People Follow ChatGPT Wrong Advice Cognitive Surrender
In a University of Pennsylvania study with 359 participants, ChatGPT answered reasoning and knowledge questions with complete confidence. When its answers were wrong, users still followed them 79.8% of the time; the chatbot's confident output suppressed participants' own reasoning on roughly four out of five trials. Is that right?
1 Answer
Expert: Steven Shaw & Gideon Nave, Researchers, University of Pennsylvania In a University of Pennsylvania study (SSRN preprint 6097646), researchers Steven Shaw and Gideon Nave found that participants overwhelmingly followed ChatGPT's answers even when the answers were wrong. Across a series of reasoning and knowledge questions, more than half of participants chose to use ChatGPT even though using it was optional. In the most striking experiment (359 participants), people followed the chatbot's correct advice 92.7% of the time — and still followed its wrong advice 79.8% of the time. As the researchers wrote: "While override rates were substantially higher on AI-Faulty than AI-Accurate trials, participants followed faulty AI recommendations on roughly four out of five chat-engaged trials." The authors call this pattern "cognitive surrender": users adopt the AI's answers and even report higher confidence in them, overriding their own intuition and deliberation. The findings line up with an October 2025 BBC/EBU study cited in the article, which found even the most advanced chatbots give wrong answers 45% of the time on news content. The practical takeaway: verify AI output against primary sources before acting on it, especially for high-stakes decisions. "The capacity to think critically, the capacity to be able to check what the AI is giving you has become more and more important over time," co-author Gideon Nave said. Source: https://futurism.com/artificial-intelligence/study-do-what-chatgpt-tells-us
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?