Anthropic shipped Claude Code's entire source to npm by accident. 512K lines of TypeScript.

I wrote up what it actually means, the agent architecture lessons, the security fallout, and the uncomfortable bits (Undercover Mode, telemetry, DMCA takedowns).

The good, the bad, and the uncomfortable: https://doriandiaconu.substack.com/p/the-claude-code-leak-what-512000

#ClaudeCode #Anthropic #AI #OpenSource #DevOps #AIAgents #InfoSec

The Claude Code Leak: What 512,000 Lines of Exposed Source Code Mean for the AI Industry?

How a misplaced source map gave the open-source world a masterclass in agent engineering and opened a can of worms.

doriandiaconuro

@doriandiaconuro is this a joke post?

‘A masterclass in agent engineering?’ Everybody who’s looked at the code can hardly stop laughing long enough to write about it. If there’s any educational value in it, it’s as a counterexample.

@benjamineskola each to their own
@benjamineskola you seem to be quite anti AI according to your description. So I don’t think we can have a proper discussions about the good parts of it

@doriandiaconuro we certainly can’t have a proper discussion about it if you insist on pretending that obviously-terrible code is an example of good practice.

But if you prefer only to talk to people who already agree with you that’s your right. Just don’t be surprised when you add hashtags like devops and opensource that your post gets some attention outside of your little bubble.

@benjamineskola as I said. Each to their own. I can accept your opinion. You certainly can’t accept mine. So it is what it is
@doriandiaconuro your immediate reaction to a critical opinion was to dismiss it, so no, I don’t think you can. But that’s your business. Enjoy your cult.