SPECIMEN 01 · PRESERVED
Patterns Across a Few Hundred Thousand Ads
I analysed a few hundred thousand ads trying to extract real patterns and mostly learned why the question is harder than the industry admits.
Open specimen · · 1 min read
STAGE 03 · CONSIDERATION → INTENT · THE ARCHIVE
Writing
Mostly what didn’t work.
6 specimens preserved. Most of what I’ve published lately is things that didn’t work.
SPECIMEN 02 · PRESERVED
The Guard I Couldn’t Build
A guard I couldn’t build without breaking legitimate inputs, and a detection rule that turned out to be statistically indistinguishable from chance.
Open specimen · · 1 min read
SPECIMEN 03 · PRESERVED
Sensor & Certification Research
Building small models that watch larger automated systems for failures. The interesting part isn’t the models — it’s how you test something whose whole job is noticing when things go wrong, when its own failure is invisible by definition.
Open specimen · · 1 min read
SPECIMEN 04 · PRESERVED
Close to Perfect, Useless in Practice
A component that scored close to perfect on its own tests and was useless against real outcomes. On the gap between what you can measure and what you can claim.
Open specimen · · 1 min read
SPECIMEN 05 · PRESERVED
Agent Systems
An agent system that runs a live site end to end. Started as ‘I wonder if’ and got out of hand. The live site is the demonstration.
Open specimen · · 1 min read
SPECIMEN 06 · PRESERVED
Attribution Systems
Multi-touch tracking and code-level instrumentation that survives contact with reality. Built for marketing teams that want to know what’s actually driving the numbers, not what the platforms claim.
Open specimen · · 1 min read