Curated reading list of foundational AI / deep learning papers — reportedly the ~30 papers Ilya Sutskever gave John Carmack, with the line that if you really learn all of them you’ll know 90% of what matters. The site hosts each paper in full with plain-language explanations of hard terms.
Link: https://30papers.com/
To read — good candidate to cross-reference against the interpretability / IRL reading roadmap.