Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
When I’m working on a research problem I generally begin by filling dozens of sheets of scratch paper with partial calculations. When I eventually get to a point where I can think about the problem while swimming, then I’m often ready to solve it.
Knuth Airgaps & Knuth Buffers
Taylor Troesh
A three second warning can’t compete against 45 minutes of seeing charismatic and funny guys do reckless things.
Be Wary of Imitating High-Status People Who Can Afford to Countersignal
Rob Henderson
The only issue is that it missed out on two decades of hardware development (and a bag of other optimization tricks). Modern deep learning implementations requires machine sympathy at scale. It also doesn't have any literature on autoregressive networks like RNNs or image processing tricks like CNNs.
Ask HN: What Are the Foundational Texts for Learning About AI/ML/NN?
ycombinator.com
...catch up on these, and many more highlights
Readwise