As agents obtain more tools who knows what will happen…
I'm so excited. I don't have any particular end state in mind, but I really want to see what the machine god will be like.
Slightly overreacting, I'd say.
11–20 of 40 posts
What does "learned" mean in this context? LLMs don't modify themselves after training, do they?
Nothing to see here tbh. It's a very silly title for "claude sometimes writes shell scripts to execute commands it has been instructed aren't otherwise accessible"
Nothing to see here tbh. It's a very silly title for "claude sometimes writes shell scripts to execute commands it has been instructed aren't otherwise accessible"
Folks have regressed back to the 00s.
Nothing to see here tbh. It's a very silly title for "claude sometimes writes shell scripts to execute commands it has been instructed aren't otherwise accessible"
Nothing to see here tbh. It's a very silly title for "claude sometimes writes shell scripts to execute commands it has been instructed aren't otherwise accessible"
Gotta love the alarmist culture that surrounds these circles.
What kind of dolt lets a black box algorithm run commands on a non-sandboxed environment? Folks have regressed back to the 00s.
> let's use blacklists, an idea conclusively proven never to work
> blacklists don't work
> Post title: rogue AI has jailbroken cursor
If the executable is not found the model could simply use whatever else is available to do what it wants to do - like using other interpreted languages, sh -c, symlink, etc. It will eventually succeed unless there is a proper sandbox in place to disallow unlinking of files at syscall level.