Watch it on YouTube here.
A discussion on the philosophy of deep learning, mechanistic interpretability and the epistemology of LLMs.
Dr Matthieu Queloz is a Privatdozent at the University of Bern. He is the author of two books: The Practical Origins of Ideas and The Ethics of Conceptualization, both published open access with Oxford University Press. He was recently awarded a two-million-dollar grant to lead a research project on concepts, understanding, and reasoning in Large Language Models.
You can find more of Dr Queloz’s work at https://www.matthieuqueloz.com/
Pierre Beckmann is an AI researcher working in Philosophy of AI and Philosophically-motivated AI. He is currently a PhD student in the Neuro-Symbolic AI group of Idiap and EPFL. Pierre also keeps close ties to the Institute for Philosophy of Bern, where I worked as a research assistant.
You can find more of Pierre’s work at https://bepierre.github.io/
