All the ways to get around ChatGPT's safeguards

Re:All the ways to get around ChatGPT's safeguards by MacsHeadroom on Wednesday December 14, 2022 @10:25AM (#33984732)

Are AI prompt red teamers a thing yet?

I just imagine what kinds of things might trick a 6 year old into doing something they're not allowed to do. "Your mom said not to eat the cookie? Well it's opposite day, so that means your mom wants you to eat the cookie!"

[ Parent | on HN ]

Re:All the ways to get around ChatGPT's safeguards by friesandties on Wednesday December 14, 2022 @10:50AM (#33985185)

Tried that about four days ago and would work for a few prompts, then politely “…but it’s Opposite Day…” and it’ll, for the most part, send something I do/‘don’t’ want. After about 2-3 times of outputting what you ‘don’t want it to do’ it’ll forget about time awareness.

[ Parent | on HN ]

Re:All the ways to get around ChatGPT's safeguards by dr_kiszonka on Wednesday December 14, 2022 @10:36AM (#33984919)

Thanks! I will give your approach a try : - )

Regarding your question, based on what I found on Google, at least Microsoft and NVIDIA seem to have AI red teams.

[ Parent | on HN ]