectors Actually Work? What the Data Shows
AI detector accuracy data, false-positive rates, and why OpenAI retired its own tool. The honest answer on whether AI checkers can be trusted.
Read more →Will AI Take Over the World? An Honest Answer
What AI researchers, superforecasters, and the public actually say about existential AI risk, sourced instead of speculated.
Read more →Will AI Take Your Job? What the Data Says by Profession
The real BLS and research data on AI and jobs, broken down by lawyers, accountants, doctors, teachers, and radiologists.
Read more →How Much Water Does AI Actually Use?
Published water-per-query estimates range from 0.26 mL to 500 mL. We break down where that nearly 2,000x gap comes from.
Read more →What Is Artificial Intelligence, in Plain English?
A plain-English definition of AI, how it actually works, and how AI, machine learning, and generative AI differ.
Read more →Who Invented Artificial Intelligence? The Real History
No single person invented AI. The sourced timeline from Turing's 1950 question to the 1956 Dartmouth workshop and beyond.
Read more →Is AI a Bubble? The Numbers Behind the Question
Real 2025-2026 capex, revenue, and valuation numbers, the bull case and the bear case laid out plainly.
Read more →The Best Free AI Tools in 2026 (Actually Free)
What is genuinely free on ChatGPT, Claude, and Gemini in July 2026, and exactly where each one draws the line.
Read more →Context Engineering
Prompts are one message. Context is everything the model sees. Why that distinction decides whether your AI system works.
Read more →Harness Engineering
Our operating doctrine: when an AI agent fails, fix the harness, not the model.
Read more →AI Agent Evaluation
Public benchmarks measure models. They tell you almost nothing about your system. How we test agents like software.
Read more →React Three Fiber in Production
What R3F is, when to choose it over vanilla Three.js, and the lessons that only show up after launch.
Read more →Three.js Examples for Business Sites
Ten categories of 3D work that actually earn their place on a business website, with honest performance notes.
Read more →How Scroll Animation Websites Work
Scroll progress as a timeline: video scrubbing, frame sequences, ScrollTrigger, and the performance rules that keep it smooth.
Read more →