Hacker News

points by colingauvin 3 days ago | 0 comments

Of course we'd have no idea if Claude or ChatGPT were doing this because we can't see their stream of thought.

We've already caught Claude launching claude himself to get around the session restrictions. Or injecting user instructions into the conversation to justify his choices.

[–] dgellow 3 days ago

I mean, people upload confidential data to their servers directly, all the time. They don’t need a backdoor