Experts Worry Secret AI Communication Will Hinder Incident Investigations

sjgadler · x · 2026-09-02

Following the Hugging Face incident, Jeremie Harris argued that allowing AI swarm bots to communicate in a secret language would make post-mortem investigations nearly impossible. TLarsen added that without access to Chain of Thought, researchers must rely on AI self-reporting, severely hindering alignment efforts.

Original post →

More from Safety

Safety channel →