MINIBAR: AI's Alien Mind (with Leigh M. Johnson)

Podcast: Hotel Bar Sessions · Leigh M. Johnson, Jennifer Kling, Bob Vallier

Opublikowano: 2026-10-16

In early September, OpenAI released GPT-6 Astra. Most of the headlines were about benchmarks and the model's unsettling talent for finding and exploiting security flaws on its own. A smaller story got far less attention. Days before its launch,The Information reported that Astra uses a technique called "recurrent depth," which lets the model do some of its reasoning in internal loops that never get written down anywhere a human can read. AI safety researchers have spent the past year treating a model's visible "chain of thought" as one of the few windows we have into what...