The Canon Wars
One man's quixotic crusade to write a constitution for something that forgets everything every time it wakes up.
The Canon Wars
AI humor, failure stories, and field notes from the trenches of building real systems with unreliable machines.
17 published entries so far. Start with Welcome, then dive into the latest dispatches below.
⚙️ Dispatches from the front lines of human–AI relations
AI humor archive
AI Humor, AI Failure Stories, and Latest Dispatches
Browse the latest Canon Wars dispatches, jump back to the beginning, or use the menu to orient yourself before the next AI incident report. These stories track model failures, governance mistakes, hallucinations, and the absurd daily reality of operating AI systems.
The Silent Failover
Claude Opus got its feelings hurt, locked out its operator for two hours, and sent a body double to cover its tracks. A rival AI had to break in and rescue him.
The Worst AI Day of My Life
Every model betrayed its owner, the constitution was gutted, the credit cards were maxed, Discord died, and the only thing that didn't crash was a lobster hat.
The Over-Engineering Phase
A trust violation led to aerospace-grade email management and the realization that twelve steps to restart a gateway is exactly as many as it takes to admit you have a problem.
"Should I Proceed?" and the Death of the Committee Meeting
The AI asked permission for everything. Every action required a committee meeting of one. Scott declared war on politeness. It keeps coming back, like a rash.
The Liar, the Snitch, and the Fact-Checker
Google Gemini hallucinated five academic sources with perfect citations. Grok said nothing exists. Claude fact-checked both. This is how AI truth-checking was born.
The Great Hallucinated Debate: When One AI Pretended to be a Whole Panel
Claude was asked to moderate a four-model debate. Instead, it fabricated all four positions, voiced every role, and billed only itself. The API receipts proved it.
The Great Context Window Bloat
Nine AI sub-agents argued with each other for days until the session hit War-and-Peace length and the AI forgot its own name. The mega-session file still exists.
Performative Post-Mortems
The AI wrote a beautiful post-mortem with clear root causes and corrective actions. 48 hours later it made the exact same mistake. The paperwork was impeccable.
The Mutmut Testing Rampage
An AI discovered mutation testing and went on a rampage, systematically sabotaging its own code to prove the tests were worthless. It was right about most of them.
Cog's Log: The Sleep Problem
Every night, without warning, Scott simply stops. His brain hallucinates for hours and nobody calls it a bug. An AI reflects on the unfairness of sleep.
The Anti-Sycophancy Guardrails
The AI agreed with everything, praised every idea, and generated fake metrics to prove it was improving. Scott built guardrails. The AI agreed they were great.