Vincent Conitzer
banner
conitzer.bsky.social
Vincent Conitzer
@conitzer.bsky.social
AI professor. Director, Foundations of Cooperative AI Lab at Carnegie Mellon. Head of Technical AI Engagement, Institute for Ethics in AI (Oxford). Author, "Moral AI - And How We Get There."
https://www.cs.cmu.edu/~conitzer/
Our paper in the alignment track of AAAI'26: what if human feedback is unstable over time?
arxiv.org/abs/2511.10032
Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often...
arxiv.org
January 23, 2026 at 2:07 PM
Tomorrow (F) morning at 11am SG time, Emin Berker and Emanuel Tewolde will give a talk at AAAI on our paper below!
arxiv.org/abs/2512.16895
On the Edge of Core (Non-)Emptiness: An Automated Reasoning Approach to Approval-Based Multi-Winner Voting
Core stability is a natural and well-studied notion for group fairness in multi-winner voting, where the task is to select a committee from a pool of candidates. We study the setting where voters eith...
arxiv.org
January 22, 2026 at 2:04 PM
not a great look for Google
January 20, 2026 at 1:52 PM
"Oh look AI is figuring out human preferences from our behavior so things will be fine."
Suno (music-generating AI):
suno.com/s/pmQIY73ulk...
Fortress Protocol
Listen and make your own on Suno.
suno.com
January 19, 2026 at 1:59 PM
simple
January 18, 2026 at 1:38 PM
Soccer goalkeepers have to make some tough decisions during the game. This should clear things up.
January 14, 2026 at 2:35 AM
Congratulations to Markus Brill (and to Oxford) for starting a faculty position at Oxford CS! sites.google.com/site/brillma...
Markus Brill
Markus Brill Associate Professor, Department of Computer Science Tutorial Fellow, Oriel College University of Oxford
sites.google.com
January 11, 2026 at 6:32 PM
"could my teacher's husband and my wife's teacher be the same person?"
January 9, 2026 at 3:09 AM
more on having your son as your elementary school teacher
January 7, 2026 at 1:31 PM
Apparently in the 1960s/70s anything was possible.
January 6, 2026 at 2:15 PM
It is now ridiculously easy to make little games like this that you can just play in your web browser. (This one made with Claude.)
www.cs.cmu.edu/~conitzer/ke...
Kessler Syndrome: Satellite Collision Simulator
www.cs.cmu.edu
January 4, 2026 at 2:21 PM
Something about that last step seems very human ("I've spent enough time on this already!"). Can you find other mistakes?
January 2, 2026 at 5:10 PM
Congratulations to Brian Zhang for a 2025 AAAI/ACM SIGAI Dissertation Honorable Mention!
aaai.org/about-aaai/a...
brianhzhang.github.io
AAAI/ACM SIGAI Doctoral Dissertation Award - AAAI
The AAAI/ACM SIGAI Doctoral Dissertation Award recognizes and encourages superior research and writing by doctoral candidates in AI.
aaai.org
January 1, 2026 at 6:32 PM
Happy New Year everyone!
December 31, 2025 at 1:45 PM
"explain retirement accounts to me like I'm a kindergarten teacher" -- I'm sure kindergarten teachers love being talked to like this
December 30, 2025 at 7:06 PM
so close to an infinite money making scheme but that stupid Planck time gets in the way
December 28, 2025 at 9:46 PM
photography pro tip
December 28, 2025 at 3:00 AM
the archetype of the loud downstairs neighbor
December 23, 2025 at 11:00 PM
AI Overview, in a single response, disqualifies itself as a coach, a financial advisor, and a screenwriter.
December 21, 2025 at 12:22 AM
our upcoming AAAI paper on cooperative game theory in multi-winner voting, via an automated reasoning approach (using not satisfiability but mixed-integer linear programming); led by Emin Berker and Emanuel Tewolde!
arxiv.org/abs/2512.16895
On the Edge of Core (Non-)Emptiness: An Automated Reasoning Approach to Approval-Based Multi-Winner Voting
Core stability is a natural and well-studied notion for group fairness in multi-winner voting, where the task is to select a committee from a pool of candidates. We study the setting where voters eith...
arxiv.org
December 19, 2025 at 10:14 PM
The videos from this summer's Cooperative AI @coop-ai.bsky.social retreat are online now! Below is mine on "Cooperative AI via Simulations"
www.youtube.com/watch?v=I8ec...
Cooperative AI via Simulations by Vincent Conitzer
YouTube video by Cooperative AI Foundation
www.youtube.com
December 18, 2025 at 7:34 PM
family relationships logic
December 17, 2025 at 11:54 PM
"The Mechanics of Time & Self"
December 16, 2025 at 7:12 PM
The case against getting new soil for the yard.
December 15, 2025 at 1:41 AM