Matrix multiplies have the property that as the size of inputs grow, the ratio of compute, O(n^3), to data access, O(n^2), improves. If you can dedicate hardware to speeding up arithmetic and coordinating data movement you can exploit this,
Interesting approach based entirely on GitHub Actions. Not super accurate for most teams, but…
The largest truly open library in human history. 📈 61,344,044 books, 95,527,824 papers — preserved forever.
Some good approaches to handling ACME DNS challenges.