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 · #18651

I

Itay Inbar

Personal blog · itayinbarr.substack.comaiprogramming

Itay Inbar's personal blog at itayinbarr.substack.com covers ai and programming. Since 2026, 4 different Hacker News readers have linked it 4 times, most often “Honey, I Shrunk the Coding Agent”. It is still writing: the last post was on 2026-06-28, and you can follow it by feed.

Visit the blog
4mentions?
4HN people?
2026–2026first – last linked?

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

Why HN links it

Linked in HN threads on small local language models and coding harness design. Commenters point to it for adapting prompting and tooling to smaller models that need more explicit instructions.

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.

Data Scientist @ BRAIN.Q | Computational Neuroscience @ BGU. Click to read Itay Inbar on Substack. Launched 6 months ago.

Most-linked posts?

  1. Honey, I Shrunk the Coding Agent
    3 people · 3 mentions · first linked 2026-04-22

What Hacker News says?

  1. There’s some weak evidence against this actually. Harness design makes a huge difference for tiny local models for example: https://itayinbarr.substack.com/p/honey-i-shrunk-the-coding-... I have only my own personal experience for frontier models, but I have seen different performance of Opus when used from Pi or Claude Code or Zed for example.

    Comment linking /p/honey-i-shrunk-the-coding-agent?triedRedirect=true

    on “Claude AI recovers an 11 yrs old BTC wallet holding 400k USD”
  2. Submitted Honey, I Shrunk the Coding Agent as a story · 5 points

    HN discussion
  3. simjnd · 2026-05-07Recommends
    This link [1] features some good insight on how to adapt your usage to smaller models which require more explicit or deliberate prompting. I have been using Gemma 4 31B a lot and have found it very competent. It can be a bit unstable and start spiraling or end up in infinite loops that you need to reset, but for the most part it's been really good. [1]: https://itayinbarr.substack.com/p/honey-i-shrunk-the-coding-...

    Comment linking /p/honey-i-shrunk-the-coding-agent

    on “ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math”
  4. Submitted Honey, I Shrunk the Coding Agent as a story · 2 points

    HN discussion

Search all of HN for itayinbarr.substack.com