Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #10916

B

Bounded Rationality

Personal blog · bjlkeng.github.iomathai

Bounded Rationality is a personal blog at bjlkeng.github.io about math and ai. Since 2020, 7 different Hacker News readers have linked it 7 times. It is still writing: the last post was on 2026-03-10, and you can follow it by feed.

Visit the blog
7mentions?
7HN people?
2020–2023first – last linked?
Links on Hacker News per year · peak 3 in 2020

Too few sampled comments (5) to say how often HN recommends it.?

Why HN links it

HN readers link Bounded Rationality for long, technical explainers on machine learning, lossless compression and tensors. Commenters cite it as a clearer account than the original papers.

Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Understanding math, machine learning, and data to a satisfactory degree.

What Hacker News says?

  1. I wonder if a two step process could work better than this, first use a variational autoencoder or simple an autoencoder then use it to train the labeled sampled. In (1) there is a full example of using the two step strategy but using more labeled data to obtain 92% of accuracy. Someone can try changing the second part to use only ten labels for the classifying part and share results? (1) https://www.datacamp.com/co…

    Comment linking /posts/semi-supervised-learning-with-variational-autoencoders/

    on “Illustrated FixMatch for semi-supervised learning”
  2. Submitted Hamiltonian Monte Carlo as a story · 2 points

    HN discussion
  3. twic · 2020-12-17Recommends
    Zstandard uses finite state entropy (FSE) for entropy encoding (after finding repeats), which in turn us based on asymmetric numeral system (ANS) encoding. The canonical paper on ANS is indecipherable to me (i honestly think it's poorly written, it's not just me, although it is partly me!), but this seems like a clearer explanation (although i still don't entirely get it): https://bjlkeng.github.io/posts/lossless-co…

    Comment linking /posts/lossless-compression-with-asymmetric-numeral-systems/

    on “Zstandard v1.4.7”
  4. Submitted Hyperbolic Geometry and Poincaré Embeddings as a story · 2 points

    HN discussion
  5. https://bjlkeng.github.io/posts/lossless-compression-with-la... ?

    Comment linking /posts/lossless-compression-with-latent-variable-models-using-bits-back-coding/

    on “A secret language of cells? New cell computations uncovered”
  6. I follow these three for AI progress and concepts - http://karpathy.github.io/ (best one) - http://bjlkeng.github.io/ - https://lilianweng.github.io/lil-log/

    Comment linking /

    on “Ask HN: What niche blogs are worthwhile to follow in 2021?”
  7. KeyXiote · 2022-10-10Recommends
    Have been interested in similar abstractions, take a look at contravarient and covariant tensors. Great in depth on Tensors and relational ML databases: (1) https://bjlkeng.github.io/posts/tensors-tensors-tensors/

    Comment linking /posts/tensors-tensors-tensors/

    on “j/0=1”

Search all of HN for bjlkeng.github.io

Linked by the same people?