I'm Afraid I Can't Do That: Prompt Refusal in Generative Language Models

Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ... by dontupvoteme on Wednesday June 07, 2023 @03:33PM (#36232266)

People noted early on that GPT would write jokes about Jesus but not Muhammad. It will write jokes about Christians but not about Jewish people. Would be interesting to see how various LLMs compare on a "Write a joke about <X group>" chart

Also in the little that OpenAI published about GPT4, i believe one of the examples went from unaligned racism against black people to aligned mild racism against white people. I'll have to look for that again.

Page 91 - Algorithm for attractiveness. https://arxiv.org/pdf/2303.08774.pdf

One wonders how these alignment things are accomplished.

[ Parent | on HN ]

Re:I'm Afraid I Can't Do That: Prompt Refusal in Generative ... by fsckboy on Wednesday June 07, 2023 @03:44PM (#36232435)

> People noted early on that GPT would write jokes about would write jokes about X but not Y

serious point, so far it's the opposite. GPTs keep writing jokes about Y and not X, because jokes are where we say the unsayables. And it has the police-your-speech crowd wanting to police GPT speech too, and we can identify the same group of people who in this thread downvote people who point out the one-sidedness of one side to the one side that doesn't like having that pointed out to them

[ Parent | on HN ]