Great opportunity for prospective phd students and postdocs to learn from Vera Liao on Responsible AI & HCI & explainable AI. So excited for Vera's new journey as a professor!

Wow, LaTeX poster

🚨 New paper: We find that even safety-tuned LLMs learn to manipulate vulnerable users when training them further with user feedback 🤖😵‍💫 In our simulated scenarios, LLMs learn to e.g. selectively validate users' self-destructive behaviors, or deceive them into giving 👍. 🧵👇

This is a lovely, relatable, thoughtful talk by Niloofar (✈️ ACL) ! I was rowing while listening to it but eventually stopped rowing to pay a closer attention to it.

Yesterday GOV.UK released the first International #AI Safety Report 2025, which is a collaboration of independent experts & researchers including Princeton Center for Information Technology Policy's Arvind Narayanan, Ed Felten, & Sayash Kapoor. Read the full report now: assets.publishing.service.gov.uk/media/679a0c48…

Students might be on spring break, but that just might be the perfect time to catch up on past Tuesday Seminars at #CITP you've missed. Check out guest lecturers on our Youtube! Recents include Steven Kelts, Inyoung Cheong, Parastoo Abtahi + sohyeon hwang 📺👇 youtube.com/@citpprinceton

Congrats 🎉 and thanks for letting me play a small role. Check out this #CHI2025 award paper where we found human self-confidence can be swayed by AI confidence, challenging the assumption that human-AI complementarity can be reached by considering human confidence as static

Can't wait to interview award-winning science fiction author Annalee Newitz about her new book Automatic Noodle at Third Place Books! eventbrite.com/e/annalee-newi…

The semester might be over, but researchers, students, and faculty alike stay busy during the summer months. We can't wait to see what CITP postdoc Inyoung Cheong get into at her fellowship at Consumer Reports innovation.consumerreports.org/2025-public-in…

Ryan's beautiful sentences with time-tested, interdisciplinary insights for $40. I agree it's a steal, especially given how expensive law books are!

Pleased to share our new piece nature titled: "We Need a New Ethics for a World of AI Agents". AI systems are undergoing an ‘agentic turn’ shifting from passive tools to active participants in our world. This moment demands a new ethical framework.