Release not stated
OpenAI
rich detail 8 method fields published
Evaluation
GPT-4 interactions with other systems red teaming (chemistry purchase task)
Adversarial tasks with tool-augmented GPT-4 (literature search, molecule search, web search, purchase check)
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.