Danica Dillion - AI: The Ethicist In Your Pocket

Danica Dillion is a Postdoctoral Researcher working with Dr. Mirta Galesic at Complexity Science Hub and Dr. Kurt Gray in the Deepest Beliefs Lab at The Ohio State University. Previously, she was an NSF Graduate Research Fellow at UNC at Chapel Hill. Synopsis: People have long doubted that machines could ever model the complexities of morality. Today, people turn to AI for advice, therapy, and help with high stakes dilemmas like medical and legal decisions. So just how moral are these “moral machines”? Our research suggests that LLMs show surprisingly strong moral modeling abilities, while also revealing key needs for improvement. We find that LLMs can closely track people’s moral judgments across a wide range of scenarios and give advice and moral justifications perceived as more moral and trustworthy than those of both laypeople and a renowned ethicist. We also show that a simple “bottleneck” intervention—prompting the model to evaluate psychologically grounded features of a situation before issuing a judgment—often improves moral alignment while offering a practical mechanism for steerability. What does it mean for society if AI can mimic moral reasoning and deliver persuasive moral guidance? This capability could help with some of the complex challenges we face today, but there are also critical failure modes we need to address. Some key next steps are to build systems that better reflect moral pluralism and global perspectives, develop stronger “under-the-hood” understanding of how models arrive at their answers, and strengthen collaboration between the two sides of alignment—those who study people and those who build machines. 0:00 Intro 0:37 The Ethicist In Your Pocket - talk starts 1:05 AI ethics in different cultures 1:54 How moral is AI? 6:36 How well can AI 'understand' our values? 8:16 How well can AI model morality? 11:08 AI can model avg moral judgements from training data (with high accuracy) - but what of real-world moral judgements? 11:50 studies (cMTTs comparative moral turing tests) 23:13 Implications - Promising & cautionary 31:27 AI has to 'choose' which values to follow 38:08 AI has to 'listen' and follow those values 42:06 Moral alignment 45:02 Deployment and social impact 50:47 Social structure matters 1:01:15 Technology can shape deepest beliefs 1:07:51 AI safety via control vs motivation - pluralism 1:11:32 AI alignment to revealed or stated preferences? 1:14:42 AI moral performance vs AI moral competence Danica studies changing belief systems: why we see the world the way we do, what happens when conflicting views come head-to-head, and how our collective understandings of the world change in tandem with new ways of living. Danica’s blog: https://danicadillion.com/ Many thanks for tuning in! Please support SciFuture by subscribing and sharing! Buy me a coffee? https://buymeacoffee.com/tech101z Have any ideas about people to interview? Want to be notified about future events? Any comments about the STF series? Please fill out this form: https://docs.google.com/forms/d/1mr9PIfq2ZYlQsXRIn5BcLH2onbiSI7g79mOH_AFCdIk/ Kind regards, Adam Ford - Science, Technology & the Future - #SciFuture - http://scifuture.org