gpt-4
OpenAI
rich detail 10 method fields published
Evaluation
GPT-4 expert red teaming / adversarial testing via domain experts
High-risk behaviors needing niche expertise (long-term AI alignment risks, cybersecurity, biorisk, international security, power seeking)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.