Top all-time · #7596
Soumith Chintala
Personal blog · soumith.chaiprogrammingcareer
Soumith Chintala's personal blog at soumith.ch covers ai, programming and career. Since 2015, 10 different Hacker News readers have linked it 11 times, most often “NeuralNets dreaming natural images”. No feed was found, so read it on the site itself.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN commenters link Soumith Chintala's personal site only for its about page, in a discussion of his absence from the Llama 3 model card contributor list. No comment judges his writing.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- NeuralNets dreaming natural images3 people · 3 mentions · first linked 2015-06-22
- Leaving Meta and PyTorch2 people · 2 mentions · first linked 2025-11-06
- Growing open source from Torch to PyTorch2 people · 2 mentions · first linked 2021-08-02
What Hacker News says?
Surprisingly, looks like Mark Zuckerberg is listed as a contributor in the Model Card [1]. I thought since its a pretty big effort, most executives would be added to it as well, but that does not seem to be the case at all. In fact I was surprised that Soumith Chintala was left out here [2]. [1] - https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md... [2] - https://soumith.ch/about/
Comment linking /about/
on “Meta Llama 3”Submitted Leaving Meta and PyTorch as a story · 721 points
HN discussionI don't think overfitting will be an issue (at all!) on a 65TB dataset. A bigger CNN model should be more effective at this task than a DBN, (almost) regardless of the features added. If we can use convolutional generative models (from raw noise -> images) to make this kind of stuff [1][2] I see no reason why it shouldn't be super effective to classify with a CNN. The equivalent DBN-type generative model for CIFAR10…
Comment linking /eyescream/
on “Deep Belief Networks at Heart of NASA Image Classification”Submitted Growing open source from Torch to PyTorch as a story · 78 points
HN discussionSubmitted How to train a model on 10k H100 GPUs? as a story · 33 points
HN discussionSubmitted NeuralNets dreaming natural images as a story · 11 points
HN discussionSubmitted Leaving PyTorch and Meta as a story · 7 points
HN discussionSubmitted Decisions and Pivots on PyTorch as a story · 6 points
HN discussionSubmitted The Eyescream Project: NeuralNets dreaming natural images as a story · 5 points
HN discussionSubmitted Growing open-source: from Torch to PyTorch as a story · 3 points
HN discussionSubmitted PyTorch's Design Origins as a story · 2 points
HN discussion
