sbondaryev
Re:
on Monday October 12, 2026 @12:42PM (#50059026)
An interactive guide to Diffusion Transformers and Flow Matching, using a simple model that turns random dots into shapes.
Re:A Transformer Plays Tic-Tac-Toe
on Thursday September 03, 2026 @10:25AM (#49550341)
Thanks for resharing!
Re:How a Transformer Plays Tic-Tac-Toe
on Friday July 10, 2026 @05:24AM (#48857689)
Thanks for sharing!
Re:
on Thursday May 21, 2026 @08:12AM (#48221376)
An interactive guide to how attention, embeddings, and positional encoding work together to predict the next move.
Re:Solving Mastermind with Maximum Entropy
on Friday February 13, 2026 @11:21AM (#47004443)
Inspired by 3Blue1Brown's Wordle video I applied maximum entropy to Mastermind.
The solver averages 4.42 guesses across all 1296 possible codes.
Includes an interactive game where you can see the optimal next move.
Re:Monosketch
on Friday February 13, 2026 @08:57AM (#47002749)
That's fair. It's just a suggestion - it's been useful for me in early stages of UI prototyping.
Re:Monosketch
on Friday February 13, 2026 @08:01AM (#47002249)
Nice project!
This pairs nicely with ASCII-Driven Development - for iterating and modifying layouts with AI.
https://medium.com/@calufa/ascii-driven-development-850f6666...
Re:Ask HN: What Are You Working On? (February 2026)
on Monday February 09, 2026 @07:38AM (#46944577)
https://sbondaryev.dev/
An attempt to build intuition with interactive articles and experimentation, inspired by explorabl.es
Re:Chess OCR: End-to-end ML pipeline running in the browser
on Wednesday January 28, 2026 @11:41AM (#46797745)
Hi HN,
I built a chess position recognition system that runs entirely in the browser.
The project walks through the full pipeline: manually collecting data from book scans, comparing Autoencoders vs. SimCLR for representation learning, and deploying with ONNX Runtime and Pyodide to avoid server costs.
The included demo recognizes board diagrams and generates Lichess links for analysis.
Chess OCR: End-to-end ML pipeline running in the browser
Re:Show HN: I quit coding years ago. AI brought me back
on Sunday January 18, 2026 @08:44PM (#46674168)
Nice project! One small suggestion, adding a search or category filter would help simplify navigation given the number of calculators available.
Re:Just the Browser
on Friday January 16, 2026 @08:20AM (#46646093)
Nice touch - seeing the Windows 95 IE favicon took me back for a while.
Re:Tldraw pauses external contributions due to AI slop
on Thursday January 15, 2026 @07:15PM (#46641377)
Seems like reading the code is now the real work. AI writes PRs instantly but reviewing them still takes time. Everything flipped. Expect more projects to follow - maintainers can just use ai themselves without needing external contributions.
Show HN: Why Neural Networks Need He Init, Clipping, and Momentum
https://sbondaryev.dev/articles/he-init-clipping-momentum
Hi HN,I made an interactive guide showing why neural networks need specific training techniques.Start with a simple network trying to learn x². Each section introduces a problem like gradient explosion or dead neurons and shows the fix that solves it using ReLU activation, He initialization, gradient clipping, and momentum.All code is editable and runs in the browser.
Re:Ask HN: Could you share your personal website here?
on Wednesday January 14, 2026 @04:34PM (#46623881)
https://sbondaryev.dev/
An attempt to build intuition with interactive articles and experimentation, inspired by explorabl.es
Re:Reproducing DeepSeek's MHC: When Residual Connections Explode
on Monday January 12, 2026 @10:47AM (#46590011)
Nice visualization of the residual connections. Is the animated svg manually created or programmatically generated? What tools did you use?
Re:Ask HN: What Are You Working On? (January 2026)
on Monday January 12, 2026 @09:36AM (#46589106)
It's a website https://sbondaryev.dev/
Re:Ask HN: What Are You Working On? (January 2026)
on Sunday January 11, 2026 @01:26PM (#46578186)
I'm working on interactive explorations of algorithms and machine learning.
Small, visual, hands-on demos that help build intuition by letting people tweak code/parameters and see how things behave in real time.
Re:Show HN: Typical is TypeScript with type-safety at runtime
on Sunday January 11, 2026 @07:05AM (#46574995)
This looks promising - I've always found the schema duplication annoying with Zod/Yup.
Would be great to see benchmarks vs Typia/ArkType at https://moltar.github.io/typescript-runtime-type-benchmarks/
Re:ASCII-Driven Development
on Saturday January 10, 2026 @03:18PM (#46569516)
Great idea, thanks for sharing!
Tried your prompts with ChatGPT and Claude than iterated on it. The ASCII doesn't render perfectly in the web interface but looks good when copy/pasted into a text editor.
Key benefit: I used to iterate on layout by generating HTML+Tailwind directly, which burns tokens fast. This ASCII approach lets you nail the structure first without the token cost. Much better for free tier usage.
Appreciate the writeup!
Re:Lights and Shadows
on Saturday January 10, 2026 @10:29AM (#46566498)
It really depends on your level - this kind of graphics work is usually learned over many years.
Some sources
> Math & motion: – The Nature of Code https://natureofcode.com/ – Coding Math https://www.youtube.com/user/codingmath
> Shaders / math-based rendering: – The Book of Shaders https://thebookofshaders.com/ – Inigo Quilez https://iquilezles.org/
> Interactive explanations: – Red Blob Games https://www.redblobgames.com/
You can also find some insight into his work process here: https://x.com/BCiechanowski/status/1387827101294686210?s=20
Most people doing this level of work built their own tools over time, learned a bit here and there, and kept refining things throughout their career.
Re:Show HN: I made a memory game to teach you to play piano by ear
on Friday January 09, 2026 @01:27PM (#46557203)
Nice project! I'm not very strong at note recognition, so I see the “Wrong note” message quite often (which is totally fine), but the frequent blinking feels a bit distracting. You might consider making the feedback a little less visually intense.
Re:Mathematics for Computer Science (2018) [pdf]
on Friday January 09, 2026 @06:38AM (#46552796)
I like this book. The probability section is great, especially how they handle the Monty Hall paradox. They use "four step method" that breaks it down perfectly - way clearer than the explanations you get in movies like 21 or numb3rs.
Re:Lights and Shadows
on Thursday January 08, 2026 @11:15AM (#46542742)
I skimmed the source code (base.js, light.js) to see what he was using.
It appears to be entirely custom, with no graphics libraries like Three.js.
He even implements his own low-level math functions from scratch.
It's impressive to see that kind of discipline.
Re:Show HN: Jax-JS, array library in JavaScript targeting WebGPU
on Wednesday January 07, 2026 @07:41PM (#46535452)
The examples are great. It would be really nice to have a sandbox with the full training code (e.g. MNIST) to play with.
Show HN: Big O Notation – An Interactive Guide
https://sbondaryev.dev/articles/big-o-notation
Hi HN,I built this interactive guide to help build intuition for time complexity.There is already a lot of writing on this topic here (e.g. [1], [2]), so I tried to keep the explanation minimal and focus on examples you can interact with.The visualizer runs your JavaScript code, tracks `op()` markers as `n` increases, and plots the growth curve in real-time.I also tried to visualize the Master...
Re:Show HN: A spectrogram in the style of Unknown Pleasures album art ...
on Monday January 05, 2026 @09:54AM (#46499437)
Really nice work - love the aesthetic. It'd be great to have this as a JS library with support for arbitrary audio inputs.
Re:Show HN: Tasker – An open-source desktop agent for browser and OS a...
on Friday January 02, 2026 @06:34AM (#46463777)
Nice idea - unfortunately I didn't manage to get it running on my MacBook Pro (Late 2013).
I'm on Big Sur 11.7.10, which I know is pretty old at this point. The app launches, but it only shows an empty window.
I was also a bit concerned about privacy while running it :)
Re:Show HN: Turning 100-plus comments HN threads into readable discuss...
on Thursday January 01, 2026 @10:10PM (#46460991)
Nice project — it makes long HN threads much easier to revisit.
Interesting to see the edge cases, like "Tell HN: Happy New Year": https://hn-discussions.top/happy-new-year-2025/
Basically everyone just saying "Happy New Year" so it's fun to see how the LLM tries to interpret that. For example, my comment was summarized as: "gratitude – celebratory – looking forward: celebratory greeting for the new year"