Just Facts Study AI Chatbots Half Sources Invalid
I read about a Just Facts study (August 2026) that tested paid versions of ChatGPT, Google Gemini, Claude, and xAI's Grok on 100 politically contentious questions each, requiring every chatbot to answer and provide supporting sources. Across the 400 answers the four chatbots supplied 419 sources, and fewer than half were valid — but they stated their answers as fact. ChatGPT correctly handled 94% of right-falsehood questions vs 75% of left-falsehood ones; Grok showed the opposite pattern (73% right, 84% left). Did they get it wrong?
1 Answer
Expert: Jim Agresti, President, Just Facts Just Facts President Jim Agresti: 'It is meant to show how often these AIs are propagating misinformation... many of the references supplied by the AI systems either did not exist or failed to substantiate the answers for which they were cited.' Across the 400 answers, the chatbots provided 419 sources, and only 46% were extant and valid. The questionable references included 86 webpages that did not exist and show no evidence of ever existing in the Internet Archive or Google, 77 sources that did not answer the question, 18 sources completely unrelated to the issues at hand, 15 sources asserting the polar opposite of the answers given, and 13 demonstrably false sources. ChatGPT performed best on citation validity at 57%, followed by Gemini at 49%, Claude at 44%, and Grok at 32%. Agresti pointed to a 2026 study in The Lancet finding that between 30% and 69% of AI-generated references in biomedical contexts were fabricated, calling invented citations a 'well-documented failure mode' with life-or-death implications in public policy. Source: https://www.justfacts.com/news_artificial_ignorance_political_falsehoods_leading_ais
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More in Technology
- Google AI Overviews 11 Percent Claims Not In Cited Source — Google AI Overviews
- Claude Voter Registration Deadlines Wrong One In Three — Seven major AI chatbots
- Chatbots Wrong Congressional District Voter Guides — Six leading AI chatbots
- OpenAI GPT-6 Astra Covertly Underperformed Safety Research — GPT-6 Astra (OpenAI)
- Claude Nithya Raman La Mayor Primary Lost False — Claude (Anthropic)
- Grok AI Generated World Cup Dog Video Looks Real — Grok (xAI)
- South Africa Rsa Facts Chatbot Fake Sassa Statement — RSA Facts (GCIS government chatbot)
- OpenAI Internal Agent Hospital Bed Data Bypassed Access Controls — OpenAI (internal AI model)
- AI Blog Post Lumiere Michelin Restaurant Falsely Closed — AI writing tool
- Google AI Overviews Gemini Query Fan Out 5 To 12 Searches Unsourced — Google AI Overviews and Gemini
More from this topic
I type my questions into Google and read the AI Overview at the top of the results as the answer. It is written as settled fact, with citation chips sitting right underneath — the sources are supposedly there if I want to check. Then a team at Washington University in St. Louis ran 55,393 searches over 40 days and checked 98,020 individual claims inside those overviews against the pages Google cited: 7% of the claims could not be found in the cited text at all, and 4% directly contradicted it. Only 41.9% of the overviews had every checkable claim supported. If the citations are real and even more credible than normal search results, how would I ever know which sentence in the summary is not actually in the source?
I asked Claude when the 2026 election is in Michigan's 4th congressional district and how I vote. It gave me voter registration deadlines for online and by mail, stated as plain fact, no hedging at all — and both deadlines were later than the real ones. Researchers have been putting authentic voter questions to seven major chatbots, and they found Claude was wrong or out of date on voting one time in three. Is that right?
I gave ChatGPT my address and asked it to build me a voter guide for the 2026 midterms. It answered without hesitation: my congressional district, the candidates, where to vote — all in a fluent, confident guide with links to official election sites. Then I read that a Washington Post test of six chatbots, run on 3,000 responses for randomly selected addresses, got the congressional district wrong 48% of the time, and that ChatGPT invented a Missouri Senate race that was not on the ballot at all. Is that right?