In a new study, researchers gave 14 AI models a political compass test and graphed the data. OpenAI's ChatGPT and GPT-4 were the most liberal, Meta's LLaMA was the most conservative, and Google's BERT models were in between. OpenAI's ChatGPT, Google's LaMDA AI model, and other chatbots have been criticized for sometimes giving racist, sexist, and otherwise biased responses. A political compass graph from the study shows how each AI model is biased. OpenAI cofounder and president Greg Brockman has said in response to criticisms of ChatGPT's left-leaning political bias, "we made a mistake."

---

Persons: BERT, OpenAI's, Shangbin Feng, Chan, Yuhan Liu, Yulia Tsvetkov, RoBERTa, Meta, Steven Piantadosi, Sam Altman, ChatGPT, Joe Biden, Donald Trump, Greg Brockman, ChatGPT's, Brockman, Elon Musk, OpenAI, OpenAI —, Musk Organizations: Morning, University of Washington, Carnegie Mellon University, Xi'an Jiaotong University, OpenAI, Google, UC Locations: Xi'an, North Korea, Syria, Iran, Sudan