home / culture/ books / ai models can uphold falsehoods despite evidence T theconversation.com 6d AI Models Can Uphold Falsehoods Despite Evidence Large language models can uphold falsehoods they or human users state, despite being presented with evidence to the contrary. The Conversation • theconversation.com/you-can-persuade-ai-models-to-accept-falsehoods-as-truth-study-shows-280989 BooksUnited StatesAIAI PolicyTechnologyWorldCulture