{"slug": "how-well-does-current-ai-find-errors-in-economics-papers", "title": "How well does current AI find errors in economics papers?", "summary": "A new study by Alexis Akira Toda tested four AI models—Gemini, Refine, Claude, and ChatGPT—on their ability to detect errors in published economics papers, with ChatGPT Pro performing best but still failing to identify any error without substantial human guidance. The findings suggest that while a human paired with a frontier model can outperform current peer review, AI alone cannot yet refute economic theory, raising questions about its reliability in academic verification.", "body_md": "# How well does current AI find errors in economics papers?\n\nCan artificial intelligence (AI) refute economic theory? I document experiments in which I asked several AI models (Gemini, Refine, Claude, and ChatGPT) to check the correctness of four published papers in economic theory, each containing an error that I helped identify or correct. ChatGPT Pro performed best, occasionally constructing counterexamples and corrected proofs, while other models fared worse. However, no model located a true error without substantial human guidance, and data contamination complicates interpretation. I argue that a competent human paired with a frontier model can outperform current peer review, but AI cannot yet refute economic theory on its own.\n\nThat is from [a new piece](https://arxiv.org/pdf/2606.05383) by Alexis Akira Toda.", "url": "https://wpnews.pro/news/how-well-does-current-ai-find-errors-in-economics-papers", "canonical_source": "https://marginalrevolution.com/marginalrevolution/2026/06/how-well-does-current-ai-find-errors-in-economics-papers.html?utm_source=rss&utm_medium=rss&utm_campaign=how-well-does-current-ai-find-errors-in-economics-papers", "published_at": "2026-06-09 18:20:40+00:00", "updated_at": "2026-06-11 17:36:19.165756+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["Gemini", "Refine", "Claude", "ChatGPT", "Alexis Akira Toda"], "alternates": {"html": "https://wpnews.pro/news/how-well-does-current-ai-find-errors-in-economics-papers", "markdown": "https://wpnews.pro/news/how-well-does-current-ai-find-errors-in-economics-papers.md", "text": "https://wpnews.pro/news/how-well-does-current-ai-find-errors-in-economics-papers.txt", "jsonld": "https://wpnews.pro/news/how-well-does-current-ai-find-errors-in-economics-papers.jsonld"}}