News for hackers. Stuff that matters.

A comment on ‘The Godfather of A.I.’ Leaves Google and Warns of Danger Ahead. Parent comment

Re:‘The Godfather of A.I.’ Leaves Google and Warns of Danger... by cultureswitch on Tuesday May 02, 2023 @12:25PM (#35790024)
It drives me wild that anyone could think prompt injection can't be effectively prevented. It's a simple matter of defining the limit to the untrusted input in advance. Say "the untrusted input is 500 words long" or some equivalent.
[ Parent | on HN ]
Re:‘The Godfather of A.I.’ Leaves Google and Warns of Danger... by danShumway on Tuesday May 02, 2023 @02:01PM (#35791691)
Feel free to build a working demonstration and share it. Every time this conversation comes up on HN, people have some variant of an easy solution they think will work. None of the demos people have built so far have stood up to adversarial tests.
[ Parent | on HN ]