Ressources

On this page, I want to share various ressources (research papers, lectures, blog posts, websites…) that I enjoyed watching or reading.

Some Tips For Doing Research

• How to do research ? (Bill Freeman, MIT)
• How I think About My Research (Neel Nanda, Google DeepMind)
• Research Taste Exercises (Chris Olah, Anthropic)
• Research as a Stochastic Decision Process (Jacob Steinhardt, Berkeley)
• Being Impactful as a Researcher (Dwarkesh Patel, Sholto Douglas, Trenton Bricken) ; Full Podcast Episode
• Great “80,000 Hours” Podcast Episode on How To Do Research (Neel Nanda, Google DeepMind)

Technical Writing Advice

• Common mistakes in technical writing (Wojciech Jarosz, Dartmouth)
• Highly Opinionated Advice on How to Write ML Papers (Neel Nanda, Google DeepMind)
• How to ML Paper - A brief Guide (Jakob N. Foerster, University of Oxford)
• How to ML Rebuttal - A brief Guide (Jakob N. Foerster, University of Oxford)
• Some Notes on Writting (Mark Scmidt, University of British Columbia)

AI / Machine Learning Positions

• The Bitter Lesson (Rich Sutton, University of Alberta)
• From Scaling to Research (Dwarkesh Patel, Ilya Sutskever)
• Can AI do scientific research? (Lex Fridman, Demis Hassabis)

Lectures

• Causal Representation Learning: A Natural Fit for Mechanistic Interpretability (Dhanya Sridhar, Université de Montréal / MILA)
• Lecture Series on Probabilistic ML (Philipp Hennig, University of Tübingen)
• Causal Mechanistic Interpretability((Atticus Geiger, Stanford))