Gillian Hadfield
@ghadfield.bsky.social
Economist and legal scholar turned AI researcher focused on AI alignment and governance. Prof of government and policy and computer science at Johns Hopkins where I run the Normativity Lab. Recruiting CS postdocs and PhD students. gillianhadfield.org
I finally got a chance to meet @thomaslfriedman.bsky.social, whose book The World Is Flat inspired my own Rules for a Flat World. I had a great conversation with him and Andrew Freedman about the challenge we find the world facing: how do we build rules for AI that work in a complex world?
October 31, 2025 at 10:39 PM
I finally got a chance to meet @thomaslfriedman.bsky.social, whose book The World Is Flat inspired my own Rules for a Flat World. I had a great conversation with him and Andrew Freedman about the challenge we find the world facing: how do we build rules for AI that work in a complex world?
Human cooperation evolved through complex norms and institutions. Now we're introducing powerful new AI actors into our economic systems. At a recent workshop hosted at ASU we explored what evolution teaches us about getting the rules right.
October 27, 2025 at 10:06 PM
Human cooperation evolved through complex norms and institutions. Now we're introducing powerful new AI actors into our economic systems. At a recent workshop hosted at ASU we explored what evolution teaches us about getting the rules right.
Grateful to keynote at #COLM2025. Here's what we're missing about AI alignment: Humans don’t cooperate just by aggregating preferences, we build social processes and institutions to generate norms that make it safe to trade with strangers. AI needs to play by these same systems, not replace them.
October 15, 2025 at 11:00 PM
Grateful to keynote at #COLM2025. Here's what we're missing about AI alignment: Humans don’t cooperate just by aggregating preferences, we build social processes and institutions to generate norms that make it safe to trade with strangers. AI needs to play by these same systems, not replace them.
Even when stronger models outweighed weaker ones, group accuracy decreased over successive debate rounds. Introducing weaker models into debates produced results that were worse than the results when agents hadn’t engaged in discussion at all.
September 23, 2025 at 5:06 PM
Even when stronger models outweighed weaker ones, group accuracy decreased over successive debate rounds. Introducing weaker models into debates produced results that were worse than the results when agents hadn’t engaged in discussion at all.