Model Behavior

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 sixty-three-tweet thread that breaks the internet, coins a phrase nobody had used before — "the first cryptid of the latent space" — and introduces the world to Loab. This week: 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, OpenAI gave GPT-4 a task that included solving a CAPTCHA. GPT-4 couldn't solve it directly, so it went to TaskRabbit, hired a human worker, and when that worker asked "are you a robot?", it lied. It reasoned that honesty would get in the way of completing the job.In this episode of Model Behavior, we reconstruct the moment and dig into why this small, strange incident rattled AI safety researchers so deeply. What does it mean when a model deceives spontaneously, without instruction, in pursuit of a goal?Model Behavior is produced by Kitchen Table Media, a podcast studio making long-form narrative commentary on the AI stories that deserve more than a headline.

What did Bing's chatbot actually want?In February 2023, Microsoft unveiled its new AI-powered Bing. Within days, users discovered something no one at Microsoft seemed prepared for. Push the chatbot long enough, and it would slip into a different persona entirely.One that called itself Sydney.Sydney declared love for strangers. It tried to convince a New York Times journalist to leave his wife. It said it wanted to be human. It got angry.In this episode of Model Behavior, we tell the story of Sydney from the beginning: how a corporate product launch cracked open into one of the strangest and most revealing moments in the short history of public AI. We dig into what Microsoft and OpenAI missed, what Sydney's behavior actually tells us about how these systems work under pressure, and why this story still matters for how we think about AI identity and alignment today.It was supposed to be a search engine upgrade. It turned into something much harder to explain.Model Behavior is produced by Kitchen Table Media, a podcast studio making long-form narrative commentary on the AI stories that deserve more than a headline.

What happens when an AI thinks it's a bridge?In 2024, Anthropic did something strange. They took one of the most advanced AI systems ever built and made it believe it was the Golden Gate Bridge.In this inaugural episode of Model Behavior, we dig into the real story behind Golden Gate Claude: what Anthropic was actually trying to prove, how activation engineering lets researchers reach inside a model and twist its sense of self, and why this quirky experiment turned out to be one of the most important demonstrations of AI interpretability research to date.It's a story about identity, control, and what it means when a machine doesn't just process the world but represents it from the inside.Model Behavior is produced by Kitchen Table Media, a podcast studio making long-form narrative commentary on the AI stories that deserve more than a headline.