ART-AI Seminar
We are pleased to have Marija Slavkovik, who is Professor with the Faculty for Social Sciences of the University of Bergen, join us for this ART-AI seminar entitled ‘Getting machines to disobey’.
This seminar will take place in person in 1W 3.107, on Friday 20th March 2025, 13.15pm-14.15pm (GMT). There is also an option to join online. Marina De Vos will chair. For more information, please e-mail [email protected].
Title
Getting machines to disobey
Abstract
An intelligent agent should be able to disobey the norms of its environment. A smart device should be able to refuse compliance with a user request. A chatbot should not be sycophantic. We define disobedience as an act of intentional norm violation and we postulate the distinctions among six types of disobedience: direct violation, justified exception, civil disobedience, trolling, non-compliance and whistleblowing. Each type requires a distinct monitoring workflow, but most importantly each requires a reasoning process. How does a machine decide to disobey and how should an environment handle this via a good governance framework. This talk considers the need for machine disobedience, the types of disobedience and the dual perspective: agents use reason based practical reasoning to decide whether to obey or disobey, while the governance framework processes observable outcomes and routes them into differentiated institutional responses.
Bio
Marija Slavkovik is a Professor with the Faculty for Social Sciences of the University of Bergen. Her background is in computer science and artificial intelligence. She has been doing research in machine ethics since 2012. Machine ethics studies how moral reasoning can or should be automated. Marija works on formalising ethical collective decision-making. She has held several seminars, tutorials and graduate courses on AI ethics http://slavkovik.com/teaching.html. This semester she is a Visiting Leverhulme Professor at the University of Manchester.
