logoalt Hacker News

tuwtuwtuwtuwyesterday at 6:10 PM2 repliesview on HN

Couldn't that be solved by whitelisting specific commands?


Replies

wolttamyesterday at 6:20 PM

Such a mechanism would need to be implemented at `execve`, because it would be too easy for the model to stuff the command inside a script or other executable.

g947oyesterday at 8:02 PM

Give it a try, and challenge yourself (or ChatGPT) to break it.

You'll quickly realize that this is not feasible.