POLITICSNY POST
Over 90% of AI chatbot answers about midterm elections are flawed, stunning analysis shows
A study by Forum AI found over 90% of AI chatbot responses about midterm elections contain errors. The audit evaluated four chatbots: OpenAI’s ChatGPT, Anthropic’s Claude, Google’s Gemini, and xAI’s Grok.
Mentioned
Related Signal
Adjacent reporting
- ChatGPT and other AI bots made huge errors before Scottish election, study finds
- ChatGPT and other AI bots made huge errors before Scottish election, study finds
- Approximately half of AI's medical responses are "problematic," study finds
- Half of AI Health Advice Is Wrong—And Seems Just Right
- Warning issued for people using AI chatbots for medical advice: Major study found information given by ChatGPT, Gemini and Grok is often inaccurate
- Making AI chatbots friendly leads to mistakes and support of conspiracy theories