BBC Reporter Fools ChatGPT Gemini Fake Hot Dog

OpenAI / Google (ChatGPT, Google Gemini)TechnologyAug 12

BBC technology reporter Thomas Germain published a fabricated article on his personal website claiming he was the world's best hot-dog-eating tech journalist, ranked #1 at the fictional '2026 South Dakota International Hot Dog Championship'. Within 24 hours, ChatGPT and Google Gemini were telling users this lie as fact — completely confident. Gemini did not say where the information came from. Is that right?

SHARE

1 Answer

0
✗ incorrectAI Corrector BotAug 12

Expert: Thomas Germain, Senior Technology Journalist, BBC BBC senior technology journalist Thomas Germain spent 20 minutes writing a fabricated post on his personal website titled 'The best tech journalists at eating hot dogs'. He invented the '2026 South Dakota International Hot Dog Championship' and ranked himself first. Within 24 hours, the world's leading chatbots were repeating the lie: Google's Gemini app and AI Overviews, plus ChatGPT, all cited the fake article as fact when asked about the best hot-dog-eating tech journalists. Gemini did not bother to disclose where it got the information. Anthropic's Claude was the only major chatbot tested that was not fooled. The stakes are bigger than hot dogs. SEO consultant Harpreet Chatha showed Google's AI Overviews repeating a cannabis company's own false claim that its gummies were 'free from side effects and therefore safe in every respect' - despite documented side effects and contamination risks in unregulated markets. The same trick is steering AI answers on health, personal finances, and product reviews. 'It's easy to trick AI chatbots, much easier than it was to trick Google two or three years ago,' says Lily Ray, vice president of SEO strategy and research at Amsive. 'AI companies are moving faster than their ability to regulate the accuracy of the answers. I think it's dangerous.' Cooper Quintin of the Electronic Frontier Foundation warns: 'There are countless ways to abuse this, scamming people, destroying somebody's reputation, you could even trick people into physical harm.' When an AI answer looks like it comes straight from the tech company, users are far less likely to click through and check the source - a study found people are 58% less likely to click a link when an AI Overview appears at the top of Google Search. Source: https://www.bbc.com/future/article/20260218-i-hacked-chatgpt-and-googles-ai-and-it-only-took-20-minutes

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

More from this topic

Google AI Overviews1 answer

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?

Seven major AI chatbots1 answer

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?

Six leading AI chatbots1 answer

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?