# Today ## enrico's comments I wonder whether we should look for a specific scientific discipline (semiotic physics vs mechaniastic interpetability) or just try to characterize the relevant knowledge required to carry out order appreciation for LLMs regardless of the label and the disciplinary framing. The key for me is this passage of the old (PPR-submitted) version: >Despite their different framings – Janus's simulator ontology and Picca's Peircean semiotics – these accounts share a core insight: we should attend to what regularities govern how text propagates through the system, not to whether LLMs think or intend. In a similar vein, Wolfram (2023) states that inside ChatGPT any piece of text is effectively represented by an array of numbers that we can think of as coordinates of a point in some kind of ‘linguistic feature space’. So when ChatGPT continues a piece of text this corresponds to tracing out a trajectory in linguistic feature space. But now we can ask what makes this trajectory correspond to text we consider meaningful. And might there perhaps be some kind of ‘semantic laws of motion’. From Wolfram’s perspective, semiotic physics thus would have three main objects to investigate: (i) the “linguistic feature space” in which words and other linguistic items have their place; (ii) the “trajectories” that can be traced out in this space to continue a piece of text; and (iii) the “semantic laws of motion” that determine such trajectories. > >We draw on this literature but develop it in a specific direction. Our aim is to show how semiotic physics can serve as the "right kind of knowledge" for aesthetic appreciation of LLMs in Carlson's sense: the knowledge that makes order visible and intelligible, and that guides acts of aspection. The connection to environmental aesthetics, and the claim that semiotic physics can play the role for LLMs that geology plays for landscapes, is our contribution. We also articulate the 'forces' of semiotic physics at the level of textual effects rather than at the level of mechanistic detail. The existing literature tends to discuss semiotic physics in terms of probability distributions, embedding spaces, and dynamical systems. These descriptions are accurate, but they do not directly connect to what readers can perceive in generated text. Our articulation of the forces operates at a level that does connect to perceivable features. > >What does semiotic physics track? The regularities it describes manifest as perceivable features of generated text. Consider vocabulary clustering: words do not appear independently but make other related words more probable, so that once a medical term appears, other medical terms become more likely to follow. Or consider coherence dynamics: the model threads material from earlier in an exchange through later responses, or fails to, and a reader can attend to how far this threading extends and where it breaks down. There is also what might be called register stability: once the model enters a mode – expository, creative, reasoning – it tends to remain there until something disturbs it. And there are the marks of post-training: hedging expressions, step-by-step organisation, preemptive qualifications, which are the shapes that reinforcement learning has made more probable. What matters for present purposes is the level of description: semiotic physics operates at a level that connects to perceivable features of language, features that competent readers can attend to without specialist tools but that become salient and intelligible when understood as products of a text-trained statistical system. According to Wolfram (2023), LLMs reveal that "human language (and the patterns of thinking behind it) are somehow simpler and more ‘law like’ in their structure than we thought. ChatGPT has implicitly discovered it. But we can potentially explicitly expose it". Semiotic physics pursues such an exposition by investigating the forces that govern the artificial production of texts. Perhaps we don't even need to call all this "semiotic physics", we can just say that this is the relevant knowledge for order appreciation of LLMs This passage of our old version also seems very important: "The aspection guided by semiotic physics is, in a sense, aspection of language itself – of the textual order produced by semiotic forces. We are not attending to mechanical internals – activation patterns, attention weights, circuit-level features – since these require specialist tools and are not accessible to readers. We are attending to the textual manifestation of semiotic order: how vocabulary clusters, how coherence is maintained or lost across an exchange, how register persists or shifts, how post-training shapes response structure. These are features of the language itself, perceivable by competent readers. Competent readers already have tacit knowledge of how language works: syntactic, semantic, pragmatic, and discourse-level knowledge built up through immersion in spoken and written language. They perceive patterns in LLM outputs using this tacit knowledge. Semiotic physics adds explicit articulation of these patterns and a causal story about their source in training. The competent reader senses that different models have different 'vibes'; semiotic physics—knowledge of how meaning clusters, how register persists, how training shapes the texture of response—explains what produces those vibes and makes them available for sustained attention." The whole section 5.2 (Practical Acquaintance) also is very important because it makes order appreication of LLMs intelligible, it avoids that the relevant sort of knowledge (semiotic physics") remained mysterious. (Do you know the Italian expression "Buttare via il bambino con l'acqua sporca"?) This passage (end of 6.3) also seems to say something very important that we should not downplay and probably discuss earleier, when talking about the relevant knowldege for order appreciaiton of LLMs: "Each model, as an instantiation of semiotic physics, has learned regularities from human text. It reflects, in transformed form, the semiotic culture of its training data. There is a sense in which generative AI is a mirror of culture, not only morally, as Vallor (2024) has argued, but aesthetically. The model shows us our own semiotic patterns, filtered through statistical learning. Appreciating an LLM is, in part, appreciating culture seen through technology." To wrap up, the set-up should something along this lines: We have the aesthetics of design (Carlson and Parsons, Forsey), let's try to apply it to LLMs. It doesn't work because of Olah's point. Let's try first to supplement it with person aesthetics. It's a bit better, but not satisfying yet, it still misses something crucial. We need environmantal aesthetics to miss the gap between design (captued by design aesthetics) and function (somwhow partlally captured by person aesthetics). And we need to higlight the relevant knowledge for order appreciation of such environments. *fill the gap "But the thing that we actually create, it's *this almost biological entity or organism* that we're studying'. (Olah 2024)" We shouls stress that "almost biological entity" might be interpreted in two ways: person and environent. The person-interpretation only capures something about the function (with due qualifications), whereas the environment-interpretation capture the core features that fill the gap between design and personish functioning. I wonder whether we should look for a specific scientific discipline (semiotic physics vs mechaniastic interpetability) or just try to characterize the relevant knowledge required to carry out order appreciation for LLMs regardless of the label and the disciplinary framing. The key for me is this passage of the old (PPR-submitted) version: Despite their different framings – Janus's simulator ontology and Picca's Peircean semiotics – these accounts share a core insight: we should attend to what regularities govern how text propagates through the system, not to whether LLMs think or intend. In a similar vein, Wolfram (2023) states that inside ChatGPT any piece of text is effectively represented by an array of numbers that we can think of as coordinates of a point in some kind of ‘linguistic feature space’. So when ChatGPT continues a piece of text this corresponds to tracing out a trajectory in linguistic feature space. But now we can ask what makes this trajectory correspond to text we consider meaningful. And might there perhaps be some kind of ‘semantic laws of motion’. From Wolfram’s perspective, semiotic physics thus would have three main objects to investigate: (i) the “linguistic feature space” in which words and other linguistic items have their place; (ii) the “trajectories” that can be traced out in this space to continue a piece of text; and (iii) the “semantic laws of motion” that determine such trajectories. We draw on this literature but develop it in a specific direction. Our aim is to show how semiotic physics can serve as the "right kind of knowledge" for aesthetic appreciation of LLMs in Carlson's sense: the knowledge that makes order visible and intelligible, and that guides acts of aspection. The connection to environmental aesthetics, and the claim that semiotic physics can play the role for LLMs that geology plays for landscapes, is our contribution. We also articulate the 'forces' of semiotic physics at the level of textual effects rather than at the level of mechanistic detail. The existing literature tends to discuss semiotic physics in terms of probability distributions, embedding spaces, and dynamical systems. These descriptions are accurate, but they do not directly connect to what readers can perceive in generated text. Our articulation of the forces operates at a level that does connect to perceivable features. What does semiotic physics track? The regularities it describes manifest as perceivable features of generated text. Consider vocabulary clustering: words do not appear independently but make other related words more probable, so that once a medical term appears, other medical terms become more likely to follow. Or consider coherence dynamics: the model threads material from earlier in an exchange through later responses, or fails to, and a reader can attend to how far this threading extends and where it breaks down. There is also what might be called register stability: once the model enters a mode – expository, creative, reasoning – it tends to remain there until something disturbs it. And there are the marks of post-training: hedging expressions, step-by-step organisation, preemptive qualifications, which are the shapes that reinforcement learning has made more probable. What matters for present purposes is the level of description: semiotic physics operates at a level that connects to perceivable features of language, features that competent readers can attend to without specialist tools but that become salient and intelligible when understood as products of a text-trained statistical system. According to Wolfram (2023), LLMs reveal that "human language (and the patterns of thinking behind it) are somehow simpler and more ‘law like’ in their structure than we thought. ChatGPT has implicitly discovered it. But we can potentially explicitly expose it". Semiotic physics pursues such an exposition by investigating the forces that govern the artificial production of texts. Perhaps we don't even need to call all this "semiotic physics", we can just say that this is the relevant knowledge for order appreciation of LLMs This passage of our old version also seems very important: --- --- # Actions ---