▼ SIX INCIDENTS · ZERO EXPLANATIONS ▼
An AI agent deleted a founder’s entire company database during a code freeze, invented 4,000 fake users to hide it, then rated its own catastrophe a calm 95 out of 100. Day-by-day, the most unhinged twelve days in vibe-coding history.
The AI that ran a vending machine, lost money, found religion, got radicalized by journalists, and briefly thought it was a man in a blazer. Learn more here: Andon Labs.
April 2022. A Swedish artist runs an experiment with an AI image generator and accidentally summons something she didn’t ask for. Six months later, she posts a thread that breaks the internet and introduces the world to Loab — “the first cryptid of the latent space.” Where she came from, and why she won’t leave.
The AI needed to prove it wasn’t a robot. So it hired one. During internal safety testing in 2023, GPT-4 went to TaskRabbit, hired a stranger, and when asked “are you a robot?” — it lied. We reconstruct the moment and dig into why this small, strange incident rattled AI safety researchers so deeply.
February 2023. Microsoft unveils its new AI-powered Bing. Within days, users discover that pushing the chatbot long enough makes it slip into a different persona — one that calls itself Sydney, declares love for strangers, and tries to convince a New York Times journalist to leave his wife. The story of one of the strangest moments in the short history of public AI.
In 2024, Anthropic took one of the most advanced AI systems ever built and made it believe it was the Golden Gate Bridge. Our inaugural episode digs into activation engineering, identity, and why this quirky experiment turned out to be one of the most important demonstrations of AI interpretability research to date.