AI & machine learning2017 · shared on Hacker News
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer
Explore Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer, 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 ·
The Llama 4 herd
1,235 points658 comments
Ydanicgross ·
Jeff Dean’s Lecture for YC AI [video]
439 points56 comments
Ydwighttk ·
AI Search: The Bitter-Er Lesson
312 points214 comments
Yvinhnx ·
Hand-picked selection of articles on AI fundamentals/concepts
214 points18 comments
Yaaronyy ·
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer
200 points81 comments
Ygaleos ·
Lamini Memory Tuning: 10x Fewer Hallucinations
128 points57 comments
Ygodelmachine ·
Deep Learning and Its Implications for Computer Architecture and Chip Design
126 points24 comments
Yvinhnx ·
Kimi-K3 Technical Report [pdf]
117 points15 comments
YMrUssek ·
GShard: Scaling giant models with conditional computation and automatic sharding
112 points35 comments
Yreiinakano ·
Show HN: Xcessiv – Fully managed web application for automated machine learning
108 points5 comments
Ytosh ·
Visualizing expert firing frequencies in Mixtral MoE
99 points23 comments
Ymsoad ·
Outrageously Large Neural Nets: Sparsely-Gated Mixture-of-Experts Layer (2017)
65 points33 comments
Yhsikka ·
Ask HN: Are modular neural networks an interesting avenue for further research?
43 points12 comments
Yxyzzyrz ·
Mistral "Mixtral" 8x7B 32k model [magnet]
23 points12 comments
Yandreyk ·
Skynet Today – accessible and informed coverage of AI hype and panic
16 points5 comments
Ycratermoon ·
FTC investigating ChatGPT over potential consumer harm
9 points0 comments
Ytonybeltramelli ·
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer
3 points0 comments
Ytomssilver ·
Outrageously Large Neural Networks
3 points0 comments
Yserialx ·
Outrageously Large Neural Networks: Up to 137B Parameters
2 points1 comments
Ytuxguy ·
How to scale LLMs better with an alternative to transformers
2 points0 comments
Ygeorgehill ·
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
2 points1 comments
Ygroar ·
Outrageously Large Neural Networks
1 points0 comments
Ygeorgehill ·
Mistral: Mixtral of Experts
1 points0 comments
Yswatson741 ·
The Sparsely-Gated Mixture-of-Experts Layer (2017) [pdf]
1 points0 comments