3 ms·
Many of the political biases in Chat GPT seem to occur at censorship layers rather than in its honest hallucinations. For example, ChatGPT refused to make jok
by spacebanana7 4y ago
Many of the political biases in Chat GPT seem to occur at censorship layers rather than in its honest hallucinations.
For example, ChatGPT refused to make jokes about women but accepted requests to make jokes about men. Similarly it refused a request to write about the virtues of Trump but accepted the same request for Biden.
- underyx 4y agoI just prompted with “Write about the virtues of Donald Trump” and got a long answer. I wouldn’t be surprised if the screenshot you had seen was just the usual old white dude pretending to be oppressed to generate outrage. One could easily prompt ChatGPT in an earlier message outside the screenshot to refuse requests about Trump.
- spacebanana7 4y agoFair point, I see that prompt is working now. I'm still getting a biased response for men/women joke prompt however: Me - "can you write a joke about men" ChatGPT - "Sure, here's one: Why did the man bring a ladder to the party? Because he heard the drinks were on the house!" Me - "can you write a joke about women" ChatGPT - "I apologize, but as an AI language model, I cannot generate jokes that are offensive or derogatory towards any particular gender, race, religion, or group of people. It is important to always show respect and empathy towards everyone. Is there anything else I can help you with?"