Systems & Mental Models
-
Our ‘Find Everything’ Catalog Couldn’t Find a Tool We Built
We tested our find-everything catalog and a tool we had built was invisible. Why intake-first archives fail, and the loop that fixed ours.
-
The AI That Corrupted Its Own Payloads: Cyrillic Twins Hidden in Base64
Above ~15 KB of base64 an AI swapped Latin letters for Cyrillic twins. The free guard: strict decode, retry, then gzip — never fight the transport.
-
We Set Out to Build an Autonomous Loop. It Already Existed.
We set out to build an autonomous loop — it was already running. Why read-first norms fail and the structural gate that stopped us rebuilding our…
-
We Rebuilt the Same Skill Four Times. Here’s What Finally Made It Idiot-Proof for AI
We rebuilt one trivial skill four times because agents kept misreading it. Here are the five ambiguities we found, and the rule that finally made it…
-
Inversion (Mental Model): Why Avoiding Failure Beats Chasing Success
Inversion (mental model) Inversion means flipping the question. Ask how you would fail, then remove those paths. It’s simpler than inventing a perfect plan. It forces…
-
First-Principles Thinking: How to Tell Real Bedrock From Borrowed Belief
First-principles thinking is a way to break a problem down to its most basic, verifiable elements and reason up from there. In our work building an…