this post was submitted on 15 Jul 2026
380 points (99.0% liked)
Fuck AI
7769 readers
810 users here now
"We did it, Patrick! We made a technological breakthrough!"
A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.
AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Yes and no. There are no guardrails on its output, so it will happily emit
sudo rm -rf /*. But the "harness" of the agents gets to check if this gets executed. The default is usually "ask every time", but you can change that to "everything is allowed" or "every invocation oflsandgrepis allowed". Problem is, when users get tired to constantly proof read and check every single command (and it will constantly emit commands) and then just hit "allow everything for this session" or such. Or when a user definesls .* \| grep .*is a regex that defines that this is always OK to run but don't see that it also matches any command after the grep that could do whatever with that data.Basically: the only safe way is to manually check every single command and you will be annoyed quickly and let you guard down.
Claude’s harness parses pipes and asks for permission for each individual command.
Of course you're right about the issues, e.g. when it creates a script file to execute and you allow that for the session, it can edit it and then re-execute it without your further input.
But the harness doesn't actually prevent Claude Code from running commands. It just tells the model to end with a question instead of running the command directly. I haven't actually read the source code though, just an anecdote from it running commands even when "ask every time" is enabled.
Huh? I have access to Claude Code at work (and I'm not forced to use it for everything but rather as I see fit, yay!). It constantly asks me. BUT we get a custom config rolled out with it that is already pre populated with several commands and permissions for allow, deny and ask. Maybe it is a bit more lenient in the default mode?
On the other hand, in the last thread of someone loosing their production server/database to Claude it was revealed that their cloud provider had some unintuitive settings that also immediately deleted all corresponding backups if you delete the resource - so I can see how this could have happened even when issuing commands manually.