Ideas & society2022 · shared on Hacker News
Transformers learn in-context by gradient descent
Explore Transformers learn in-context by gradient descent, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
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.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ygeorgehill ·
ARC-AGI without pretraining
351 points121 comments
Yszopa ·
Teaching ChatGPT to Speak My Son’s Invented Language
5 points0 comments
Ydanboarder ·
Do Large Language Models learn world models or just surface statistics?
3 points0 comments
YlostConnection ·
ChatGPT Hype Is Proof Nobody Understands AI
3 points2 comments
Ysva_ ·
Transformers learn in-context by gradient descent
1 points0 comments
Yamichail ·
GPT-4 gets a B on my quantum computing final exam
1 points0 comments