AI Chatbots Generate Inaccurate Election Information in Voter Guide Tests
A study conducted by The Washington Post, reportedly in conjunction with NPR, found that leading AI chatbots like ChatGPT, Gemini, and Perplexity produced significant errors when asked to create voter guides. The chatbots frequently invented non-existent races, misidentified candidates, and hallucinated other election-related information. This highlights concerns about the reliability of AI models for critical civic information.
3 articles from 3 outlets covered this story. The underlying claim is sourced from a benchmark.
What do all outlets agree on?
3 outlets covered “AI Chatbots Generate Inaccurate Election Information in Voter Guide Tests”. All of them report the following:
- AI chatbots including ChatGPT, Gemini, and Perplexity were tested.
- The chatbots generated inaccurate election information.
- Errors included inventing non-existent races and misidentifying candidates.
- The study was conducted by The Washington Post, with NPR also reporting findings.
Which outlets covered this?
All 3 articles found on this story, grouped by the stance of the piece. Every link goes to the original publisher.