Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I wanted to better understand how Claude Code is wired under the hood, so I captured its API requests and pulled out the system prompt and tool definitions. Also posting the full thing as a gist below if you want to dig in!

85,545 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von Sergey Karayev
Sergey Karayevvor 1 Jahr

Have fun. Lots to learn in there

Profilbild von Yogesh Kumar
Yogesh Kumarvor 1 Jahr

Great stuff 🔥 really helpful! P.S. Those subtitles are 🤌 How are you generating them?

Profilbild von thud
thudvor 1 Jahr

What's with the tell a joke line?

Profilbild von Sergey Karayev
Sergey Karayevvor 1 Jahr

And if you want to launch dozens of Claude Codes in parallel, check out

Profilbild von angel imaz (AI)
angel imaz (AI)vor 1 Jahr

thank you. model is even more impressive if that is what Claude Code is using.

Profilbild von moonbi
moonbivor 1 Jahr

@thdxr

Profilbild von arti
artivor 1 Jahr

You could just reverse the binary from the release that shipped with the source map like all of the open code type GitHub repos did

Profilbild von Gabriel Paiz
Gabriel Paizvor 1 Jahr

Is there a youtube link?

Profilbild von Jeffrey Behnke 💻
Jeffrey Behnke 💻vor 1 Jahr

Thanks for that. Interesting read

Profilbild von Ahmed
Ahmedvor 1 Jahr

This is great.

Ähnliche Videos

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,825 Aufrufe • vor 2 Monaten