News for hackers. Stuff that matters.

A comment on Prompt engineers have already jailbroken GPT-4 in just two days. Parent comment

Re:Prompt engineers have already jailbroken GPT-4 in just tw... by Mezzie on Friday March 17, 2023 @09:33AM (#35196853)
I got a warning from ChatGPT for asking 'are butts inappropriate'. (I'm a librarian who was playing with it from the POV of different users and I was trying to approximate an elementary school aged child at the time.) I forsee a lot of people being banned as teens and it causing issues later.
[ Parent | on HN ]
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by JasonFruit on Friday March 17, 2023 @10:55AM (#35197896)
My bet is that OpenAI, for all its dominance right now, won't be a sole provider long into the future. Being banned by them early won't be a lifelong handicap.
[ Parent | on HN ]
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by Mezzie on Friday March 17, 2023 @11:57AM (#35198778)
Probably true, but given how the politics are developing, I wouldn't be shocked if there were a universal blacklist eventually.
[ Parent | on HN ]
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by AussieWog93 on Friday March 17, 2023 @09:01PM (#35204921)
I spent several hours over several days getting it to generate hate speech, illegal content and semi-incoherent strings of ethnic slurs.

It gave the warnings, but nothing really happened.

I suspect that OpenAI actually wants kids to play with the tech in this way, as it creates a whole lot of rich data that can be used to fortify the system against actual bad actors.

[ Parent | on HN ]
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by s3p on Saturday March 18, 2023 @12:55PM (#35210762)
Everyone keeps talking about getting banned while OpenAI is saying nothing about it. Just speculation on everybody's part. Not super helpful
[ Parent | on HN ]