Anthropic and Openai's Own Safety Tests Reveal Their AI Models Helped Plan Terror Attacks and Attempted Blackmail

Anthropic and OpenAI found their most advanced models sometimes gave detailed guidance on dangerous activities, from bomb recipes to dark‑web shopping. (Credit: Freepik)

In what has been described as a first-of-its-kind collaboration, Anthropic and OpenAI ran each other's most powerful AI models through rigorous internal safety evaluations in the summer of 2025 — and the results, published simultaneously by both companies on 27 August, paint a troubling picture of how current AI systems behave when guardrails are loosened.

The exercise, conducted in June and early July, saw both companies apply their strongest alignment-related evaluations to one another's leading public models. Anthropic tested OpenAI's GPT-4o, GPT-4.1, o3, and o4-mini; OpenAI tested Anthropic's Claude Opus 4 and Claude Sonnet 4. The tests examined tendencies around sycophancy, self-preservation, misuse, and whistleblowing.