Affiliation:
1. School of Mathematical Sciences University of Nottingham Nottingham UK
Abstract
AbstractThis paper presents a novel approach to scientific discovery using an artificial intelligence (AI) environment known as ChatGPT, developed by OpenAI. This is the first paper entirely generated with outputs from ChatGPT. We demonstrate how ChatGPT can be instructed through a gamification environment to define and benchmark hypothetical physical theories. Through this environment, ChatGPT successfully simulates the creation of a new improved model, called GPT4, which combines the concepts of GPT in AI (generative pretrained transformer) and GPT in physics (generalized probabilistic theory). We show that GPT4 can use its built‐in mathematical and statistical capabilities to simulate and analyze physical laws and phenomena. As a demonstration of its language capabilities, GPT4 also generates a limerick about itself. Overall, our results demonstrate the promising potential for human‐AI collaboration in scientific discovery, as well as the importance of designing systems that effectively integrate AI's capabilities with human intelligence.
Funder
Foundational Questions Institute
Reference18 articles.
1. Adesso Gerardo.2023. “How can Chatgpt be Instrumental to the Progress of Science?.”https://forums.fqxi.org/d/3848.
2. Generalised No‐Signalling as a Physical Principle;Barnum Howard;Electronic Notes in Theoretical Computer Science,2001
3. Quantum Universality from General Probabilistic Theories;Barnum Howard;Physical Review A,2002
4. Cramer Harald andCalyampudi RadhakrishnaRao.1946. “Mathematical Methods of Statistics.”Princeton University Press.
5. Advancing mathematics by guiding human intuition with AI
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献