Bryan Caplan recently wrote about using ChatGPT to fact-check Modern Times by Paul Johnson. I commented there how I was able to use Claude Cowork to do a more thorough fact-check, which Bryan discussed here. Some people asked about my process, so I wrote a guest post for Bryan:
Besides my process, I discuss the powerful capabilities and existing weaknesses of modern AI, a generic way to fact-check books, and a more advanced pipeline to do this systematically.


