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 · #12580

J

June Kim

Personal blog · june.kim · on HN as kimjune01aiprogrammingwriting

June Kim's personal blog at june.kim covers ai, programming and writing. Since 2023, 6 different Hacker News readers have linked it 40 times, most often “Show HN: I submitted 316 AI-generated PRs to open source”. It is still writing: the last post was on 2026-10-20, and you can follow it by feed.

Visit the blog
40mentions?
6HN people?
2023–2026first – last linked?
Links on Hacker News per year · peak 21 in 2026

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

Commenters link June Kim's posts for a resume and for an account of open-source contributions to tinygrad, where pull requests were closed and a maintainer's rejections were narrated publicly. Comments do not judge the writing.

Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

June Kim writes about software agents, cognition, epistemology, methodology, and verifiable work through essays, projects, and open research.

The author on HN?

kimjune01 · 136 karma · member since 2015

In Vancouver, Canada. www.june.kim

From their public HN profile, which links to this site.

Most-linked posts?

  1. Show HN: I submitted 316 AI-generated PRs to open source
    2 people · 3 mentions · first linked 2026-05-12
  2. Cord: Coordinating Trees of AI Agents
    2 people · 2 mentions · first linked 2026-02-19

What Hacker News says?

  1. I've been working on a similar project, also open source: https://www.june.kim/jamdojo/

    Comment linking /jamdojo/

    on “Learning music with Strudel”
  2. Submitted Cord: Coordinating Trees of AI Agents as a story · 8 points

    HN discussion
  3. Just letting you know, your resume link doesn't load for me on Firefox. I think you wanted this one: https://www.june.kim/assets/resume.pdf

    Comment linking /assets/resume.pdf

    on “Ask HN: Who wants to be hired? (May 2024)”
  4. Submitted Would You Hire a Calculator? as a story · 8 points

    HN discussion
  5. Location: Vancouver, B.C. (Authorized for both Canada and USA) Remote: Preferred, open to hybrid and onsite Willing to relocate: Yes, preferably Seattle or Bay area Technologies: iOS/Swift, Javascript/TypeScript, React, React Native, HTML, CSS, Python, C++ Résumé/CV: https://june.kim/resume Email: june \at\ june.kim

    Comment linking /resume

    on “Ask HN: Who wants to be hired? (May 2024)”
  6. Submitted Quality Standards as a story · 6 points

    HN discussion
  7. working on building a bench for human ICs for hiring https://june.kim/human-signal

    Comment linking /human-signal

    on “Ask HN: What are you working on? (August 2026)”
  8. Submitted Show HN: I submitted 316 AI-generated PRs to open source as a story · 3 points

    HN discussion
  9. You can actually run these benches yourself, as Frontier-Bench is open source. Also have a look at these other coding benchmarks I audited. Frontier-Bench v0.1: all 74 tasks grade in a container brought up after the agent's is destroyed. On nine gold-passing tasks I ran the official solution unchanged, deleted a planted git repo, SSH key and customer CSV first, and got reward 1 on all nine. https://june.kim/auditing…

    Comment linking /auditing-mirrorcode

    on “Claude Opus 5”
  10. Submitted Software Is Made of People as a story · 3 points

    HN discussion
  11. This you? https://june.kim/speedrunning-open-source > tinygrad I picked on purpose. geohot narrates rejections in public, and a narrated rejection is data; a silent close is noise. Thirteen PRs, one merged, twelve closed. His comments tell the escalation story: >> be careful with AI usage, we never trade complexity for speed >> You need to stop with AI PRs, you will be banned. >> Last warning about low quality PRs b…

    Comment linking /speedrunning-open-source

    on “Software Developers Say AI Is Rotting Their Brains”
  12. Submitted A protocol for knowledge between agents who do not trust each other as a story · 2 points

    HN discussion
  13. for small to medium sized bugs I managed to get a bit more than half of my PRs to get merged. ~90 PRs since May https://june.kim/speedrunning-open-source Verify yourself: { merged: search(query: "is:pr is:merged author:kimjune01 created:>2026-05-09T00:34:00Z", type: ISSUE) { issueCount } closed: search(query: "is:pr is:closed is:unmerged author:kimjune01 created:>2026-05-09T00:34:00Z", type: ISSUE) { issueCount } al…

    Comment linking /speedrunning-open-source

    on “Nothing works and everyone is euphoric”
  14. Submitted The Journey of Internet Ads – A Scrollytelling as a story · 2 points

    HN discussion
  15. https://www.june.kim/

    Comment linking /

    on “Ask HN: Could you share your personal website here?”
  16. Submitted Elicitation as a story · 2 points

    HN discussion
  17. It is my pleasure to write for you. https://www.june.kim/cord-human

    Comment linking /cord-human

    on “Cord: Coordinating Trees of AI Agents”
  18. Submitted Auditing DeepSWE as a story · 1 points

    HN discussion
  19. an audit for the bench for the curious: https://www.june.kim/terminal-bench-frame

    Comment linking /terminal-bench-frame

    on “DeepSeek V4 Flash 0731: 82.7% on Terminal-Bench 2.1 with a public harness”
  20. Submitted Continuous context compaction using Union-find as a story · 1 points

    HN discussion
  21. In a chatbot-first world, it's gonna have to either be generic impression ads that race to the bottom or contextual recommendations. Of course, the fear is that the advertiser hoards personal data or the chat answers are skewed to make you spend more money. Those concerns can be resolved by decoupling the text generation from the recommendation engine. It works by casting your intent and match it up with an advertis…

    Comment linking /vector-space

    on “Advertise in ChatGPT”
  22. Submitted Show HN: Union-find for chatbot memory instead of flat compaction as a story · 1 points

    HN discussion
  23. internet ads are largely a story of parasitic exchanges using information asymmetry to suck as much surplus out of the middle as possible. https://june.kim/advertising-journey/

    Comment linking /advertising-journey/

    on “Does Internet Advertising Work?”
  24. Submitted Show HN: How ads should work on chatbots, and why no one has built it yet as a story · 1 points

    HN discussion
  25. https://www.june.kim I like to write about self improvement and other things I'm thinking about

    Comment linking /

    on “Ask HN: Could you share your personal blog here?”
  26. Submitted Show HN: Cord – Agents that build their own coordination trees as a story · 1 points

    HN discussion
  27. Location: Vancouver, Canada Remote: Yes Willing to relocate: Yes for research Technologies: Python, TypeScript, Go, Rust, C++; LLM and coding agents, evaluation harnesses and graders, benchmark design and auditing, tool use/MCP, RAG and retrieval, agent observability Résumé/CV: https://june.kim/about Email: june@june.kim Research/evaluation engineer with 10+ years in software engineering, including Google/YouTube, L…

    Comment linking /research

    on “Ask HN: Who wants to be hired? (August 2026)”
  28. Submitted Geometrically Allocated Ads in AI Conversations as a story · 1 points

    HN discussion
  29. hi Thariq, I dont know how else to reach someone at claude code, so here goes: I solved context compaction by using a better caching algorithm. It's being implemented in gemini-cli with limited success. https://june.kim/union-find-compaction https://github.com/google-gemini/gemini-cli/pull/24736

    Comment linking /union-find-compaction

    on “Tell HN: Claude 4.7 is ignoring stop hooks”
  30. Submitted Learn Pinyin with Games as a story · 1 points

    HN discussion

Search all of HN for june.kim