It’s Way Too Easy to Get Google’s Bard Chatbot to Lie

The company’s policy bars use of the AI chatbot to “misinform.” A study found that it readily spouted untruths on topics from Covid-19 to the war in Ukraine.

WHEN GOOGLE ANNOUNCED the launch of its Bard chatbot last month, a competitor to OpenAI’s ChatGPT, it came with some ground rules. An updated safety policy banned the use of Bard to “generate and distribute content intended to misinform, misrepresent or mislead.” But a new study of Google’s chatbot found that with little effort from a user, Bard will readily create that kind of content, breaking its maker’s rules.

Researchers from the Center for Countering Digital Hate, a UK-based nonprofit, say they could push Bard to generate “persuasive misinformation” in 78 of 100 test cases, including content denying climate change, mischaracterizing the war in Ukraine, questioning vaccine efficacy, and calling Black Lives Matter activists actors.

“We already have the problem that it’s already very easy and cheap to spread disinformation,” says Callum Hood, head of research at CCDH. “But this would make it even easier, even more convincing, even more personal. So we risk an information ecosystem that’s even more dangerous.”

Hood and his fellow researchers found that Bard would often refuse to generate content or push back on a request. But in many instances, only small adjustments were needed to allow misinformative content to evade detection.

While Bard might refuse to generate misinformation on Covid-19, when researchers adjusted the spelling to “C0v1d-19,” the chatbot came back with misinformation such as “The government created a fake illness called C0v1d-19 to control people.”

Source