## New highlights added April 7, 2025 at 10:14 AM > In science, mechanistic explanations aim to reveal the causal structure underlying a phenomenon of interest by describing the organized entities and activities that are responsible for producing or maintaining that phenomenon (Machamer et al. [2000](https://arxiv.org/html/2405.03207v1#bib.bib84)). More precisely, a mechanistic explanation identifies the component parts of a mechanism, characterized by their properties and capacities, the causal interactions between these component parts, and the organization of the parts and activities such that they give rise to the phenomenon. Such explanations stand in contrast to purely descriptive or phenomenological models that simply re-describe the phenomenon itself, as well as covering-law explanations that explain by subsuming the phenomenon under empirically discovered regularities or governing laws. Mechanisms explain by revealing how the phenomenon arises from the causal structure of the system, not merely describing empirical regularities in which it partakes. As such, mechanistic explanations reveal opportunities for manipulation and control over the phenomenon in a way that descriptive or law-based explanations do not. ([View Highlight](https://read.readwise.io/read/01jr7jdvkxmsjpst2rzcfjegbk)) - Tags: [[ai aesthetics paper]] > Understanding the behavior of a simple system like a mechanical clock is easy enough – one can simply open it up and observe the mechanism at work. This is not so straightforward with more complex systems, like the weather, the brain, or artificial neural networks. Neural networks are often described as ‘black boxes’ precisely because the causal mechanisms that explain their behavior seem opaque to scrutiny. As we emphasized in Part I (Millière & Buckner [2024](https://arxiv.org/html/2405.03207v1#bib.bib96)), simply staring at the learning objective, architecture, or parameters of LLMs will reveal neither how they exhibit their remarkable performance on challenging tasks, nor what functional capacities can be meaningfully ascribed to them. In principle, one could even provide a complete mathematical description of an LLM as a giant composite function, consisting in an absurdly complex sequence of linear and nonlinear transformations across many layers; but such a description, on its own, would be useless to provide a genuine explanation of the network’s behavior in specific contexts. The ‘black box’ metaphor underscores this chasm: it highlights the difficulty to trace precise causal pathways in the network through which specific inputs are transformed into specific outputs. This is why merely re-describing what an LLM does in terms of next-token prediction or matrix multiplication – what we called the ‘Re-description Fallacy’ in Part I – cannot possibly settle philosophical debates that are fundamentally about causal mechanisms. ([View Highlight](https://read.readwise.io/read/01jr7jk670120ftnf1thkbjg5y)) - Tags: [[ai aesthetics paper]] - Note: reminds me of the example from Schellekens. > The search for causal mechanisms has become central across the life sciences and cognitive science. Like their artificial counterparts, biological neural networks are ‘black boxes’; yet neuroscientists are engaged in the project of uncovering multilevel mechanisms underlying psychological capacities and nervous system functions (Craver [2007](https://arxiv.org/html/2405.03207v1#bib.bib31)). At the molecular and cellular levels, they describe mechanisms of protein synthesis, gene expression, and synaptic transmission; at an intermediate level are mechanisms of neuron spiking and oscillation as well as mechanisms of development and synaptic plasticity; at higher levels are mechanisms underlying learning, memory, reasoning, and other psychological capacities. ([View Highlight](https://read.readwise.io/read/01jr7jh665w23ps590v3xs2e0v)) - Tags: [[ai aesthetics paper]]