Top all-time · #3655
Alex Rogozhnikov
Personal blog · arogozhnikov.github.ioaimath
Alex Rogozhnikov writes Brilliantly wrong, a personal blog at arogozhnikov.github.io about ai and math. Since 2016, 21 different Hacker News readers have linked it 31 times, most often “Marching neural network”. It is still writing: the last post was on 2026-07-15, and you can follow it by feed.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link Alex Rogozhnikov's blog for explanatory posts on Markov chain Monte Carlo and Hamiltonian Monte Carlo, and for a post on calling Fortran code from Python.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Brilliantly Wrong — Alex Rogozhnikov's blog about math, machine learning, programming, physics and biology.
Most-linked posts?
- Marching neural network5 people · 5 mentions · first linked 2017-06-15
- Hamiltonian Monte Carlo explained4 people · 4 mentions · first linked 2016-12-22
- Gradient Boosting Interactive Playground2 people · 2 mentions · first linked 2016-07-18
- Reconstructing pictures with machine learning2 people · 2 mentions · first linked 2016-02-18
- Jupyter (IPython) notebooks features2 people · 2 mentions · first linked 2016-09-14
- Hamiltonian Monte Carlo Explained (2016)2 people · 2 mentions · first linked 2020-12-09
- Don't write command-line interfaces (and how to write if you have to)2 people · 2 mentions · first linked 2020-10-09
What Hacker News says?
Good paper indeed. And here's a nice blog post with nice visualizations for MCMC and Hamiltonian MC. https://arogozhnikov.github.io/2016/12/19/markov_chain_monte...
Comment linking /2016/12/19/markov_chain_monte_carlo.html
on “Ask HN: What's the best paper you've read in 2020?”Submitted Hamiltonian Monte Carlo explained as a story · 210 points
HN discussionWhy not using both ? You can reuse existing fortran code withing Python, and benefit from the prior experience and speed while enjoying the qualities of Python. There are several ways to bind Python and fortran together. E.G http://arogozhnikov.github.io/2015/11/29/using-fortran-from-...
Comment linking /2015/11/29/using-fortran-from-python.html
on “Why physicists still use Fortran (2015)”Submitted Marching neural network as a story · 113 points
HN discussiondescribed here: http://arogozhnikov.github.io/2013/07/20/blog-post.html
Comment linking /2013/07/20/blog-post.html
on “Hamiltonian Monte Carlo explained”Submitted Gradient Boosting Explained in 3D as a story · 105 points
HN discussionSubmitted Fastest autograd in the West as a story · 90 points
HN discussionSubmitted Don't write command-line interfaces (and how to write if you have to) as a story · 13 points
HN discussionSubmitted Reconstructing pictures with machine learning as a story · 13 points
HN discussionSubmitted Hamiltonian Monte Carlo explained as a story · 7 points
HN discussionSubmitted Jupyter (IPython) notebooks features as a story · 6 points
HN discussionSubmitted Visualizing neural networks in 3D as a story · 3 points
HN discussionSubmitted Hamiltonian Monte Carlo explained as a story · 3 points
HN discussionSubmitted Machine Learning in Science and Industry Slides as a story · 3 points
HN discussionSubmitted Jupyter (IPython) notebooks features as a story · 3 points
HN discussionSubmitted Einops, Retrospective of 5 Years as a story · 2 points
HN discussionSubmitted Delimiter-First Code as a story · 2 points
HN discussionSubmitted Things I wish someone told me about microscopy (2020) as a story · 2 points
HN discussionSubmitted Don't write command-line interfaces (generate them) as a story · 2 points
HN discussionSubmitted Hamiltonian Monte Carlo explained in 3D as a story · 2 points
HN discussionSubmitted Writing a better code with pytorch and einops as a story · 2 points
HN discussionSubmitted Marching neural network: Visualizing level surfaces of a neural network as a story · 2 points
HN discussionSubmitted Gradient Boosting Interactive Playground as a story · 2 points
HN discussionSubmitted Hamiltonian Monte Carlo Explained (2016) as a story · 1 points
HN discussionSubmitted Neural Networks in 3D with WebGL as a story · 1 points
HN discussionSubmitted Numbers that lie to you (2020) as a story · 1 points
HN discussionSubmitted GitHype – tool for scanning GitHub for fresh popular repositories on some topic as a story · 1 points
HN discussionSubmitted Interactive demonstrations for ML courses (2016) as a story · 1 points
HN discussionSubmitted Reconstructing pictures with machine learning (demo) as a story · 1 points
HN discussionSubmitted Neural networks in 3d with webGL as a story · 1 points
HN discussion
