AI & machine learning2021 · shared on Hacker News
Learning in High Dimension Always Amounts to Extrapolation
Explore Learning in High Dimension Always Amounts to Extrapolation, 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 #48407232 Comment #47012347 Comment #42563271 Comment #41987804 Comment #41834991 Comment #39592744 Comment #38651705 Comment #38190783 Comment #38180028 Comment #38179878 Comment #38141343 Comment #38140199 Comment #38052807 Comment #37668729 Comment #31569809 Comment #31417808 Comment #29509311
Yjbredeche ·
GitHub cuts AI deals with Google, Anthropic
897 points702 comments
Ynabla9 ·
Counterintuitive Properties of High Dimensional Space (2018)
248 points67 comments
Ydeltree7 ·
Gato – A Generalist Agent
140 points58 comments
Yjerpint ·
Performance of LLMs on Advent of Code 2024
135 points92 comments
YHard_Space ·
Training computer vision models on random noise instead of real images
133 points64 comments
Ydavidbarker ·
GPT-5.2 derives a new result in theoretical physics
100 points34 comments
Yoli5679 ·
The Scaling Hypothesis (2021)
97 points63 comments
Yhislaziness ·
Transformers struggle with generalizing tasks beyond pre-training data
36 points36 comments
YWarOnPrivacy ·
Large language models can do jaw-dropping things. But nobody knows why
13 points7 comments
Ywebmaven ·
The copyright fight over authors and OpenAI's ChatGPT
4 points1 comments
Ylordleft ·
No, Artificial Intelligence is not Conscious - Ted Chiang
4 points0 comments
YTerretta ·
Telling GPT-4 you're scared or under pressure improves performance
3 points0 comments
Ylogicallee ·
Ask HN: What is your standard for judging when AGI exists?
2 points0 comments
Yjazzyjackson ·
Ask HN: Have you seen anything original produced by generative AI?
1 points1 comments
Yog_kalu ·
Learning in High Dimension Always Amounts to Extrapolation
1 points0 comments
Ytosh ·
Learning in High Dimension Always Amounts to Extrapolation
1 points1 comments
Yreqo ·
FunSearch: Making new discoveries in mathematical sciences using LLMs
1 points0 comments