News for hackers. Stuff that matters.

A comment on Prompt injection: what’s the worst that can happen?.

Re:Prompt injection: what’s the worst that can happen? by alomaki on Saturday April 15, 2023 @06:09AM (#35579178)
Couldn't we use another gpt-3 model which is not visible to the user and can be used to find out those injection prompts.
[ Parent | on HN ]
Re:Prompt injection: what’s the worst that can happen? by MagicMoonlight on Saturday April 15, 2023 @06:24AM (#35579261)
That model will only be able to detect prompts it is trained on which is the security strategy they already use and doesn’t work
[ Parent | on HN ]