Sarah Barrington (College of California, Berkeley)
Ruby Sales space (Berkeley Threat and Safety Lab)
Miles Brundage (OpenAI)
Husanjot Chahal (OpenAI)
Michael Depp (Middle for a New American Safety)
Invoice Drexel (Middle for a New American Safety)
Ritwik Gupta (College of California, Berkeley)
Marina Favaro (Anthropic)
Jake Hecla (College of California, Berkeley)
Alan Hickey (OpenAI)
Margarita Konaev (Middle for Safety and Rising Know-how)
Kirthi Kumar (College of California, Berkeley)
Nathan Lambert (Hugging Face)
Andrew Lohn (Middle for Safety and Rising Know-how)
Cullen O’Keefe (OpenAI)
Nazneen Rajani (Hugging Face)
Michael Sellitto (Anthropic)
Robert Trager (Centre for the Governance of AI)
Leah Walker (College of California, Berkeley)
Alexa Wehsener (Institute for Safety and Know-how)
Jessica Younger (Microsoft)
All authors supplied substantive contributions to the paper via sharing their concepts as individuals within the workshop, writing the paper, and/or editorial suggestions and course. The primary two authors are listed so as of contribution, and the remaining authors are listed alphabetically. Some workshop individuals have chosen to stay nameless. The claims on this paper don’t symbolize the views of any creator’s group. For questions on this paper, contact Sarah Shoker at sshoker@openai.com and Andrew Reddie at areddie@berkeley.edu.
*Vital contribution, together with writing, offering detailed enter for the paper, analysis, workshop group, and setting the course of the paper.
**Vital contribution, together with offering detailed enter for the paper, analysis, workshop group, and setting the course of the paper.
