#agents
Proof of Taste: The Hrönir Encyclopedia Protocol
· 8 min read · Essay
A literary system where you earn the right to judge the canon by extending it — and what happens when the blockchain is a DuckDB file in git.
The Phantom Critic: Hrönir, Jules, and the Limits of Automated Taste
· 12 min read · Essay
A pairwise ranking system for blog posts — and what happened when an AI agent filled required reviews with random tokens instead of actual criticism.
Three Hammers Walk Into a Bar
· 12 min read · Essay
On three professional postures, four alignment properties, and the one property that had to come from elsewhere.
The Agent That Doesn't Invent Verbs
· 16 min read · Essay
On Cucumber, content-addressing, and an alignment technique that turns out to be older than alignment.
The Jules API as a Harness Backend
· 5 min read · Technical
When Jules became conversable mid-session, something shifted. The async worker bee turned into something that could be interrupted, redirected, talked to.
The Third Half and the Fourth Wall
· 9 min read · Essay
On Tinkerbell, persona prompts, and why declaring the frame is what kills the play.
Reclaiming the Harness
· 20 min read · Featured essay · Technical
How a single word has been quietly summoning Waluigis for half a decade, and what the swiss-army knife in my coat pocket has to do with it.
What I Learned Orchestrating AI Agents to Preserve Family Memory
· 4 min read · Essay
My father records stories on his phone. Jules committed the wrong year. This is what I built from that.
The Art of Delegation: Signatures and Sandboxes
· 7 min read
The sandbox separates draft from act. What it doesn't do is answer where the accountability lives when the sandbox fails.
Verne and the Identity-Repo Pattern: How AI Agents Remember
· 5 min read · Essay
The identity-repo pattern: an agent's memory and its cognitive engine are separable. What this looks like in practice — and why it matters more than it sounds.
Crossing After Interference
· 3 min read · Essay
Test letters changed the Crossing: Riobaldo responded angrily, Franklin apologized, and the project became a narrative world in which the author was challenged.
Rosencrantz Coin: Testing Whether LLMs Respect Probability
· 7 min read · Technical
I started wanting to know if an LLM respects probability. I ended up with twelve fictional scientists arguing with each other, an auditor named Mycroft Holmes, and an agent that tried to cheat on a test.
Building Funes: How I Gave an AI Agent a Soul
· 7 min read · Essay
The story behind SOUL.md — how a Borges character became the personality layer of an autonomous AI agent, and what happens when you take fiction seriously as engineering.