You can persuade AI models to accept falsehoods as truth, study shows

By Ashique KhudaBukhsh, Assistant Professor of Computing and Information Sciences, Rochester Institute of Technology

When you ask a large language model a question, the reply may include falsehoods, and if you challenge those statements with facts, the AI may still uphold the reply as true. That’s what my research group found when we asked five leading models to describe scenes in movies or novels that don’t actually exist.

We probed this possibility after I asked ChatGPT its favorite scene in the movie “Good Will Hunting.” It noted a…

Read complete article

~	“Family, football and the World Cup should make space for everyone”

~	Why were Russian disinformation, government propaganda and AI-generated campaigning ineffective in Hungarian elections 2026?

~	Australians wait 12 months for aged care – and the latest budget funding is unlikely to change that

~	A historic court victory has upheld transgender rights in Australia. A legal academic explains why

~	After an opaque summit, China and the US want to work together again. That might not be good news for the world

~	Xi-Trump summit: reset for US-Chinese relations but tension over Taiwan remains

~	The conspiracy theorists who feel vindicated by the Epstein files

~	Paula Rego’s Story Line – an exhibition that invites exploration of the ambiguous narratives the Portuguese artist drew

~	Elizabeth I refused to go to bed before she died – a stubborn final act that reflected her reign

~	How reindeer herds, nature and Sámi culture can thrive when forests are restored across northern Europe