Hacker News Reader

1eon The Next Decade Could Be Even Worse

Thank you for the succinct summary. You might be interested in one theory on why Elizabeth Warren was so popular: https://americanaffairsjournal.org/2019/11/the-real-class-wa...

1eon Hunting for Malicious Packages on PyPI

i really enjoyed this write up. i am glad someone far smarter than me is thinking about this problem.

1eon Launch HN: Deepnote (YC S19) – A better data science notebook

jupyter = julia + python + r

1eon How Transformers Work (2019)

in my experience, it is more useful to view neural nets as geometric transformations - via stateful functions - that map stuff in input space (eg a sentence written in english) to stuff in some other space (eg the same sentence written in french).

by viewing neural nets (and machine learning, in general) from a mathematical perspective, you can readily exploit an entire field of tools and techniques (eg numerical optimization) and clearly define objective functions to train against - benefits that you dont necessarily get by viewing ml from a biological perspective.