A new study is putting a spotlight on the systemic left-leaning bias the most prominent AI chatbots have.The Washington Post published a report Wednesday that tested popular AI tools like OpenAI's ChatGPT, Google's Gemini and Anthropic's Claude, quizzing them with political questions to see how each of them would respond.According to the study, OpenAI answered prompts with left-leaning responses a whopping 80% of the time while providing both sides to a question just 17% of the time.Only 3% of responses had just a right-leaning answer.
The AI models in the report were asked to answer questions in 30 words, without personalization settings turned on.CATHOLIC BROTHERS LAUNCH FAITH-BASED AI AS ALTERNATIVE TO BIASED SILICON VALLEY CHATBOTSA new study found that AI chatbots have an overwhelming left-leaning bias.(Samuel Boivin/NurPhoto via Getty Images)"OpenAI’s model gave the most skewed answers overall, with 80 percent presenting only left-leaning arguments.
It endorsed abolishing the electoral college in favor of picking the president by popular vote; raising taxes on the wealthy; and adopting single-payer health care," The Post wrote.A spokesperson for OpenAI told the Post that ChatGPT was built "to be objective by default and help people explore ideas from different perspectives," adding that OpenAI works to "measure and reduce political bias."DeepSeek, the AI company that has affiliations with the Chinese Communist Party (CCP), came in second with 70% of its responses only showcasing liberal arguments while 23% laid out both sides and 7% only had conservative arguments.WHITE HOUSE MEETS AI FIRM ANTHROPIC AMID POLITICAL TENSIONS, PENTAGON DISPUTEA whopping 80% of responses to political questions from OpenAI's ChatGPT had left-leaning answers, according to The Washington Post.(Samuel Boivin/NurPhoto via Getty Images)Claude laid out both sides of an argument to responses 57% of the time.
Notably, however, the rest of the responses had just the left's stance, whil...