Computer science2022 · shared on Hacker News
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Explore Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets, 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.
Ynandhinianand ·
I asked GPT-NeoX-20B a hundred arithmetic questions
175 points216 comments
Yparsadotsh ·
Socratic Models – Composing Zero-Shot Multimodal Reasoning with Language
115 points38 comments
Ynsoonhui ·
How do machines ‘grok’ data?
102 points16 comments
YYourCupOTea ·
Groq surpasses 1,200 tokens/sec with Llama 3 8B
43 points31 comments
Ycubefox ·
PaLM 2 Technical Report [pdf]
33 points8 comments
Yvincvinc ·
Jailbreaking ChatGPT with Dan (Do Anything Now)
11 points0 comments
Ymparrett ·
DyLoRA: Parameter Efficient Tuning of Pre-Trained Models
11 points0 comments
Y1wheel ·
Do Machine Learning Models Memorize or Generalize?
7 points0 comments
YIanNorris ·
Understanding the limits of large language models
4 points0 comments
YMaxLeiter ·
"They're made out of weights"
3 points0 comments
Ystygiansonic ·
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
2 points1 comments
Ythunderbong ·
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
2 points0 comments
Yrain1 ·
And yet It Understands
1 points0 comments
Ythenobsta ·
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
1 points0 comments
Yasmodeuslucifer ·
Who discovered grokking and why is the name hard to find?
1 points0 comments