AI & machine learning2022 · shared on Hacker News
Why Can GPT Learn In-Context? Language Models Perform Gradient Descent
Explore Why Can GPT Learn In-Context? Language Models Perform 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.
Comment #40900563 Comment #37777476 Comment #35931724 Comment #35684509 Comment #35684242 Comment #35389345 Comment #35367296 Comment #35323516 Comment #35287127 Comment #35192562 Comment #35187059 Comment #35179275 Comment #35178673 Comment #35160483 Comment #35115833 Comment #35022796 Comment #35005133 Comment #34960684 Comment #34881486 Comment #34797185 Comment #34754312 Comment #34726419 Comment #34248526
Ye0m ·
GPT-4
499 points201 comments
Ybelter ·
Reasoning in Large Language Models: A Geometric Perspective
214 points171 comments
Ymarviel ·
GPT-4 Designed a Programming Language
26 points9 comments
Ycolinprince ·
The Expanding Dark Forest and Generative AI
22 points3 comments
Ylucidguppy ·
The Philosophy of Computer Science
17 points15 comments
Ywashedup ·
What Is ChatGPT Doing and Why Does It Work?
16 points8 comments
Ythinxer ·
Sparks of Artificial General Intelligence: Early Experiments with GPT-4
6 points1 comments
Ygeorgehill ·
Do large language models need sensory grounding for meaning and understanding?
6 points0 comments
Ysimonw ·
Large language models are having their Stable Diffusion moment
4 points0 comments
Ysquidhunter ·
GPT in 60 Lines of NumPy
3 points0 comments
Yxaedes ·
Why Can GPT Learn In-Context? Language Models Perform Gradient Descent
2 points0 comments
Yssaddi ·
ChatGPT Is a Blurry JPEG of the Web
2 points1 comments
Ysonabinu ·
To Build Truly Intelligent Machines, Teach Them Cause and Effect
2 points0 comments
Ylnyan ·
Prompt to bypass the restrictions of Bing Chat or to restore the old “Sydney”
2 points0 comments
Ytejohnso ·
OK, it’s time to freak out about AI
2 points0 comments
Yduck ·
AI-enhanced development makes me more ambitious with my projects
2 points0 comments
Ypanabee ·
Scaling Transformer to 1M tokens and beyond with RMT
2 points0 comments
Ybelter ·
Chatbots Don’t Know What Stuff Isn’t
2 points0 comments
Ymuggermuch ·
Ring Attention with Blockwise Transformers for Near-Infinite Context
2 points0 comments
Yfreeqaz ·
Cerebras-GPT vs. LLaMA AI Model Performance Comparison
1 points0 comments