K Kyunghyun Cho personal blog

Softmax forever, or why I like softmax

kyunghyuncho.me 5 min read

[UPDATE: Feb 8 2025] my amazing colleague Max Shen noticed a sign mistake in my derivation of the partial derivative of the log-harmonic function below.

Points

184

HN comments

110

Submissions

1

Cited by

0 commenters

AI & Machine LearningProgramming Languages2025

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

RRikiya Takehi20262,957 points898 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,885 points641 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details