Karim Abdel Sadek

I was recently awarded the prestigious Cooperative AI PhD Fellowship, which will support me with complete funding for the entire duration of my PhD. I am applying for PhD positions for the Fall 2025 intake, feel free to reach out if you would like to chat!
Hi, Iโm Karim! I am an MSc student at the University of Amsterdam. Currently, I am an intern at the Krueger AI Safety Lab, University of Cambridge, working on Goal Misgeneralization and Unsupervised Environment Design supervised by Michael Dennis, Usman Anwar and David Krueger.
Starting in January 2025, I will be a research intern at the Center of Human Compatible AI, UC Berkeley, working on preference learning, changing preferences, and influence incentives of assistive AI systems. At CHAI, I will be supervised by Micah Carroll and Anand Siththaranjan.
I am broadly interested in topics at the intersection of Multi-Agent AI systems, Reinforcement Learning, AI alignment, Game Theory, and Cooperative AI.
Before my MSc, I graduated with a BSc in Mathematics and Computer Science for AI from Bocconi University. I was advised by Marek Elias, working on algorithms with predictions and theory of algorithms. Our paper has been accepted at ICLR 2024. During my BSc, I spent the Spring โ23 semester at Georgia Tech, supported with a full-ride scolarship.
If you are interested in working together, have a quick chat, or anything else, please reach out! You can e-mail me at karim dot abdel dot sadek at student dot uva dot nl.
news
Dec 01, 2024 | I have been awarded the Cooperative AI PhD Fellowship which will fully support me for the duration of my upcoming PhD! |
---|---|
Nov 25, 2024 | Starting in January 2025, I will be a research intern at the Center for Human Compatible AI! |
May 15, 2024 | I am joining the Krueger AI Safety Lab as a Research Intern this summer in Cambridge! I will be supported by the ERA Fellowship. |
Jan 15, 2024 | My very first paper, โ๐๐ฅ๐ ๐จ๐ซ๐ข๐ญ๐ก๐ฆ๐ฌ ๐๐จ๐ซ ๐๐๐๐ก๐ข๐ง๐ ๐๐ง๐ ๐๐๐ ๐ฐ๐ข๐ญ๐ก ๐ซ๐๐๐ฎ๐๐๐ ๐ง๐ฎ๐ฆ๐๐๐ซ ๐จ๐ ๐ฉ๐ซ๐๐๐ข๐๐ญ๐ข๐จ๐ง๐ฌโ, has been accepted at ICLR with scores 8,8,8,8! ![]() |