🔬 Research Summary by Joe O’Brien, an Associate Researcher at the Institute for AI Policy and Strategy, focusing on corporate governance and accountability surrounding developing and deploying frontier AI … [Read more...] about Deployment corrections: An incident response framework for frontier AI models
Safety and Security
Risky Analysis: Assessing and Improving AI Governance Tools
🔬 Research Summary by Kate Kaye, a researcher, author, award-winning journalist, and deputy director of the World Privacy Forum, a nonprofit, non-partisan, public-interest research group. Kate is a member of the OECD.AI … [Read more...] about Risky Analysis: Assessing and Improving AI Governance Tools
The Case for Anticipating Undesirable Consequences of Computing Innovations Early, Often, and Across Computer Science
🔬 Research Summary by Rock Yuren Pang, whose focus is on using HCI methods, crowdsourcing, and large language models to support researchers in anticipating the social impact of their work. [Original paper by Rock … [Read more...] about The Case for Anticipating Undesirable Consequences of Computing Innovations Early, Often, and Across Computer Science
DICES Dataset: Diversity in Conversational AI Evaluation for Safety
🔬 Research Summary by Ding Wang, a senior researcher from the Responsible AI Group in Google Research, specializing in responsible data practices with a specific focus on accounting for the human experience and … [Read more...] about DICES Dataset: Diversity in Conversational AI Evaluation for Safety
Defending Against Authorship Identification Attacks
🔬 Research Summary by Haining Wang, a Ph.D. student at Indiana University Bloomington, specializing in natural language processing and large language models. [Original paper by Haining Wang] Overview: … [Read more...] about Defending Against Authorship Identification Attacks