Generally I feel like I'm pretty good at understanding concepts.<p>But after reading this Wikipedia page and then Googling it and then reading MollyRealized's ChatGPT explanation in a sibling comment...<p>...I have utterly no idea what the heck this is supposed to be.<p>If this is about using nonsense to explain something in philosophy, that seems awfully silly.<p>If this is about how e.g. high school students need simplified versions of how an electron works (a point) before college students learn the reality (a cloud), then it seems banal.<p>If this is about achieving mystical realizations along the lines of zen koans, then OK but what has that got to do with Wittgenstein? And it seems like a Wikipedia article ought to mention this.<p>So I'm baffled. I think I need a ladder to help me understand this ladder? And understand why this was submitted to HN in the first place?
<i>This Is Just To Say</i><p><pre><code> I have kicked away
the ladder
which transcends
these propositions
and which
you were probably
climbing
to see the world aright
Forgive me
whereof one cannot speak
one must pass over
in silence.</code></pre>
ME: Pretend I am a five-year-old. Can you explain Wittgenstein's ladder?<p>CHATGPT: Sure! Wittgenstein's ladder is a metaphor used by philosopher Ludwig Wittgenstein to explain how language and ideas work.<p>Imagine you want to get to the top of a tree. At first, you might use a ladder to climb up. But once you get to the top, you don't need the ladder anymore. You can throw it away or leave it behind.<p>In the same way, Wittgenstein argued that language is like a ladder. It's a tool we use to get to a certain point, but once we've reached that point, we don't need the language anymore. We can throw it away or leave it behind.<p>For example, imagine you're learning to count. You might use your fingers to help you count to five. But once you've learned how to count to five, you don't need to use your fingers anymore. You can count to ten, twenty, or even a hundred without needing to use your fingers.<p>Wittgenstein's ladder is a reminder that language is a tool we use to reach a certain goal, but it's not the goal itself. Once we've reached the goal, we don't need the language anymore.<p>ME: Why is this concept useful? Don't we always need language, simply to communicate with those around us?<p>CHATGPT: You're right that language is essential for communication, but Wittgenstein's ladder is more about the nature of language and how we use it to think and talk about the world around us.<p>The ladder metaphor is useful because it highlights the idea that language is not fixed and unchanging. Rather, it's a flexible tool that we can use in different ways to achieve different goals. Sometimes, we need to use language in a precise, technical way to communicate complex ideas, while other times we might use language more loosely and creatively to express our emotions or share stories.<p>Wittgenstein's ladder can also help us recognize when we're using language in a way that's no longer serving its original purpose. For example, if we're using technical jargon to communicate with someone who doesn't understand it, we might be climbing up the wrong ladder. We might need to switch to a different ladder (i.e., a different way of using language) that's more accessible and useful for the person we're communicating with.<p>Ultimately, the concept of Wittgenstein's ladder reminds us that language is a tool we can use in different ways to achieve different goals. By being aware of how we're using language and why, we can become more effective communicators and thinkers.
This reminds me of the Buddha's comparison of the Dhamma to a raft, which one does not carry around on his or her back after crossing over on it.<p><a href="https://www.accesstoinsight.org/tipitaka/mn/mn.022.than.html" rel="nofollow">https://www.accesstoinsight.org/tipitaka/mn/mn.022.than.html</a>
I'm intuitively suspicious that what people call Theory today begins with "all map, no territory," and results in, "maps all the way down."<p>This seems similar to a ladder of physical competence, but applied to philosophical reasoning. It's not clear to me that there is a <i>there</i> there outside of math, physics, (and increasingly computation) where you have to physically practice the calculations to arrive at the conclusions, whereas I don't think philosophy has an analogous objective competence. Ironically, some mysticisms like meditation (and perhaps even prayer) may even have a higher bar because they are a physically transformative competence akin to practicing music, whereas attaching yourself to an academic and fundamentally political consensus doesn't have the same honest signals or investment.
My interpretation is that the words written down are just pointers or triggers to other thoughts, ideas, and interpretations. The words themselves (the ladder) can be thrown away and it is no longer important to know how you got to your current state of mind.<p>I’m not completely in agreement with this philosophy if indeed my interpretation holds water.<p>A related concept to this interpretation is Eno’s oblique strategies deck or random word decks.
I've heard professors preface generalisation or metaphors with, "What I'm about to say isn't exactly true but it should be helpful in apprehending the central concept."<p>Basically to include extensive caveats and exceptions in the first explanation is to risk overwhelming the novice.<p>I think that's what this is. Sort of just moving from a high level understanding to a lower level one. Is there more to it?
For those that are uninitiated, Wittgenstein's Ladder is essentially the conclusion of his extreme logical positivist view of language specifically, but reality more generally; it's kind of far out, so we don't really have a term for it, but it's probably something like "materialist positivism" or "logical realism†." It's <i>extremely</i> fringe and essentially does away with all metaphysics, which is very problematic because we have a lot of metaphysical problems in philosophy. Even if we ignore the more "pedestrian" moral quandaries, we'll quickly need to deal with things like the metaphysics of causation[1] or modality[2].<p>Full disclosure, I'm not a fan of Wittgenstein at <i>all</i> (I wish he were less studied in universities), and I think his Tractatus is nonsense (though not because I'm climbing his ladder) and an abject failure.<p>† Which is a real thing, but I'm not sure if it's completely correct to use here.<p>[1] <a href="https://plato.stanford.edu/entries/causation-metaphysics/" rel="nofollow">https://plato.stanford.edu/entries/causation-metaphysics/</a><p>[2] <a href="https://plato.stanford.edu/entries/logic-modal/" rel="nofollow">https://plato.stanford.edu/entries/logic-modal/</a>
To understand modern LLMs we all should study more Wittgenstein.<p>I have been contemplating the use theory of meaning recently, and it’s direct implications for generative language models.