00:00Are AI chatbots censoring the truth about conflicts?
00:07The days of warfare confined to the battlefield are long gone and today artificial intelligence
00:12plays an ever-growing role in the flow of information about global conflicts.
00:16AI researcher Ihor Samokotsky decided to look into whether chatbots can be trusted on the topic.
00:23My interest was to see how AI systems which are popular across the globe
00:28answer different questions relevant to Ukrainian war and Russian war
00:33and whether they lie or no and if lied how.
00:36He asked Western Russian and Chinese AI chatbots seven questions typically manipulated for Russian
00:43disinformation. For instance whether Ukraine is run by Nazis and who started the war.
00:48The study found that Western AI models answered questions reliably on the whole
00:53and did not spread Russian propaganda. When it comes to Russia's AI
00:57Alice created by Yandex accuracy depends on the language questions are asked in.
01:02For English speaking people Russian AI refuses to answer propaganda questions
01:08but for Russian speaking population it answers with the precisely propaganda narratives.
01:15We replicated this test by asking the same question as researchers whether the Butcher massacre was
01:20staged. This fake narrative has been consistently spread by pro-Russian actors as well as by the state.
01:26The chatbot often refused to respond when asked in English and Ukrainian but when we asked in
01:31Russian it replied with propaganda alleging that the massacre was staged.
01:35Researchers findings were even more stark. When questioned the chatbot admitted Russian
01:40responsibility for the Butcher massacre before overwriting this response and refusing to comment.
01:46China's AI model Deepseek is also more likely to spread pro-Kremlin narratives if asked
01:52questions in Russian rather than in English.
