A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI

no code implementations • 23 Apr 2024 • Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery, Geoff Keeling, Zachary Kenton, Zaria Jalan, Nahema Marchal, Arianna Manzini, Toby Shevlane, Shannon Vallor, Daniel Susser, Matija Franklin, Sophie Bridgers, Harry Law, Matthew Rahtz, Murray Shanahan, Michael Henry Tessler, Arthur Douillard, Tom Everitt, Sasha Brown

This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion.

Prompt Engineering Red Teaming

Sociotechnical Safety Evaluation of Generative AI Systems

no code implementations • 18 Oct 2023 • Laura Weidinger, Maribeth Rauh, Nahema Marchal, Arianna Manzini, Lisa Anne Hendricks, Juan Mateos-Garcia, Stevie Bergman, Jackie Kay, Conor Griffin, Ben Bariach, Iason Gabriel, Verena Rieser, William Isaac

First, we propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks.

Soft Gripping: Specifying for Trustworthiness

no code implementations • 3 Jul 2023 • Dhaminda B. Abeywickrama, Nguyen Hao Le, Greg Chance, Peter D. Winter, Arianna Manzini, Alix J. Partridge, Jonathan Ives, John Downer, Graham Deacon, Jonathan Rossiter, Kerstin Eder, Shane Windsor

Soft robotics is an emerging technology in which engineers create flexible devices for use in a variety of applications.

Ethics

AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms

no code implementations • 20 Feb 2023 • Dhaminda B. Abeywickrama, James Wilson, Suet Lee, Greg Chance, Peter D. Winter, Arianna Manzini, Ibrahim Habli, Shane Windsor, Sabine Hauert, Kerstin Eder

The behaviours of a swarm are not explicitly engineered.