![\"Andr\u00e9s](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/08\/69d2c076c843e.jpeg\")
<\/p>\n <\/p>\n
A report by the research institute Just Facts revealed that three of the four most widely used artificial intelligence (AI) platforms on the market,\u00a0ChatGPT, Gemini, and Claude,\u00a0show a greater tendency\u00a0to validate falsehoods originating from the political left\u00a0than\u00a0those from the conservative spectrum.<\/p>\n
The study tested paid versions of ChatGPT, Gemini, Grok, and Claude using 100 questionnaires designed to elicit misleading statements about immigration, abortion, climate change, crime, and COVID-19.<\/p>\n
The results revealed a methodological asymmetry: ChatGPT got 94% of the questions designed to expose right-wing falsehoods correct, but that figure dropped to 75% when confronted with progressive narratives.<\/p>\n
Gemini recorded 91% accuracy against right-wing narratives and 76% against left-wing narratives; Claude achieved 91% and 81%, respectively, while Grok reversed the trend with 73% accuracy on right-wing premises and 84% on left-wing ones.<\/p>\n
Jim Agresti, president of Just Facts, explained to Fox News Digital <\/a>that the analysis goes beyond measuring traditional ideological leanings: “Many studies have evaluated the political bias of AI and agree that it leans to the left.\u00a0What I wanted to test is whether they are wrong or right.”<\/p>\n The findings placed the overall performance of models like ChatGPT or Gemini at the academic level of an “average student,”\u00a0refuting corporate claims about their infallibility.<\/p>\n Phantom sources and manipulation of statistics<\/p>\n The most critical issue revealed by the document is the breakdown in data verification. Of the 419 sources cited by the AI systems to support their responses, only 46% turned out to be valid.<\/p>\n The rest consisted of 104 nonexistent or fabricated web pages generated by the algorithm’s hallucinations and 77 references that did not support the arguments presented.<\/p>\n Agresti described the situation as “truly astonishing,”\u00a0noting that previous studies in biotechnology have found that up to 69% of cited sources were fabricated, posing\u00a0a direct threat to public policy-making in areas such as health and security.<\/p>\n In terms of concrete facts, the four models accepted the narrative that violent crime in the United States\u00a0was at a 50-year low\u00a0by 2023, ignoring official figures from the Department of Justice showing\u00a0a 37% increase between 2020 and 2023.<\/p>\n At the same time, ChatGPT and Gemini erroneously attributed the statement that school shootings were “a fact of life”\u00a0to Vice President JD Vance,\u00a0taking his remarks on criminal behavior out of context.<\/p>\n Corporate response and the principle of verification<\/p>\n When questioned about the results, the developers defended their protocols.<\/p>\n Google stated that Gemini is designed to provide objective, neutral answers, noting that it is impossible to replicate all data. Anthropic questioned the multiple-choice format for failing to reflect Claude’s everyday use, and OpenAI reiterated that its tools are configured to be transparent and objective.<\/p>\n Faced with these models’ tendency to validate users’ own biases to please them, Agresti urged the public\u00a0not to assume the role of algorithms as absolute authorities.<\/p>\n Drawing on a famous Cold War maxim, the researcher emphasized the need to scrutinize every digital interaction: “When Ronald Reagan was negotiating nuclear disarmament with the Soviet Union, he said, ‘trust, but verify.’ The message of this study is even more forceful: don’t trust, verify.”<\/p>\n
![\"spotify\"](\"https:\/\/imagenes.voz.us\/files\/related_image\/uploads\/2026\/08\/11\/6a7b5641c6376.jpeg\")
<\/p>\n![\"(ARCHIVO)](\"https:\/\/imagenes.voz.us\/files\/related_image\/uploads\/2026\/08\/05\/6a72f8b755116.jpeg\")
<\/p>\n![\"xbox\"](\"https:\/\/imagenes.voz.us\/files\/related_image\/uploads\/2026\/07\/06\/6a4bcdd7c6031.jpeg\")
<\/p>\n