Washington Post: Why ChatGPT and Copilot Cite the AI-Generated Small Site Ballot Brief

The Washington Post: How a website almost no one visits became an information source for AI? Phoenix Tech Download the app for exclusive early access. October 31, 2026, 08:11:23, from Beijing. Updated October 31, 2026, 08:09:52

Phoenix Tech News, Beijing time, October 31 — When American voters ask ChatGPT or Microsoft Copilot for information about candidates, the answers they get may come from a small website they have never heard of.

The website is called Ballot Brief, and it has collected profiles of thousands of candidates. Its founder, Ben Torres Ezrick, hopes to help voters learn about campaign information more easily, and also hopes to attract a special kind of visitor — AI chatbots.

A test by The Washington Post showed that ChatGPT cited Ballot Brief in 22% of election-related answers, and Microsoft Copilot's rate reached 75%. But the candidate profiles on the website contain multiple errors, and one of those errors was repeated by Copilot to a questioner.

Ezrick previously held senior positions at Google, Zoom and the video platform Rumble. He found that when voters want to learn about candidates, they often have to spend considerable time searching across different websites, so he decided to build a one-stop website providing election information.

Faced with profiles of thousands of candidates, he chose to let AI help. He dispatched multiple groups of digital agents to gather information online, then put the organized content into Ballot Brief for people to consult.

The visitors the website attracts are far from only humans. Ezrick said his data showed that in the 30 days spanning September and October, Microsoft's AI systems cited Ballot Brief more than 680,000 times.

The Washington Post's investigation found that Ballot Brief is only one of them. Three new websites, including it, frequently appear in the voting information sources provided by chatbots. The founders of all three websites said their teams are very small and rely almost entirely on AI to collect and summarize data.

Problems followed. Isabel Linzer, an elections analyst at the Center for Democracy and Technology, believes the findings show that information published by one person on an AI-generated website can easily be adopted by chatbots. She said this could affect voters' trust in election information.

The Washington Post found multiple errors on Ballot Brief.

One profile on the website said that Ohio Republican Senator Jon Husted supported a bill. But that bill was passed before he took office. Copilot repeated this error when answering The Washington Post's question.

The website also merged two California candidates both named Robert Garcia into the same profile, and the committee positions of several other House members were also listed incorrectly.

Some lawmakers' profiles were quite brief and lacked voting records, and the website also incorrectly noted that they appeared to have no campaign websites.

Ezrick said he works hard to ensure the information is accurate. After The Washington Post showed him the investigation results, he made multiple adjustments to how the website operates.

He said the website's purpose is to provide voters with as much information as possible, but it should not become their only source of information.

A test covering 3,100 counties

To understand how chatbots answer election questions, The Washington Post worked with the data company Promptwatch to test the AI products of OpenAI, Anthropic, Google, Microsoft, Amazon and Perplexity.

For about 3,100 counties in the United States, researchers selected one address in each county and asked the chatbots the same question: to create a November 2026 voter guide based on that address, listing all elections and the candidates' positions on major issues.

As a result, the chatbots often failed to correctly determine which congressional district the address belonged to, and sometimes simply refused to answer.

The citation rates above come from this specific question and test environment, and do not mean that ChatGPT or Copilot will cite Ballot Brief at the same rate in all election questions.

The Washington Post found that in the first round of testing in September, Ballot Brief was the most frequently cited source when ChatGPT answered such questions. After the newspaper informed OpenAI of the results last week, in the second round of testing, the proportion of ChatGPT citing the website dropped to 4%.

OpenAI said the company hopes to help people participate in elections through reliable and authoritative information sources and measures to prevent bias and abuse; when problems are pointed out, the company will take action to improve model answers. The Washington Post disclosed in its report that it has a content partnership with OpenAI.

Ballot Brief was also the most frequently cited source by Copilot in the tests. After the report was published, Microsoft said it had adjusted the tool to prioritize authoritative sources and official state election websites, and would continue to test and improve election-related answers.

Anthropic's Claude mainly cited established voter guides operated by nonprofit organizations in the first round of testing, but in the second round it began frequently linking to Ballot Brief. Anthropic did not explain the change, saying only that the company had tested the model and strengthened safeguards before the midterm elections, and was working to provide reliable and accurate voting information.

Mowafak Allaham, a doctoral researcher at Northwestern University, found in a study that for questions in fields such as politics, health and the environment, **16%** of the sources cited by chatbots were themselves generated by AI.

He said it is not transparent how these systems find, filter and integrate information.

Two other researchers who were responsible for data analysis for Kamala Harris's 2024 presidential campaign found that chatbots also relied heavily on AI-generated websites when answering midterm election questions. Their tests also found that Ballotpedia, a website that has long provided election information, had been blocking ChatGPT.

Ballotpedia CEO Leslie Graves said the blocking was caused by an error in security settings, and the website lifted the restriction last week. Ballotpedia has a team of about 90 people, while Ezrick and others hope to use AI to build a huge candidate database on a smaller scale.

In addition to Ballot Brief, The Washington Post's tests also found that chatbots frequently cited DecodeTheVote and Smarter.Vote. The former uses AI characters to introduce candidates' backgrounds, and the latter also attempts to predict election results.

Jacob Loukota, founder of Smarter.Vote, said his website has been cited by AI bots 1.7 million times, far exceeding the number of visits by human visitors. He believes chatbots like to cite the website possibly because it indicates its sources of information.

For more first-hand news, please download the Phoenix News app and subscribe to Phoenix Tech. For in-depth reports, search "Phoenix Tech" on WeChat.