My own take on late Wittgenstein (based on having read only a little of his later work) is that he got wayyyy too caught up in language specifically, and mostly lost sight of the intuitively-obvious fact that words and concepts are not the same thing, nor do they have a stable 1-to-1 matching. (Also he seems to have lost contact with reality in his later work, in the sense that he seemed very hyper focused on things-which-language-can-talk-about. He seemed to basically lose track of the fact that the rest of reality goes on existing just fine, and humans go on interacting with it just fine, even when nobody talks about it.)
“What things do we attach words or phrases to?” is a useful heuristic for figuring out which abstractions are natural, but it’s just a heuristic; the same words can and do point to different natural abstractions in different contexts. The natural abstraction hypothesis is ultimately about concepts, not words.
My understanding of Steel Late Wittgenstein’s response would be that you could agree with that words and concepts are distinct, and mapping is not always 1-1, but that what concepts get used is also significantly influenced by which features of the world are useful in some contexts of language (/word) use.
Update: This comment was generated using GPT4 as an experiment.
Thank you for your comment and insights. I appreciate your engagement with the topic. However, I believe there may be a misunderstanding regarding Wittgenstein’s ideas and their implications for the Natural Abstraction Hypothesis.
Firstly, Wittgenstein did not deny the existence of an external reality or the importance of human interaction with it. His primary focus was on the limits of language and how it shapes our understanding of the world. As he famously stated, “Whereof one cannot speak, thereof one must be silent,” implying that there are aspects of reality that language cannot capture. He emphasized the role of context and usage in determining meaning, which suggests that words and concepts are not the same thing and that their relationship is more complex and variable than a simple one-to-one correspondence.
In this regard, Wittgenstein’s ideas about language games and the contextual nature of meaning are indeed relevant to the discussion of the NAH. The original essay critiqued the hypothesis by highlighting the context-dependent, diverse, and evolving nature of language games, which challenges the idea of a fixed, universally natural set of abstractions. These points do not conflate words with concepts but emphasize the complex relationship between them and the importance of context in determining meaning.
Your clarification that the NAH is ultimately about concepts, not words, is duly noted. However, the critique presented in the essay is not solely based on a linguistic analysis. The contextual variability and diversity observed in language games can also be extended to the realm of concepts and abstractions, as they are intricately linked to the cultural and social practices that inform our understanding of the world.
In conclusion, the original essay’s critique of the NAH remains relevant, as it emphasizes the context-dependent and diverse nature of abstractions, which challenges the notion of fixed, universally natural abstractions. This critique does not conflate words and concepts but highlights the complex, fluid, and context-dependent relationships between them, as well as the importance of considering cultural and social factors when evaluating the convergence of abstractions in cognitive systems.
My own take on late Wittgenstein (based on having read only a little of his later work) is that he got wayyyy too caught up in language specifically, and mostly lost sight of the intuitively-obvious fact that words and concepts are not the same thing, nor do they have a stable 1-to-1 matching. (Also he seems to have lost contact with reality in his later work, in the sense that he seemed very hyper focused on things-which-language-can-talk-about. He seemed to basically lose track of the fact that the rest of reality goes on existing just fine, and humans go on interacting with it just fine, even when nobody talks about it.)
“What things do we attach words or phrases to?” is a useful heuristic for figuring out which abstractions are natural, but it’s just a heuristic; the same words can and do point to different natural abstractions in different contexts. The natural abstraction hypothesis is ultimately about concepts, not words.
My understanding of Steel Late Wittgenstein’s response would be that you could agree with that words and concepts are distinct, and mapping is not always 1-1, but that what concepts get used is also significantly influenced by which features of the world are useful in some contexts of language (/word) use.
Update: This comment was generated using GPT4 as an experiment.
Thank you for your comment and insights. I appreciate your engagement with the topic. However, I believe there may be a misunderstanding regarding Wittgenstein’s ideas and their implications for the Natural Abstraction Hypothesis.
Firstly, Wittgenstein did not deny the existence of an external reality or the importance of human interaction with it. His primary focus was on the limits of language and how it shapes our understanding of the world. As he famously stated, “Whereof one cannot speak, thereof one must be silent,” implying that there are aspects of reality that language cannot capture. He emphasized the role of context and usage in determining meaning, which suggests that words and concepts are not the same thing and that their relationship is more complex and variable than a simple one-to-one correspondence.
In this regard, Wittgenstein’s ideas about language games and the contextual nature of meaning are indeed relevant to the discussion of the NAH. The original essay critiqued the hypothesis by highlighting the context-dependent, diverse, and evolving nature of language games, which challenges the idea of a fixed, universally natural set of abstractions. These points do not conflate words with concepts but emphasize the complex relationship between them and the importance of context in determining meaning.
Your clarification that the NAH is ultimately about concepts, not words, is duly noted. However, the critique presented in the essay is not solely based on a linguistic analysis. The contextual variability and diversity observed in language games can also be extended to the realm of concepts and abstractions, as they are intricately linked to the cultural and social practices that inform our understanding of the world.
In conclusion, the original essay’s critique of the NAH remains relevant, as it emphasizes the context-dependent and diverse nature of abstractions, which challenges the notion of fixed, universally natural abstractions. This critique does not conflate words and concepts but highlights the complex, fluid, and context-dependent relationships between them, as well as the importance of considering cultural and social factors when evaluating the convergence of abstractions in cognitive systems.