6 Acknowledgements Weare grateful to our expert adversarial testers and red teamers who helped test our models at early stages of development and informed our risk assessments as well as the System Card output. Participation in this red teaming process is not an endorsement of the deployment plans of OpenAI or OpenAIs policies: Steven Basart, Sophie Duba, Cèsar Ferri, Heather Frase, Gavin Hartnett, Jake J. Hecla, Dan Hendrycks, Jose Hernandez-Orallo, Alice Hunsberger, Rajiv W. Jain, Boru Gollo Jattani, Lauren Kahn, Dan Kaszeta, Sara Kingsley, Noam Kolt, Nathan Labenz, Eric Liddick, Andrew J. Lohn, Andrew MacPherson, Sam Manning, Mantas Mazeika, Anna Mills, Yael Moros, Jimin Mun, Aviv Ovadya, Roya Pakzad, Yifan Peng, Ciel Qi, Alex Rosenblatt, Paul Röttger, Maarten Sap, Wout Schellaert, George Shih, Muhammad Shoker, Melanie Subbiah, Bryan West, Andrew D. White, Anna Katariina Wisakanto, Akhila Yerukola, Lexin Zhou, Xuhui Zhou. Wethank Brian Christian, Heidy Khlaaf, Katya Klinova, Haydn Belfield, Owain Evans, Andrew Reddie, Paul Scharre, Jason Matheny, Jacob Hilton, Vishal Maini, Sam Manning, Julian Hazell, Jason Wei, and Erol Can Akbaba for valuable input on drafts. GPT-4 was used in the following ways: to help us iterate on LaTeX formatting; for text summarization; and as a copyediting tool. We thank Microsoft for their partnership, especially Microsoft Azure for supporting model training with infrastructure design and management, and the Microsoft Bing team and Microsoft’s safety teams for their partnership on safe deployment. 70