AI & machine learning2025 · shared on Hacker News

Self-attention transforms a prompt into a low-rank weight-update

Explore Self-attention transforms a prompt into a low-rank weight-update, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

Read original

The conversation around the idea.

Original Hacker News threads. Different perspectives, questions, and things worth thinking about.

Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.

YLabo333 ·

Self-attention transforms a prompt into a low-rank weight-update

17 points1 comments
YJnBrymn ·

Learning without training: The implicit dynamics of in-context learning

2 points0 comments
Yomarsar ·

The Implicit Dynamics of In-Context Learning

1 points0 comments
Ysimonpure ·

Learning without training: The implicit dynamics of in-context learning

1 points0 comments

One idea leads to another.

Explore more papers