https://www.are.na/max-bo RSS for Node Sat, 25 Apr 2026 17:59:45 GMT Sun, 05 Apr 2026 05:45:10 GMT uncategorized]]> https://www.are.na/max-bo/uncategorized-ww0zx0gh1p0 https://www.are.na/max-bo/uncategorized-ww0zx0gh1p0 Sat, 25 Apr 2026 16:59:30 GMT single line motif]]> https://www.are.na/max-bo/single-line-motif https://www.are.na/max-bo/single-line-motif Sat, 25 Apr 2026 06:49:42 GMT ]]> https://www.are.na/block/44635144 https://www.are.na/block/44635144 Sat, 25 Apr 2026 06:49:23 GMT British political figures or members of the Royal Family in some degree of political strife or mortal danger who have or will imminently resign or die or be stripped of their position, photographed in cars]]> https://www.are.na/max-bo/british-political-figures-or-members-of-the-royal-family-in-some-degree-of-political-strife-or-mortal-danger-who-have-or-will-im https://www.are.na/max-bo/british-political-figures-or-members-of-the-royal-family-in-some-degree-of-political-strife-or-mortal-danger-who-have-or-will-im Sat, 25 Apr 2026 04:05:28 GMT A blazing fast CSS-in-GQL™ library. Contribute to braposo/graphql-css development by creating an account on GitHub.

]]> https://www.are.na/block/45571131 https://www.are.na/block/45571131 Fri, 24 Apr 2026 20:28:45 GMT elaborate shitposts]]> https://www.are.na/max-bo/elaborate-shitposts https://www.are.na/max-bo/elaborate-shitposts Fri, 24 Apr 2026 20:28:45 GMT In this paper, we make the case that a scientific theory of deep learning is emerging. By this we mean a theory which characterizes important properties and statistics of the training process, hidden representations, final weights, and performance of neural networks. We pull together major strands of ongoing research in deep learning theory and identify five growing bodies of work that point toward such a theory: (a) solvable idealized settings that provide intuition for learning dynamics in realistic systems; (b) tractable limits that reveal insights into fundamental learning phenomena; (c) simple mathematical laws that capture important macroscopic observables; (d) theories of hyperparameters that disentangle them from the rest of the training process, leaving simpler systems behind; and (e) universal behaviors shared across systems and settings which clarify which phenomena call for explanation. Taken together, these bodies of work share certain broad traits: they are concerned with the dynamics of the training process; they primarily seek to describe coarse aggregate statistics; and they emphasize falsifiable quantitative predictions. We argue that the emerging theory is best thought of as a mechanics of the learning process, and suggest the name learning mechanics. We discuss the relationship between this mechanics perspective and other approaches for building a theory of deep learning, including the statistical and information-theoretic perspectives. In particular, we anticipate a symbiotic relationship between learning mechanics and mechanistic interpretability. We also review and address common arguments that fundamental theory will not be possible or is not important. We conclude with a portrait of important open directions in learning mechanics and advice for beginners. We host further introductory materials, perspectives, and open questions at learningmechanics.pub.

]]> https://www.are.na/block/45571122 https://www.are.na/block/45571122 Fri, 24 Apr 2026 20:27:59 GMT to read]]> https://www.are.na/max-bo/to-read-yomybnjptwu https://www.are.na/max-bo/to-read-yomybnjptwu Fri, 24 Apr 2026 20:27:59 GMT Hi friends,

]]> https://www.are.na/block/45565057 https://www.are.na/block/45565057 Fri, 24 Apr 2026 18:29:57 GMT IN which we investigate using CSS as a query language, or even a general purpose programming language, to do things other than lay out web pages in a browser.

]]> https://www.are.na/block/45567862 https://www.are.na/block/45567862 Fri, 24 Apr 2026 18:22:54 GMT