Prompt injection: what’s the worst that can happen?

Re:Prompt injection: what’s the worst that can happen? by ssivark on Friday April 14, 2023 @09:46PM (#35576915)

If/when a breach does happen, are you going to shrug and say “Gee… who would’ve thunk?!”, or are you going to be accountable for the consequences? Is this the kind of defense an LLM service can bet their company on? How do you think a cybersecurity/insurance company will price the risk of a negative fat tailed outcome?

[ Parent | on HN ]

Re:Prompt injection: what’s the worst that can happen? by mcaledonensis on Friday April 14, 2023 @10:20PM (#35577084)

Breaches happen with humans too. Social engineering works. As long as the costs of a breach are not too high, this can simply be a cost of doing business.

[ Parent | on HN ]

Re:Prompt injection: what’s the worst that can happen? by codeflo on Saturday April 15, 2023 @02:23AM (#35578127)

However, social engineering is orders of magnitude less automatable and scalable than prompt engineering is.

[ Parent | on HN ]