走向终极大脑:用ChatGPT AI探索科学发现

IF 2.5 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Ai Magazine Pub Date : 2023-08-26 DOI:10.1002/aaai.12113
Gerardo Adesso
{"title":"走向终极大脑:用ChatGPT AI探索科学发现","authors":"Gerardo Adesso","doi":"10.1002/aaai.12113","DOIUrl":null,"url":null,"abstract":"<p>This 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 GPT<sup>4</sup>, which combines the concepts of GPT in AI (generative pretrained transformer) and GPT in physics (generalized probabilistic theory). We show that GPT<sup>4</sup> can use its built-in mathematical and statistical capabilities to simulate and analyze physical laws and phenomena. As a demonstration of its language capabilities, GPT<sup>4</sup> 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.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 3","pages":"328-342"},"PeriodicalIF":2.5000,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12113","citationCount":"4","resultStr":"{\"title\":\"Towards the ultimate brain: Exploring scientific discovery with ChatGPT AI\",\"authors\":\"Gerardo Adesso\",\"doi\":\"10.1002/aaai.12113\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>This 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 GPT<sup>4</sup>, which combines the concepts of GPT in AI (generative pretrained transformer) and GPT in physics (generalized probabilistic theory). We show that GPT<sup>4</sup> can use its built-in mathematical and statistical capabilities to simulate and analyze physical laws and phenomena. As a demonstration of its language capabilities, GPT<sup>4</sup> 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.</p>\",\"PeriodicalId\":7854,\"journal\":{\"name\":\"Ai Magazine\",\"volume\":\"44 3\",\"pages\":\"328-342\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2023-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12113\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ai Magazine\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12113\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ai Magazine","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12113","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 4

摘要

本文提出了一种利用OpenAI开发的人工智能(AI)环境ChatGPT进行科学发现的新方法。这是第一篇完全由ChatGPT输出的论文。我们展示了如何通过游戏化环境指导ChatGPT来定义和基准测试假设的物理理论。通过这种环境,ChatGPT成功地模拟了一种新的改进模型的创建,称为GPT4,它结合了人工智能中的GPT(生成预训练变换器)和物理学中的GPT(广义概率理论)的概念。我们证明GPT4可以使用其内置的数学和统计功能来模拟和分析物理定律和现象。为了展示其语言能力,GPT4还制作了一首关于自己的打油诗。总的来说,我们的研究结果证明了人类与人工智能在科学发现中的合作潜力,以及设计将人工智能的能力与人类智能有效集成的系统的重要性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Towards the ultimate brain: Exploring scientific discovery with ChatGPT AI

This 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.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Ai Magazine
Ai Magazine 工程技术-计算机:人工智能
CiteScore
3.90
自引率
11.10%
发文量
61
审稿时长
>12 weeks
期刊介绍: AI Magazine publishes original articles that are reasonably self-contained and aimed at a broad spectrum of the AI community. Technical content should be kept to a minimum. In general, the magazine does not publish articles that have been published elsewhere in whole or in part. The magazine welcomes the contribution of articles on the theory and practice of AI as well as general survey articles, tutorial articles on timely topics, conference or symposia or workshop reports, and timely columns on topics of interest to AI scientists.
期刊最新文献
Issue Information AI fairness in practice: Paradigm, challenges, and prospects Toward the confident deployment of real-world reinforcement learning agents Towards robust visual understanding: A paradigm shift in computer vision from recognition to reasoning Efficient and robust sequential decision making algorithms
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1