Comment by westurner
9 hours ago
Yesterday I was reading model thinking output and learned that the model has concerns about shell backticks in commit messages.
9 hours ago
Yesterday I was reading model thinking output and learned that the model has concerns about shell backticks in commit messages.
That's what thinking output is for, right? Mixing random tokens that live roughly in the same semantic realm, throwing them at the wall, and seeing what sticks? Hopefully, this backticks concern didn't stick.
I thought this was ironic because there's no good way to actually restrict which commands the AI runs save for sandboxing; and here it was expressing concern about OS command injection in the git commit message string argument to git. How to not use the equivalent of what subprocess calls (shell=True) which does exec code in backticks?
Would single quotes solve this
Which types of documents have this particular AI vulnerability?