Top all-time · #3800
Han Lee
Personal blog · leehanchung.github.io/blogsaiprogramming
Han Lee writes Han, Not Solo, a personal blog at leehanchung.github.io about ai and programming. Since 2022, 19 different Hacker News readers have linked it 24 times, most often “Claude Agent Skills: A First Principles Deep Dive (2025)”. It is still writing: the last post was on 2026-09-20, and you can follow it by feed.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
Han Lee's posts cover recommendation systems, including a breakdown of TikTok's algorithm, and LLM and AI topics such as deep research and agents. Commenters cite them as sources and for AI commentary.
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.
Han Lee writes about machine learning engineering, AI evaluation, agent systems, search, recommendation systems, and the technology industry.
Most-linked posts?
- Claude Agent Skills: A First Principles Deep Dive (2025)5 people · 5 mentions · first linked 2025-10-29
- Poking Around Claude Code3 people · 3 mentions · first linked 2025-03-09
- The AI Great Leap Forward2 people · 2 mentions · first linked 2026-04-08
What Hacker News says?
Most guides to wringing productivity out of these higher level Claude code abstractions suffer from conceptual and wall-of-text overload. Maybe it's unavoidable but it's tough to really dig into these things. One of the things that bugs me about AI-first software development is it seems to have swung the pendulum of "software engineering is riddled with terrible documentation" to "software engineering is riddled wit…
Comment linking /blogs/2025/10/26/claude-skills-deep-dive/
on “Claude Advanced Tool Use”Submitted The Differences Between Deep Research, Deep Research, and Deep Research as a story · 231 points
HN discussionNot a direct answer to your question, but at least in English there isn’t that much stuff on how TikTok’s recommendation system works internally. This is the best breakdown I have found on TikTok’s recommendation system internals: https://leehanchung.github.io/2020-02-18-Tik-Tok-Algorithm/ There’s a more technical recent paper from bytedance as well: https://arxiv.org/pdf/2007.07203.pdf And another recent one on byt…
Comment linking /2020-02-18-Tik-Tok-Algorithm/
on “Real World Recommendation System”Submitted AI Winter Is Coming as a story · 67 points
HN discussionAre you telling me that AI's are starting to diverge and that we might get a combinatorial explosion of reasoning paths that will produce so many different agents that we won't know which one can actually become AGI? https://leehanchung.github.io/assets/img/2025-02-26/05-quadr...
Comment linking /assets/img/2025-02-26/05-quadrants.png
on “The Differences Between Deep Research, Deep Research, and Deep Research”Submitted The AI Great Leap Forward as a story · 25 points
HN discussionFrom the clear path of attention is all you need, to the divergent fog of deep research, AI winter is coming. https://leehanchung.github.io/assets/img/2025-02-26/05-quadr...
Comment linking /assets/img/2025-02-26/05-quadrants.png
on “The Government Knows AGI Is Coming”Submitted Jev and the Return of AI/ML Engineering as a story · 4 points
HN discussionWhile TFA is not bad, some of the links contained in it are even more interesting, for example: https://leehanchung.github.io/blogs/2026/04/05/the-ai-great-... https://github.com/0xdeadbeefnetwork/ssh-keysign-pwn https://lwn.net/Articles/1072007/#Comments
Comment linking /blogs/2026/04/05/the-ai-great-leap-forward/
on “The Four Horsemen of the LLM Apocalypse”Submitted A Taxonomy of RL Environments for LLM Agents as a story · 3 points
HN discussionSubmitted Claude Agent Skills: A First Principles Deep Dive (2025) as a story · 3 points
HN discussionSubmitted MCP is not REST API as a story · 3 points
HN discussionSubmitted Claude Skills as a Meta Tool as a story · 2 points
HN discussionSubmitted Claude Agent Skills: A First Principles Deep Dive as a story · 2 points
HN discussionSubmitted Claude Agent Skills: A First Principles Deep Dive as a story · 2 points
HN discussionSubmitted Poking Around Claude Code as a story · 2 points
HN discussionSubmitted Poking Around Claude Code as a story · 2 points
HN discussionSubmitted Tik-Tok Wins the Social Media Recommendation System War (2020) as a story · 2 points
HN discussionSubmitted What the Hype and Reality of Agents as a story · 2 points
HN discussionSubmitted Updating Your Priors in the Age of Scaling Compute as a story · 2 points
HN discussionSubmitted Don't Outsource Your Understanding as a story · 1 points
HN discussionSubmitted Technical Debt of AI Systems: Agent Runtime as a story · 1 points
HN discussionSubmitted Poking Around Claude Code as a story · 1 points
HN discussionSubmitted Reasoning Series, Part 1: Understanding GPT-O1 as a story · 1 points
HN discussion
