New comment by marketingan in "Making deep learning go brrrr from first principles (2022)"

marketingan — Sat, 23 May 2026 17:03:12 +0000

Deep learning is just glorified linear algebra. Master the progression: Feed-forward CNN RNN LSTM Attention. You don't even need a GPU to understand the climax; Karpathy’s llama2.c implements a full transformer inference engine in just ~300 lines of C using SIMD pragmas for CPU execution.

Hacker News: marketingan

New comment by marketingan in "Making deep learning go brrrr from first principles (2022)"