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

191–200 of 636 posts

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

#191

Post by dboreham »

otterley wrote: post #41
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…

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"

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

#192

Post by _heimdall »

targafarian wrote: post #190
manbitesdog wrote: post #161

Earlier quoted context omitted.

I cringe every time I see Claude trying to co-author a commit. The git history is expected to track accountability and ownership, not your Bill of Tools. Should I also co-author my PRs with my linter, intellisense and IDE?

Well is it actually being used as a tool where the author has full knowledge and mental grasp of what is being checked in, or has the person invoked the AI and ceded thought and judgment to the AI? I.e., I think in many cases the AI really is the author, or at least co-author. I want to know that for attribution and understanding what went into the commit. (I agree with you if it's just a tool.)

I have worked with quite a few people committing code they didn't fully understand.

I don't meant this as a drive by bazinga either, the practice of copying code or thinking you understand it when you don't is nothing new

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

#195

Post by girvo »

Reason077 wrote: post #50

> "Anti-distillation: injecting fake tools to poison copycats" Plot twist: Chinese competitors end up developing real, useful versions of Claude's fake tools.

I cannot bring myself to care about distillation, when these companies have built their empires on top of everyone else's stolen data, while at the same time telling the world they're out to replace us all.

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

#196

Post by _heimdall »

Sharlin wrote: post #188
manbitesdog wrote: post #161

Earlier quoted context omitted.

I cringe every time I see Claude trying to co-author a commit. The git history is expected to track accountability and ownership, not your Bill of Tools. Should I also co-author my PRs with my linter, intellisense and IDE?

You have copyright to a commit authored by you. You (almost certainly) don't have copyright (nobody has) to a commit authored by Claude.

Anthropic could at least make a compelling case for the copyright.

It becomes legally challenging with regards to ownership if I ever use work equipment for a personal project. If it later takes off they could very well try to claim ownership in its entirety simply because I ran a test once (yes, there's a while silicon valley season for it).

I don't know if they'd win, but Anthropic absolutely would be able to claim the creation of that code was done on their hardware. Obviously we aren't employees of theirs, though we are customers that very likely never read what we agreed to in a signup flow.

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

#197

Post by LeoPanthera »

manbitesdog wrote: post #161
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…

I cringe every time I see Claude trying to co-author a commit. The git history is expected to track accountability and ownership, not your Bill of Tools. Should I also co-author my PRs with my linter, intellisense and IDE?

> Should I also co-author my PRs with my linter, intellisense and IDE?

Absolutely. That would be hilarious.

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

#198

Post by allajfjwbwkwja »

_heimdall wrote: post #192
targafarian wrote: post #190

Earlier quoted context omitted.

Well is it actually being used as a tool where the author has full knowledge and mental grasp of what is being checked in, or has the person invoked the AI and ceded thought and judgment to the AI? I.e., I think in many cases the AI really is the author, or at least co-author. I want to know that for attribution and understanding what went into the commit. (I agree with you if it's just a tool.)

I have worked with quite a few people committing code they didn't fully understand. I don't meant this as a drive by bazinga either, the practice of copying code or thinking you understand it when you don't is nothing new

Pre-LLM, it was much easier for reviewers to discern that. Now, the AI-generated code can look like it was well thought out by somebody competent, when it wasn't.

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

#200

Post by stephbook »

Sounds like there's still a lot of value in Typescript (otherwise they could have open sourced.)

Plus there's demand for skilled TS software devs that don't ship your company's roadmap using a js.map

20,000 agents and none of them caught it...

Post reply on HN