Multi-Agent Safety Hackathon Hub at EPFL
Join us for an exciting local hackathon event focused on Multi-Agent Safety at EPFL! Hosted by Lausanne AI Alignment (LAIA), this 48-hour event is the perfect opportunity to search for the most concerning failures specific to systems of multiple AIs.
As part of this hackathon, you will have the chance to become co-author on a large report on multi-agent risk with the Cooperative AI Foundation and more than 35 co-authors from institutions including UC Berkeley, Oxford, Cambridge, Harvard, and DeepMind. If your project submission of multi-agent failure demonstrations fits into the final report, you will be included as a co-author.
Our local event is a great way to work together with like-minded individuals and make new connections in the field of AI.
Here is the schedule of the event:
Friday 17:00 UTC: Keynote talk with Lewis Hammond and Esben Kran
Saturday afternoon: Project discussions with Lewis Hammond
Saturday evening: Two technical talks explaining approaches to this problem
Sunday afternoon: Project discussions with Lewis Hammond
Sunday evening: Ending session with Lewis Hammond
Our submissions will be evaluated based on several criteria, including multi-agent risk demonstration, reproducibility and originality. You will have access to many resources for inspiration, including ideas lists, research papers, and code bases.
If you are passionate about AI and want to make a meaningful contribution to the field, this is the event for you. Join us for a weekend of intensive research, collaboration, and fun!
Additionally, we want to ensure that all participants are well-fed and hydrated throughout the event, so we will be providing food and drinks to keep your energy levels up.
Find more information at the following link: https://alignmentjam.com/jam/multiagent