6 votes

We're all Wittgensteinians now

2 comments

  1. lou
    (edited )
    Link
    Asked by me, answered by openai. What are rigid designators (also by openai), version 1 What are rigid designators (also by openai), version 2 The idea that language has a thing of its own, free...

    Asked by me, answered by openai.

    How could Ludwig Wittgenstein explain, in his terms, the concept of "rigid designators" as defined by Saul Kripke?

    Ludwig Wittgenstein did not use the concept of "rigid designators" in his philosophy, as it was developed by Saul Kripke many years after Wittgenstein's death. However, Wittgenstein did have his own views on language and meaning that are relevant to the topic.

    In Wittgenstein's view, the meaning of a word is determined by its use in a particular context or language game. The meaning of a word is not fixed, but rather depends on the specific practices and conventions of the linguistic community in which it is used. For example, the word "water" means something different in English than it does in French or Chinese, because it is used in different contexts and conventions in each language.

    Wittgenstein also emphasized the importance of family resemblance in language. He argued that concepts and categories are not defined by a set of necessary and sufficient conditions, but rather by a network of overlapping similarities and differences. This means that there is often no clear-cut boundary between things that belong to a particular category and those that do not, but rather a range of similarities and differences that can vary depending on context.

    While Wittgenstein did not use the term "rigid designators," his views on language and meaning suggest that he might have been skeptical of the idea of terms that refer to the same thing in all possible worlds. He might have argued that the meaning of a word depends on its use in a particular context, and that the idea of a term that refers to the same thing in all possible worlds is a philosophical abstraction that does not correspond to the way language is actually used in practice.

    What are rigid designators (also by openai), version 1

    What are "rigid designators", as defined by philosopher Saul Kripke? Can you provide a few examples?

    Rigid designators are terms that refer to the same object or individual in every possible world. According to philosopher Saul Kripke, rigid designators are essential to understanding the nature of reference and meaning in language.

    For example, the name "Barack Obama" is a rigid designator because it refers to the same person in all possible worlds. Even if he had never become president or had a different career path, the name "Barack Obama" would still refer to the same individual.

    Another example of a rigid designator is the chemical formula for water, "H2O". This term refers to the same substance in every possible world, and if the formula were different, the substance would not be water.

    In contrast, non-rigid designators refer to individuals or objects based on their properties or descriptions, which can vary from world to world. For example, the phrase "the tallest person in the room" is a non-rigid designator because the individual referred to can vary depending on the context and who is in the room.

    What are rigid designators (also by openai), version 2

    What are "rigid designators", as defined by philosopher Saul Krikpe? Can you provide a few examples, and express it logically as well?

    Sure! Rigid designators are terms that designate the same object or individual in all possible worlds. In other words, if a term is a rigid designator, then it refers to the same object or individual no matter what the circumstances are.

    Here's the logical expression for this concept:

    For a term 'T' to be a rigid designator of an object 'x', it must hold that:

     If 'T' designates 'x' in some possible world, then 'T' designates 'x' in all possible worlds.
     If 'T' designates 'y' in some possible world, then 'y' is not identical to 'x'.
    

    Here are some examples:

    The name "Barack Obama" is a rigid designator because it refers to the same person in all possible worlds. Therefore, if 'Barack Obama' designates Barack Obama in one possible world, it designates Barack Obama in all possible worlds.

    The number "2" is a rigid designator because it refers to the same number in all possible worlds. Therefore, if '2' designates the number 2 in one possible world, it designates the number 2 in all possible worlds.

    The chemical formula for water, "H2O", is a rigid designator because it refers to the same substance in all possible worlds. Therefore, if 'H2O' designates water in one possible world, it designates water in all possible worlds.

    In contrast, non-rigid designators refer to individuals or objects based on their properties or descriptions, which can vary from world to world. For example, the phrase "the tallest person in the room" is a non-rigid designator because the individual referred to can vary depending on the context and who is in the room.


    The idea that language has a thing of its own, free from the objects it references, was explored and abused by some post-structuralists and deconstructionists that, ultimately, believed that the mere notion of something that is true by its own virtues is bias and a historical mistake. It makes sense for something which has no spiritual[1] life to go down the same rabbit hole. It makes sense for something which has no mind to glorify the very thing it manipulates - language! Wittgenstein wouldn't really agree with that -- even a game must be played, and he was more concerned with refining philosophical discourse than rejecting externalism. But the French deconstructionists would go even further in their version of post-truth.

    In any case, because even the strongest materialist and the most ardent skeptic operates under the ontological license that their own mind[2] exists, we are naturally attracted to the notion that some designators must be rigid -- at the very least, our own! Artificial intelligences are not under such epistemic constraint (or, if you wanna invert, they have the constraint of no-mind). Additionally, the idea that things have truth conditions that are not dictated by language is incredibly useful to numerous human endeavors, markedly science and engineering.


    [1] And here I'm not talking about spirituality, but rather the metaphysics of the mind that most humans believe in because not doing so would lead them to doubt the relevance of their own existences...
    [2] Not to be confused with the brain.


    EDIT: added a bunch of stuff.

    2 votes
  2. skybrian
    Link
    From the article: [..] [...]

    From the article:

    Biological brains differ in important ways from artificial neural networks, but the fact that the latter can emulate the capacities of the former really does contribute to human self-understanding. For one, it represents an independent line of evidence that the brain is indeed computational. But that’s just the tip of the iceberg. The success of LLMs may even help settle longstanding debates on the nature of meaning itself.

    [..]

    The tendency for reference theories of meaning to teeter on a knife edge between skepticism and Platonism eventually led philosophers to take a different tack. This included Wittgenstein, who realized the impossibility of the positivist project later in life. His posthumous book, Philosophical Investigations, thus presented a “use” theory of meaning in its stead.

    In a use theory of meaning, the pragmatics of speech come prior to the semantics. Words and propositions have meaning insofar as they do something. For Wittgenstein, this meant making a valid move in a language game; a game which arises within the holistic context of other language users and their social practices.

    In turn, rather than treat words as the atomic objects of meaning, meaning more typically resides in full sentences.

    [...]

    On this account, the meaning of a sentence isn’t built up from its constituent parts, but rather the meaning of words is inferred down from the use and context of entire sentences. This is why, when learning a new word, we often ask for it to be used in a sentence, and can even make perfectly appropriate use of words that we struggle to define when put on the spot. Common linguistic errors, such as saying “for all intensive purposes” rather than “for all intents and purposes,” arise for similar reasons: we grok the meaning of a phrase from its use, not from the meaning of the discrete words and the rules for combining them.

    I see the success of LLMs as vindicating the use theory of meaning [...]