yesnoerror is an AI agent that uses OpenAI's o1 model to find errors in published research papers. In October of 2024 a research paper claimed that black cooking utensils were extremely poisonous. People panicked. It turns out there was an error in the paper and it was wrong. When the paper was given to the AI model o1 from OpenAI, it was able to spot the error. What other errors might be hidden in the tens of millions of published research papers? What mistakes have gone unnoticed? What if an AI went and found all the errors?
