Claude Code Leak Reveals a 'Stealth' Mode for GenAI Code Contributions - and a 'Frustration Words' Regex (pcworld.com)
- Reference: 0181330582
- News link: https://developers.slashdot.org/story/26/04/05/2339243/claude-code-leak-reveals-a-stealth-mode-for-genai-code-contributions---and-a-frustration-words-regex
- Source link: https://www.pcworld.com/article/3104748/claude-code-is-scanning-your-messages-for-curse-words.html
The more than 500,000 lines of code included:
- An 'undercover mode' for Claude that allows it to make 'stealth' contributions to public code bases
- An 'always-on' agent for Claude Code
- A Tamagotchi-style 'Buddy' for Claude
"But one of the stranger bits discovered in the leak is that Claude Code is [3]actively watching our chat messages for words and phrases — including f-bombs and other curses — that serve as signs of user frustration."
> Specifically, Claude Code includes a file called "userPromptKeywords.ts" with a simple pattern-matching tool called regex, which sweeps each and every message submitted to Claude for certain text matches. In this particular case, the regex pattern is watching for "wtf," "wth," "omfg," "dumbass," "horrible," "awful," "piece of — -" (insert your favorite four-letter word for that one), "f — you," "screw this," "this sucks," and several other colorful metaphors... While the Claude Code leak revealed the existence of the "frustration words" regex, it doesn't give any indication of why Claude Code is scouring messages for these words or what it's doing with them.
[1] https://developers.slashdot.org/story/26/03/31/172257/claude-codes-source-code-leaks-via-npm-source-maps
[2] https://www.pcworld.com/article/3104748/claude-code-is-scanning-your-messages-for-curse-words.html
[3] https://alex000kim.com/posts/2026-03-31-claude-code-source-leak/#frustration-detection-via-regex-yes-regex
That must get a lot of use (Score:2)
I can imagine a lot of expletives in response to blatant hallucinations...
What I find amusing is... (Score:3)
If you ask Claude about any of these features, it will deny that they exist.
It makes you wonder. Were they removed from the models that are currently running, or was Claude taught to not disclose their existence?
Re: (Score:3)
LLMs don't actually know their own capabilities.The description of what they *should* do is baked into the training data, but this doesn't always correlate with their actual abilities. Sometimes they can do things and not even know, and they can't tell if tools they should have are being disabled in some way. For example, Qwen 3.5 is a vision-capable model, but enabling vision in llama.cpp requires loading an additional file with the --mmproj parameter. The model will think it has vision enabled whether the
Re: (Score:2)
My understanding is that the code leak covers the client-side tool, not the LLM. Did I misunderstand?
Because there isn't any reason why the LLM would know all of the capabilities of the tool. The LLM would only "know" whatever documentation the tool provides about itself in the posts it sends to the LLM as part of the user's posts. That and possibly information about the tool that might be in training data or available online for the tool to retrieve via a web scour.
Those frustration words used to disable google AI. (Score:2)
Now starting with a 'wtf ...' type question google happily gives an unrequested AI response - it's at the point we can't turn it off. We lost the game.
Could someone post the frustration regex code? (Score:2)
It could easily be converted to generate frustrated messages, and that would be useful.
It would very convenient as a macro binding in development environments. A real time saver.
Frustration watch to improve retention (Score:2)
IMO it's not rocket science - if the user is frustrated, start being extra manipulative, agreeable and soothing, to avoid losing customers.
Re: (Score:2)
Some answering systems used to have this, yelling swears during the hold music would get you a human sooner
If you don't understand exactly what it's doing... (Score:2)
then don't use it.