Understanding Deep Learning(udlbook.github.io)

347 points by georgehill 2 years ago | 79 comments

Homepage for Simon J.D. Prince's book Understanding Deep Learning (MIT Press, 2023), offering a free draft PDF of chapters 1-21 under a CC license.

Feynman's Garden(marginalia.nu)

106 points by EvgeniyZh 2 years ago | 46 comments

OPML is underrated(kmaasrud.com)

167 points by thunderbong 2 years ago | 97 comments

Why DeepSeek had to be open source(getlago.com)

472 points by AnhTho_FR 1 year ago | 239 comments

Lago blog post arguing why DeepSeek had to release its models as open source and why that won't let it defeat OpenAI.

Lamport's Byzantine Generals Algorithm in Python(bytepawn.com)

14 points by Maro 1 year ago | 1 comments

Optimizers need a rethink(typesanitizer.com)

132 points by ingve 2 years ago | 139 comments

AI has access to a vastly larger working memory than the human brain(davidepiffer.com)

524 points by rzk 2 months ago | 452 comments

A Substack essay by Davide Piffer arguing that AI's edge over mathematicians comes from a vast symbolic working memory rather than superior reasoning.

I don't like NumPy(dynomight.net)

399 points by MinimalAction 1 year ago | 164 comments

A Dynomight blog essay critiquing NumPy's design, arguing its array broadcasting and indexing make complex computations confusing.

Google DeepMind(deepmind.com)

640 points by random_moonwalk 3 years ago | 573 comments

DeepMind blog post from April 20, 2023 announcing the merger of DeepMind and Google Brain into a single unit called Google DeepMind.

Beautiful branchless binary search(probablydance.com)

342 points by ingve 3 years ago | 128 comments

Blog post by Malte Skarupke presenting a branchless C++ binary search based on Shar's algorithm that runs over twice as fast as std::lower_bound in GCC.

Open-weight AI is having its Kubernetes moment(tobi.knaup.me)

369 points by tknaup 3 months ago | 287 comments

Blog post by Tobi Knaup arguing that open-weight AI models are at a moment comparable to Kubernetes' rise, and urging the community not to squander it.

FunSearch: Making new discoveries in mathematical sciences using LLMs(deepmind.google)

341 points by reqo 2 years ago | 79 comments

Google DeepMind blog post introducing FunSearch, a method that uses large language models to make new discoveries in mathematical sciences.