Getting Here: Enter the lobby at 100 University Ave (right next to St Andrew subway station), and message Giles Edkins on the meetup app or call him on 647-823-4865 to be let up to room 6H.
Join a friendly and intelligent group as we discuss the future of AI and Machine Learning and how to help ensure the dramatic changes will go well.
Mesa Optimizers and how they fit into Robustness Frameworks
Details
Preparation: Please try to watch the video, Mesa Optimizers and Inner Alignment by Robert Miles
Getting Here: Enter the lobby at 100 University Ave (right next to St Andrew subway station), and message Giles Edkins on the meetup app or call him on 647-823-4865 to be let up to room 6H.
Join a friendly and intelligent group as we discuss the future of AI and Machine Learning and how to help ensure the dramatic changes will go well.
This week Ariel will discuss mesa optimizers and how they fit into more traditional ML robustness frameworks. We’ll go in detail into the “Risks from Learned Optimization” paper, and reference other papers such as “Uncovering mesa-optimization algorithms in Transformers”.
We welcome a variety of backgrounds, opinions and experience levels.