A study finds that assigning ChatGPT a persona, like “a bad person” or a certain historical figure, using the API, increases the chatbot’s toxicity sixfold (Kyle Wiggers/TechCrunch)

A study finds that assigning ChatGPT a persona, like “a bad person” or a certain historical figure, using the API, increases the chatbot’s toxicity sixfold (Kyle Wiggers/TechCrunch)

Kyle Wiggers / TechCrunch:
A study finds that assigning ChatGPT a persona, like “a bad person” or a certain historical figure, using the API, increases the chatbot’s toxicity sixfold  —  It’s no secret that OpenAI’s viral AI-powered chatbot, ChatGPT, can be prompted to say sexist, racist and pretty vile things.