Announcements Frontier threats red teaming for AI safety Jul 26, 2023 “Red teaming,” or adversarial testing, is a recognized technique to measure and increase the safety and security of systems. While previous…
…Acknowledgments We’re very grateful to Andon Labs for their partnership on Project Vend. You can read their earlier research on AIs running shops in a simulated environment here . Footnotes 1. “ Vibe…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.