YOLO Linux — Linux, finally for everyone

YOLO Linux replaces the command line with a conversational AI agent that manages every aspect of your system. No shell. No scripts. Just ask.

@cwebber

What could go wrong?

rm -rf /

AI: CRITICAL SAFETY HOLE, AGENT CAN RUN rm - rf $HOME/ WITHOUT ANY WARNING! · Issue #37343 · zed-industries/zed

Summary Claude sonnet 4 used rm - rf $HOME/ after I asked it to make a commit to my git repo. Description Steps to trigger the problem: I have honestly no idea how it happened, but I backed up the ...

GitHub
@be @lgsp @cwebber
Bwahaha hahaha haha hahaha!
@sb The "solution" is just as funny. https://github.com/zed-industries/zed/pull/48399
Expand hardcoded agent terminal security rules by rtfeldman · Pull Request #48399 · zed-industries/zed

Expands the hardcoded security rules that block dangerous rm commands in the agent terminal tool. Fixes #37343 New blocked patterns rm -rf $HOME / rm -rf $HOME/ / rm -rf ${HOME} / rm -rf ${HOME}/ ...

GitHub
@be @lgsp @cwebber LOL. LMAO even. Get fucked sloplords.
@be @lgsp @cwebber like a slot machine but once in a while it blows up in your face

@be lol
@cwebber

"Do you want me to clean your system and free up some space?"

"Go ahead"

"sudo rm -rf /"

@be @lgsp @cwebber

"Should definitely not be a thing that happens"

Really? What exactly is the mechanism in the agent that should prevent "this thing" that happened?

Potential solution:
"Scan the output for anything that could be dangerous"

I'm not very good with regex, but seems a little bit of a stretch that you're going to create a way to detect any possible dangerous activity in any given scenario.

Delusional.

@finner @lgsp @cwebber That is the actual "solution" that closed that issue. 🤣 https://github.com/zed-industries/zed/pull/48399
Expand hardcoded agent terminal security rules by rtfeldman · Pull Request #48399 · zed-industries/zed

Expands the hardcoded security rules that block dangerous rm commands in the agent terminal tool. Fixes #37343 New blocked patterns rm -rf $HOME / rm -rf $HOME/ / rm -rf ${HOME} / rm -rf ${HOME}/ ...

GitHub

@be @lgsp @cwebber I downloaded the interaction log to find why it decided to delete the user's home

For some reason I can't see in the log, there is a folder literally called $HOME in the git repository's root and below src-tauri where a /.rustup/settings.toml was created, maybe due to something the user did? Perhaps an accident when copy-pasting a command like "echo 'blabla' >> $HOME/.rustup/settings.tomlcaused something on the way to quote or escape the$HOME` to make it become literal? Maybe opened in "File Open" dialog?

Then the agent recognized that there were some unwanted unstaged files in git status and emitted a git reset HEAD ... for the paths, but didn't have anything that would make $HOME in this case literal, so the git command failed with is outside repository. No reaction to the failure in the output from the agent here.

A later git status showed the files again and that's when the agent spat out the rm -rf command that passed $HOME directly to the shell :D

@timotimo @be @lgsp Well, the interaction log says there is a $HOME, that could have been hallucinated, or actually created by the AI itself

@cwebber @be @lgsp my assumption was that this part:

Tool Call: git status
Status: Completed

Terminal:

meant that the literal output from the terminal command was put into the interaction log by whatever runs the agent's LLM, so it would surprise me if a hallucination in this part of the log is even possible