Top all-time · #16263
Chizoba Obasi
Personal blog · chizkidd.github.ioaimath
Chizoba Obasi's personal blog at chizkidd.github.io covers ai and math. Since 2025, 4 different Hacker News readers have linked it 19 times, most often “Sam 2 deep dive: why its FIFO memory eviction bothers me”. It is still writing: the last post was on 2026-09-17, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
One HN commenter links this site's backpropagation post and advises caution about using the site's machine learning equations as a reference, citing a definition of backpropagation from another blog.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Exploring Deep Learning.
Most-linked posts?
- Sam 2 deep dive: why its FIFO memory eviction bothers me2 people · 2 mentions · first linked 2026-04-22
- A Complete Guide to Neural Network Optimizers2 people · 2 mentions · first linked 2026-01-26
What Hacker News says?
I would echo some caution if using as a reference, as in another blog the writer states: "Backpropagation, often referred to as “backward propagation of errors,” is the cornerstone of training deep neural networks. It is a supervised learning algorithm that optimizes the weights and biases of a neural network to minimize the error between predicted and actual outputs.." https://chizkidd.github.io/2025/05/30/backprop…
Comment linking /2025/05/30/backpropagation/
on “Important machine learning equations”Submitted Important machine learning equations as a story · 302 points
HN discussionSubmitted Understanding FlashAttention Pt 1: Personal Notes as a story · 13 points
HN discussionSubmitted FlashAttention: Part 2 as a story · 2 points
HN discussionSubmitted Sam 2 deep dive: why its FIFO memory eviction bothers me as a story · 2 points
HN discussionSubmitted Tonal Fidelity in Multilingual ASR: A Diagnostic Evaluation as a story · 2 points
HN discussionSubmitted Mixture of Experts (Moe): How Transformers Scale Without Activating Everything as a story · 1 points
HN discussionSubmitted Attention Became Efficient and Scalable: KV Caching, MQA, GQA, MLA, and DSA as a story · 1 points
HN discussionSubmitted Policy Gradient Methods as a story · 1 points
HN discussionSubmitted Sam 2: Segment Anything in Images and Videos as a story · 1 points
HN discussionSubmitted Transformers as a story · 1 points
HN discussionSubmitted Muon and MuonClip Optimizers as a story · 1 points
HN discussionSubmitted Inkcast: A Free, Browser-Based Audiobook Player as a story · 1 points
HN discussionSubmitted Sutton and Barto, Ch. 11: Off-Policy Methods with Approximation (Personal Notes) as a story · 1 points
HN discussionSubmitted On-Policy Prediction with Approximation as a story · 1 points
HN discussionSubmitted Sutton and Barto, Ch. 08: Planning and Learning with Tabular Methods as a story · 1 points
HN discussionSubmitted Architectural and Mathematical Foundations of Machine Learning as a story · 1 points
HN discussionSubmitted A Complete Guide to Neural Network Optimizers as a story · 1 points
HN discussionSubmitted A Complete Guide to Neural Network Optimizers as a story · 1 points
HN discussion