Alfred studied Natural Sciences and then completed a PhD in physics at University College London. His PhD focused on feedback loops in quantum mechanics. In January 2024 he took part in AI Safety Camp and became interested in studying agent foundations.
José is an undergraduate at the University of Sao Paulo focusing on mathematics and computer science. He has done undergraduate research in PDEs. He first heard about AI safety in a camp for Brazilian students about EA/AIS called Condor Camp. Since then, he received a grant to study Jacob Hilton’s Deep Learning Curriculum and also created from scratch and taught at a program called CondorXL (designed for Condor alumni to upskill in Deep Learning).
His research taste, on the other hand, has always been very theory-oriented and he is excited about pretty much anything that involves math and proving theorems.
Dalcy is an undergraduate at Harvard and was a 2023 Atlas Fellow. They are currently interested in saying interesting things about the convergent behavioral and structural properties of agents or learning systems that are selected by some criterion.
Daniel is an Applied Mathematics MSC student at Imperial College London. He is interested in ontology identification, general purpose search, natural latents, formalizations of optimization, and understanding principles of intelligence in general, such as meta-learning and constructing modular world models.
Alex is an independent agent foundations researcher currently leading the Dovetail research group. He was formerly a MIRI fellow, MATS scholar, AI Safety Camp research lead, and two-time college dropout. He is interested in figuring out everything described in the Dovetail wiki. His special interests have a duration of interest that is drawn from a Pareto distribution, and currently include human prehistory and the development of writing systems.
