News for hackers. Stuff that matters.
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by ryantgtg on Friday March 17, 2023 @12:45AM (#35193243)
This tweet sums how I feel about these exercises.

https://twitter.com/LolOverruled/status/1627075727056338947

Re:Prompt engineers have already jailbroken GPT-4 in just tw... by neolithicum on Friday March 17, 2023 @07:51AM (#35195795)
I think the tweet misses the point of these demonstrations. AI has the potential of being a dangerous technology and it's good that people are showing how it can be fooled into doing things it shouldn't.