Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

alex000kim.com

Post reply on HN
Print view View original

481–490 of 636 posts

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#481

Post by catlifeonmars »

skydhash wrote: post #289
ImPostingOnHN wrote: post #168

Earlier quoted context omitted.

I think my post makes it pretty clear that I would. If you want, I could cite several examples of organizations which use the method I described, so you can weigh it against the one example you provided, and get the full picture. In your example, for example, where was the issue tracked before the code was written? The format you linked makes it difficult to get the history of the issue. Let me ask you this: suppose…

Everyone has its own system although companies do tend to codify it with a project manager. I used TODO.txt inside the repo. an org file, Things.app, a stack of papers, and a whiteboard. But once a task is done, I can summarize the context in a paragraph or two. That’s what I put in the commits.

I do this too. I’ll have a design.md and roadmap.md checked into the repository.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#482

Post by catlifeonmars »

jakeinspace wrote: post #120
LeifCarrotson wrote: post #116

Earlier quoted context omitted.

The human developer would just write what the code does, because the commit also contains an email address that identifies who wrote the commit. There's no reason to write: > Commit f9205ab3 by dkenyser on 2026-3-31 at 16:05: > Fixed the foobar bug by adding a baz flag - dkenyser Because it already identified you in the commit description. The reason to add a signature to the message is that someone (or something) th…

Aside from merges that combine commits from many authors onto a production branch or release tag. I would personally not leave an agent to do that sort of work.

I usually avoid merge commits in favor of rebases precisely for the reason you describe above.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#483

Post by catlifeonmars »

HeytalePazguato wrote: post #338

The hooks system is the most underappreciated thing in what leaked. PreToolUse, PostToolUse, session lifecycle, all firing via curl to a local server. Clean enough to build real tooling on top of without fighting it. The frustration regex is funny but honestly the right call. Running an LLM call just to detect "wtf" would be ridiculous. KAIROS is what actually caught my attention. An always-on background agent that a…

> Running an LLM call just to detect "wtf" would be ridiculous.

Tangentially, I wonder if the world trade federation or the Washington tennis foundation have any projects on GitHub :)

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#485

Post by RA2lover »

mzajc wrote: post #37

There are now several comments that (incorrectly?) interpret the undercover mode as only hiding internal information. Excerpts from the actual prompt[0]: NEVER include in commit messages or PR descriptions: - The phrase "Claude Code" or any mention that you are an AI - Co-Authored-By lines or any other attribution BAD (never write these): - 1-shotted by claude-opus-4-6 - Generated with Claude Code - Co-Authored-By: C…

There's a more worrying part: It refers to unreleased versions of Claude in more detail than released versions.

For a company calling chinese companies out for distillation attacks on their models, this very much looks like a distillation attack against human maintainers, especially when combined with the frustration detector.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#486

Post by snovv_crash »

Alex_L_Wood wrote: post #471
poopmonster wrote: post #331

Earlier quoted context omitted.

skill issue

Commenting every method, how pedestrian! I comment every letter of my code!

Single letter variables all the way. Then it's easy to tell what code is human welritten. /s

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#487

Post by graemep »

galaxyLogic wrote: post #420
graemep wrote: post #235

Earlier quoted context omitted.

It may be obvious to you, but it has lead to at least one protracted court case in the US: Thaler v. Perlmutter. > The question is whether anyone has or if whatever content generated by a LLM simply does not constitute a work and is thus outside the entire copyright law. Its is going to vary with copyright law. In the UK the question of computer generated works is addressed by copyright law and the answer is "the aut…

The binary should be considered "derived work". Only the original copyright owner has the exclusive right to create or authorize derivative works. Means you are not allowed to compile code unless you have the license to do so. Right?

Yes, so is LLM generated code a derivative work of the prompts? Does it matter how detailed the prompts are? How much the code conforms to what is already written (e.g. writing tests)?

It looks like it will be decided on a case by case basis.

It will also differ between countries, so if you are distributing software internationally what will be a constraint on treating the code as not copyrightable.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#488

Post by lawrjone »

dboreham wrote: post #191
otterley wrote: post #41

Earlier quoted context omitted.

I would have expected people (maybe a small minority, but that includes myself) to have already instructed Claude to do this. It’s a trivial instruction to add to your CLAUDE.md file.

I always assumed that if I tried to tell it, that it'd say "I'm sorry, Dave. I'm afraid I can't do that"

We use CC to power some of our code features and override this setting so we can provide our own attribution. So there are several legit reasons to permit this.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#490

Post by duskdozer »

danbolt wrote: post #381
poopmonster wrote: post #331

Earlier quoted context omitted.

skill issue

Please elaborate, poopmonster! What sort of skills are required to expertly use an LLM?

    // [umbrella] Describe skill 1. (Prompt engineering)
    1. Skillful use of **prompt engineering**
    // [rocketship] Describe skill 2. (Agentic loops)
    2. Know how to use **agentic loops** skillfully
    ....
Post reply on HN