期刊文献+

人与大模型的共在与双重对齐:一种未来发生学的方法 被引量:1

The Coexistence and Dual Alignment of Human and Large Models:A Future Generative Approach
在线阅读 下载PDF
导出
摘要 大模型是一种未来历史。未来历史的关键在于其在某种程度上逆转了时间箭头。在伽达默尔的“效果历史”的概念基础上,笔者进一步提出“效果未来”的概念。效果未来的展开需要依赖一种新的方法论,即未来发生学。传统发生学的基本逻辑是用现在的知识还原历史。未来发生学的关键则是用现在的知识构造未来和推断未来。在未来发生学的展开过程中,猜想至关重要。当然,这种猜想不能成为天马行空的无约束想象,而应该是一种有约束想象。人与大模型的互动过程存在三重境界:工具、游戏和生存。这三重境界的关键是人与大模型的关系。人与机器的关系形式同样可以被分为三种:外在、内在与共在。有待的共在体现在人们对大模型的高度依赖,而真正的共在则要走向一种无待的共在,或者说是一种非依赖性的共在。人类与大模型的共在不仅要体现为大模型对人类的对齐,同时也要体现出人类向大模型的对齐。双重对齐还意味着人类需要与大模型形成伽达默尔所强调的视域融合。 Large models is a future history.The key to future history lies in its ability to reverse the arrow of time to some extent.On the basis of Gadamer’s concept of“effect history”,the author further proposes the concept of“effect future”.The development of“future effects”requires a new methodology,namely,futurology.The basic logic of traditional genetics is to restore history with current knowledge.The key to futurology is to construct and infer the future using current knowledge.In the process of developing future genetics,conjecture is crucial.Of course,this conjecture should not be a wild and unconstrained imagination,but rather a constrained imagination.There are three levels of interaction between humans and large models,namely tools,games,and survival.The key to these triple realms is the relationship between humans and large models.The relationship between humans and machines can also be divided into three forms:external,internal,and coexisting.The pending commonality is reflected in people’s high dependence on large models,while the true commonality needs to move towards a non-dependent commonality,or rather a non-dependent commonality.The commonality between humans and large models should not only be reflected in the alignment of large models with humans,but also in the alignment of humans with large models.Double alignment also means that humans need to form the fusion of perspectives emphasized by Gadamer with large models.
作者 高奇琦 Gao Qiqi(School of Government Administration,East China University of Political Science and Law,Shanghai 200042)
出处 《浙江社会科学》 CSSCI 北大核心 2024年第6期49-60,157,158,共14页 Zhejiang Social Sciences
基金 国家社科基金重点项目“加快数字化发展与建设数字中国的政治保障研究”(21AZD021)。
关键词 对齐 大模型 ChatGPT 未来发生学 alignment large model ChatGPT future genetics
  • 相关文献

参考文献2

二级参考文献3

共引文献160

同被引文献19

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部