Jonathan Chang's Blog
Jonathan Chang's Blog is hip-agent (harness in prompt) is a small agent harness designed for agents: the model reads its own harness, configuration is environment variables, and the rest is existing protocols.. It is ranked #1185 on the AI Radar, in AI agents, first seen 12 days ago and shared in 3 posts (1.6k views).
hip-agent: a harness that fits in the prompt – Jonathan Chang’s Blog hip-agent: a harness that fits in the prompt hip-agent (harness in prompt) is a small agent harness designed for agents: the model reads its own harness, configuration is environment variables, and the rest is existing protocols. Agents LLM Author Jonathan Chang Published September 6, 2026 Note : this post was written with Claude Fable 5.1 and GPT 5.6 sol. Code: github.com/changjonathanc/hip-agent . Motivation There are many coding harnesses (Claude Code, Codex, and many more), but they are all designed to be used by a human. They are not designed to be used by an agent.…
What people said about Jonathan Chang's Blog on X
Announcing hip-agent ("harness in prompt"). The basic idea is that the harness is so small that it can fit in the prompt, which allows the model to know exactly how the harness works. https://jonathanc.net/blog/hip-agent?v=2
— @ChangJonathanC, 12 days ago · 25 likes · see the post
I had this idea some time ago. Are LLMs color blind? Do they have any color-weakness? turns out most LLMs fail to read numbers on a plate, in a typical color blindness test for human. https://jonathanc.net/color-vision/
— @ChangJonathanC, 9 days ago · 3 likes · see the post
If your model is so smart, why does it need a harness with so many rules telling it what to do? A hip-agent should be all you need
— @ChangJonathanC, 12 days ago · 1 likes · see the post
Alternatives to Jonathan Chang's Blog
- muse.ai — New connectors are live today. Come build with us.
- academy.dair.ai — Chat with Paper
- alphaXiv — τ-BENCH is introduced as a benchmark evaluating AI systems on their ability to construct deployable, customer-facing…
- Sakana Fugu — One model to command them all
- typesafe.ai — yes - we're hiring!
- context.dev — powers the branding, company context, and search.
Jonathan Chang's Blog in numbers
- Rank on the AI Radar: #1185 of 1190
- Shared in 3 posts by 1 account: @ChangJonathanC
- 1.6k views on those posts
- First seen 12 days ago, last shared 9 days ago
- Pricing seen by Jev: not stated
- Market: AI agents
FAQ
What is Jonathan Chang's Blog?
hip-agent (harness in prompt) is a small agent harness designed for agents: the model reads its own harness, configuration is environment variables, and the rest is existing protocols. It was first shared on X 12 days ago and is ranked #1185 on the AI Radar.
Is Jonathan Chang's Blog free?
Pricing is not stated on the page we read.
Who shared Jonathan Chang's Blog?
1 account on X, including @ChangJonathanC, in 3 posts totalling 1.6k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.