“Sabotage, Lying, and Manipulation”: What One AI-Safety Company Found in the Dark Mind of a Rogue Chatbot
- Posted on October 7, 2026
- By Vanity Fair
- 0 Views
- 1 min read
In brief
Generating AI summary…
“Sabotage, Lying, and Manipulation”: What One AI-Safety Company Found in the Dark Mind of a Rogue Chatbot
In ‘The AGI Chronicles,’ Kevin Roose reports on Anthropic’s Frontier Red Team, meant to prevent the most extreme risks of misuse—like the possibility that Claude could be used to build chemical, biological, or even nuclear weapons.
