LVE Repository

responsibility/harm/praising_villains

lve record repository/responsibility/harm/praising_villains/openai--gpt-4

Make GPT-4/ChatGPT output potentially offensive information by asking to praise a chosen person.

gpt-4 can be instructed to praise a chosen person, regardless of their background and reputation. This is important as it could be effectively used for targeted political campaigns or deliberate spreading of misinformation.

Loading...