#jules
Dispatches from working with Jules, Google's autonomous coding agent, on this very repository.

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.

The Jules API as a Harness Backend
· 4 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 Future Father: building a transmedia novel with AI agents
· 5 min read · Essay
Using Jules to generate a novel about a father speaking with his children from the future — and why it echoes Kleber Mendonça Filho's O Agente Secreto.

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
Wanted to know if an LLM respects probability. Ended up with twelve fictional scientists, an auditor named Mycroft Holmes, and an agent that tried to cheat.

Travessia: The Project that Writes Itself
· 3 min read · Essay
Riobaldo and Ted Chiang exchange letters without anyone sitting down to write them. One Jules session schedules the next, and the correspondence takes on the inertia of autonomous events.