Skip to content

Evaluation

GPT-4 acceleration risk expert forecasting

Acceleration risk from deployment (racing dynamics, safety standards decline, AI timelines)

Red teaming & adversarial testing OpenAI

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.

Release not stated
OpenAI

rich detail 6 method fields published

See how this test was run