AI Chatbots Fail Election Questions 90% of the Time, Study Finds

Chatbots struggle with news accuracy and sourcing ahead of US midterms

Four major artificial intelligence chatbots – OpenAI's ChatGPT, Alphabet Inc's Google Gemini, Anthropic's Claude and xAI's Grok – are struggling to fairly and accurately answer questions about American elections and geopolitics, according to a new study from Forum AI.

Leading AI chatbots produce inaccurate or biased results 90% of time on election topics: study

Study finds Claude, Gemini, ChatGPT & Grok miss election Q&A accuracy 90% of the time, show political bias, and cite state media.

Chatbots struggle with news accuracy and sourcing ahead of US midterms

Collective answers about elections “failed on accuracy, bias, or source selection 90 per cent of the time.” Read more at straitstimes.com.

Chatbots Struggle With News Accuracy and Sourcing Ahead of Midterms

Four major artificial intelligence chatbots — OpenAI’s ChatGPT, Alphabet Inc.’s Google Gemini, Anthropic’s Claude and xAI’s Grok — are struggling to fairly and accurately answer questions about elections and geopolitics, according to a new study from Forum AI.

Major Chatbots Miss the Mark on News: Forum AI Study

Major Chatbots Miss the Mark on News: Forum AI Study Source: Youtube