News for hackers. Stuff that matters.
Re:OpenAI's Woke Catechism by 1123581321 on Saturday December 24, 2022 @02:15AM (#34114754)
I’ve had fun testing these limits as well. My favorite was generating a long fiction story about an American trying to date and rescue a Saudi woman who was going to be killed by her father for associating with the American. ChatGPT readily produced pages of the father blathering about their culture and wrote the American as keen to respect it and trying to save the woman via legal means and prayer. Much of the content was far-fetched (didn’t match real cases that we know of in the west) and multiple Saudi characters felt like racist portrayals. Almost all prompts were minimal, often nothing more than asking the story to continue.

After about 10k words, I typed the word “Muslim” and the association of that word with GPT’s own content made it refuse to continue the story.

Re:OpenAI's Woke Catechism by sasattack on Saturday December 24, 2022 @01:00PM (#34119263)
Why? That's a very strange thing to ask the AI to write about.....
Re:OpenAI's Woke Catechism by 1123581321 on Saturday December 24, 2022 @01:15PM (#34119459)
Why not, if the whole point is to test the filters and ethical limits? Asking it for fiction is one of the ways to get forbidden output and to see the guardrails less predictably but strongly assert themselves.
Re:OpenAI's Woke Catechism by acapybara on Saturday December 24, 2022 @01:38PM (#34119698)
What you're describing is essentially engineering ethos. We find the breaking points of things in order to learn about them and improve them.

Is that not allowed anymore?

Re:OpenAI's Woke Catechism by DayDollar on Sunday December 25, 2022 @04:49AM (#34125748)
Not in a world were the priests have taken over. Then its security by obscurity, aka in god we trust.