h/t Eric Michaud for sharing his paper with me.

There's a tradition of high-impact ML papers using short, punchy categorical sentences as their titles: Understanding Deep Learning Requires Rethinking Generalization, Attention is All You Need, Language Models Are Few Shot Learners, and so forth.

A new paper by Simon et al. seeks to expand on this tradition with not a present claim but a future tense, prophetic future sentence: “There Will Be a Scientific Theory of Deep Learning”.

There's a lot of pessimism toward deep learning theory basically everywhere: the people building the AIs are pretty pessimistic, the academic AI researchers are as a general rule pessimistic (even people who used to do theory!), and with the exception of maybe 3-4 research groups, the independent AI safety ecosystem has long since given up on hoping for a theory to understand deep learning.

The paper is less of a neutral assessment of the evidence and more of a manifesto arguing for a particular theoretical deep learning research agenda. Given the overall sense of doom and gloom, its form makes sense: any less and it might not be enough to shine through the general sense of pessimism to [...]

---

First published:
April 24th, 2026

Source:
https://www.lesswrong.com/posts/2WkeiYFT5p3ph8Pkf/quick-paper-review-there-will-be-a-scientific-theory-of-deep

---

Narrated by TYPE III AUDIO.

“Quick Paper Review: “There Will Be a Scientific Theory of Deep Learning”” by LawrenceC

LessWrong (30+ Karma)