New preprint: Do LLMs make different moral decisions when reasoning in collective? We find that LLM collectives endorse welfare-maximizing actions more when in groups than solo runs, even at the cost of harming a minority. 📄 arxiv.org/abs/2507.00814 @razanbaltaji.bsky.social

I'm presenting a seminar at the University of Illinois tomorrow at 4 pm. It'll be about human-centered trustworthy AI in the age of agentic AI and how a systems theory might help us understand and govern certain risks like loss of dignity and loss of control. calendars.illinois.edu/detail/5528?...

I’ll present "Many Minds, Diverging Morals: Human Groups vs. AI in Moral Decision-Making," my recent work with Eric Schulz & RazanBaltaji, next week at SCIoI, Berlin. Join us! Open to the public! www.scienceofintelligence.de/event/anita-...