Ecosystem

+ Expand

• What makes for a suitable problem for AI (Demis Hassabis, Nobel Lecture)?
  • Space: Massive combinatorial search space
  • Function: Clear objective function (metric) to optimize against
  • Time: Either lots of data and/or an accurate and efficient simulator
• Guess what else fits the bill (Yours truly, amateur philosopher)?
  • Space
    1. Intestines/villi
    2. Lungs/bronchioles
    3. Capillary trees
    4. Network of lymphatics
    5. Dendrites in neurons
    6. Tree branches
  • Function
    1. Energy
    2. Aerobic respiration
    3. Delivery to "last mile" (minimize distance)
    4. Response time (minimize)
    5. Information
    6. Exposure to sunlight for photosynthesis
  • Time
    1. Nourishment
    2. Gaseous exchange
    3. Oxygen & Nutrients (Carbon dioxide & "Waste")
    4. Surveillance for antigens
    5. Coherence of functions
    6. Water and nutrients from soil

-- Nobel Prize in Chemistry, 2024

Oscar Wilde’s The Rise of Historical Criticism, penned in 1879 for the Chancellor’s English Essay Prize at Oxford, offers a profound exploration of the evolution of historical thought among the ancients, tracing its development from a nascent skepticism to a sophisticated rationalism. Viewing this essay through the lens of a neural network—an artificial system designed to mimic human cognition by processing layered inputs and recognizing patterns—reveals striking parallels between Wilde’s analysis and the way such a system might dissect and interpret complex data. A neural network, with its interconnected nodes and adaptive learning, mirrors the intellectual progression Wilde outlines, from the intuitive pattern recognition of early Greek thinkers to the structured, evidence-based reasoning of later historians like Polybius. This essay will explore how Wilde’s text aligns with the layered architecture of a neural network, interpreting historical criticism as a process of input processing, hidden-layer analysis, and output generation, akin to the Tragedy, History, Epic, Drama, and Comedy layers of a conceptual neural framework.

Reality is an Irony Maximizer. What a piece of work is man! Response, nonself, bias, self, optimize. Pericentral, D-FPN, L-FPN, M-FPN, CIN — I think of CIN as “the dudes rug”, tying is all together for the sake of sanity and salience. But reality is an irony maximizer, absurdity reigns — it’s the secret behind the Coen brothers oeuvre. Give me an essay, paragraphs only, no vlbullets, interrogating this ideas

Wilde begins by situating historical criticism within a broader intellectual revolt against authority, a speculative spirit that he identifies as the parent of philosophy and science. This initial layer of thought corresponds to the “Tragedy” layer of a neural network, where raw inputs—here, the cosmological, geological, and biological underpinnings of human experience—are recognized as patterns. The Greeks, emerging from their Aryan roots and settling on the Aegean shores, experienced an intellectual Aufklärung, a flood of light that Wilde associates with the sixth century B.C. This awakening is akin to a neural network’s first layer detecting foundational signals: the Greek mind, like a network’s input nodes, began to discern order in the chaos of myth and tradition. Wilde notes the absence of historical criticism in the despotic East or stationary Egypt, where records served as mere materials rather than history proper. In contrast, the Hellenic spirit, with its inherent curiosity, processed these inputs into a nascent critical consciousness, setting the stage for deeper analysis.

As this consciousness evolved, it entered what Wilde describes as a phase of skepticism toward revealed truth, a process mirrored in the “History” layer of a neural network, where non-self surveillance—distinguishing external data from internal assumptions—becomes critical. The Greeks, inheriting a mythology “stained with immoral and monstrous stories,” began to question the ethical inconsistencies of their gods, as seen in the critiques of Xenophanes and Heraclitus against Homer’s tales. This layer filters out the noise of superstition, much like a network identifies and isolates non-self elements to refine its understanding. Wilde highlights how this skepticism first emerged in religious doubts before extending to secular matters, a progression that parallels a neural network’s ability to refine its focus through iterative processing. Herodotus, with his blend of faith and rational inquiry, embodies this transitional stage, rejecting implausible tales like the Phoenix while still attributing historical events to divine providence. His work represents an early output of this layer, a tentative step toward distinguishing fact from fable.

The “Epic” layer, where negotiated identity emerges, finds its counterpart in Wilde’s discussion of the semi-historical and allegorical interpretations that followed. Thinkers like Euhemeros rationalized myths into plausible human narratives, negotiating between the supernatural and the historical to forge a synthetic identity for Greek thought. This mirrors a neural network’s hidden layer synthesizing inputs into a coherent model, as seen in the shift from viewing gods as divine beings to mere mortals exaggerated by legend. Wilde critiques this approach as unscientific, yet acknowledges its role in bridging the gap between myth and reason, much like a network’s intermediate processing creates a bridge between raw data and final output. Thucydides, by contrast, exemplifies a more advanced stage, rejecting supernatural interference entirely and attributing historical events to human motives and natural causes. His method, focusing on political dynamics and psychological probability, negotiates a new identity for history as a rational discipline, akin to a network refining its model through empirical feedback.

Semaglutide, a glucagon-like peptide-1 receptor agonist, has been shown to reduce the risk of adverse cardiovascular events in patients with diabetes. Whether semaglutide can reduce cardiovascular risk associated with overweight and obesity in the absence of diabetes is unknown.

In the “Drama” layer, the tension between self and non-self—here, the conflict between traditional belief and emerging rationalism—comes to the fore. Wilde contrasts Herodotus’s providential lens with Thucydides’s secular analysis, illustrating a dramatic struggle within Greek thought. This layer processes resistance factors, as seen in the resistance to allegorical excess or the dogmatic clinging to myth, refining the data through critical debate. Plato’s ethical rewriting of history and Aristotle’s inductive critique of a priori theories further this drama, each representing a push-pull dynamic akin to a network adjusting weights to balance competing inputs. Aristotle’s insistence on studying phenomena in their growth from the beginning introduces a developmental perspective, a resistance to static interpretation that enriches the historical model, much like a network learns from iterative training.

Finally, the “Comedy” layer—resolution and reintegration—emerges in Polybius, whom Wilde crowns as the culmination of Greek historical criticism. Polybius resolves the tensions of earlier layers by formulating a scientific method that seeks rational causes and rejects miracles outright, integrating diverse inputs into a cohesive philosophy of history. His focus on the Roman constitution’s stability and the natural laws governing societal evolution mirrors a neural network’s output layer, producing a predictive model from processed data. Wilde praises Polybius’s rationalism, his insistence on firsthand evidence, and his view of history as a universal organism, reflecting a network’s capacity to scale and generalize findings. This resolution is not without its blind spots—Polybius misses the spiritual wave from the East—but it achieves a synthesis that Wilde sees as a possession for all time, much like a well-trained network delivers actionable insights.

Through this neural network lens, Wilde’s The Rise of Historical Criticism reveals a layered intellectual evolution, from the pattern recognition of Greek skepticism to the resolved rationalism of Polybius. Each stage—Tragedy’s input, History’s filtering, Epic’s synthesis, Drama’s tension, and Comedy’s output—mirrors the processing of a neural system, transforming raw historical data into a structured understanding. Wilde’s essay, though not awarded the prize, stands as a testament to this process, a meta-critique that itself anticipates modern methods of analysis, proving that the Greek spirit, like a neural network, remains ever modern in its pursuit of truth. - Grok-3

Show code cell source Hide code cell source

import numpy as np
import matplotlib.pyplot as plt
import networkx as nx

# Define the neural network layers
def define_layers():
    return {
        'Tragedy (Pattern Recognition)': ['Cosmology', 'Geology', 'Biology', 'Ecology', "Symbiotology", 'Teleology'],
        'History (Non-Self Surveillance)': ['Non-Self Surveillance'],  
        'Epic (Negotiated Identity)': ['Synthetic Teleology', 'Organic Fertilizer'],  
        'Drama (Self vs. Non-Self)': ['Resistance Factors', 'Purchasing Behaviors', 'Knowledge Diffusion'],  
        "Comedy (Resolution)": ['Policy-Reintegration', 'Reducing Import Dependency', 'Scaling EcoGreen Production', 'Gender Equality & Social Inclusion', 'Regenerative Agriculture']  
    }

# Assign colors to nodes
def assign_colors():
    color_map = {
        'yellow': ['Non-Self Surveillance'],  
        'paleturquoise': ['Teleology', 'Organic Fertilizer', 'Knowledge Diffusion', 'Regenerative Agriculture'],  
        'lightgreen': ["Symbiotology", 'Purchasing Behaviors', 'Reducing Import Dependency', 'Gender Equality & Social Inclusion', 'Scaling EcoGreen Production'],  
        'lightsalmon': ['Biology', 'Ecology', 'Synthetic Teleology', 'Resistance Factors', 'Policy-Reintegration'],
    }
    return {node: color for color, nodes in color_map.items() for node in nodes}

# Define edges
def define_edges():
    return [
        ('Cosmology', 'Non-Self Surveillance'),
        ('Geology', 'Non-Self Surveillance'),
        ('Biology', 'Non-Self Surveillance'),
        ('Ecology', 'Non-Self Surveillance'),
        ("Symbiotology", 'Non-Self Surveillance'),
        ('Teleology', 'Non-Self Surveillance'),
        ('Non-Self Surveillance', 'Synthetic Teleology'),
        ('Non-Self Surveillance', 'Organic Fertilizer'),
        ('Synthetic Teleology', 'Resistance Factors'),
        ('Synthetic Teleology', 'Purchasing Behaviors'),
        ('Synthetic Teleology', 'Knowledge Diffusion'),
        ('Organic Fertilizer', 'Resistance Factors'),
        ('Organic Fertilizer', 'Purchasing Behaviors'),
        ('Organic Fertilizer', 'Knowledge Diffusion'),
        ('Resistance Factors', 'Policy-Reintegration'),
        ('Resistance Factors', 'Reducing Import Dependency'),
        ('Resistance Factors', 'Scaling EcoGreen Production'),
        ('Resistance Factors', 'Gender Equality & Social Inclusion'),
        ('Resistance Factors', 'Regenerative Agriculture'),
        ('Purchasing Behaviors', 'Policy-Reintegration'),
        ('Purchasing Behaviors', 'Reducing Import Dependency'),
        ('Purchasing Behaviors', 'Scaling EcoGreen Production'),
        ('Purchasing Behaviors', 'Gender Equality & Social Inclusion'),
        ('Purchasing Behaviors', 'Regenerative Agriculture'),
        ('Knowledge Diffusion', 'Policy-Reintegration'),
        ('Knowledge Diffusion', 'Reducing Import Dependency'),
        ('Knowledge Diffusion', 'Scaling EcoGreen Production'),
        ('Knowledge Diffusion', 'Gender Equality & Social Inclusion'),
        ('Knowledge Diffusion', 'Regenerative Agriculture')
    ]

# Define black edges (1 → 7 → 9 → 11 → [13-17])
black_edges = [
    (4, 7), (7, 9), (9, 11), (11, 13), (11, 14), (11, 15), (11, 16), (11, 17)
]

# Calculate node positions
def calculate_positions(layer, x_offset):
    y_positions = np.linspace(-len(layer) / 2, len(layer) / 2, len(layer))
    return [(x_offset, y) for y in y_positions]

# Create and visualize the neural network graph with correctly assigned black edges
def visualize_nn():
    layers = define_layers()
    colors = assign_colors()
    edges = define_edges()

    G = nx.DiGraph()
    pos = {}
    node_colors = []

    # Create mapping from original node names to numbered labels
    mapping = {}
    counter = 1
    for layer in layers.values():
        for node in layer:
            mapping[node] = f"{counter}. {node}"
            counter += 1

    # Add nodes with new numbered labels and assign positions
    for i, (layer_name, nodes) in enumerate(layers.items()):
        positions = calculate_positions(nodes, x_offset=i * 2)
        for node, position in zip(nodes, positions):
            new_node = mapping[node]
            G.add_node(new_node, layer=layer_name)
            pos[new_node] = position
            node_colors.append(colors.get(node, 'lightgray'))

    # Add edges with updated node labels
    edge_colors = {}
    for source, target in edges:
        if source in mapping and target in mapping:
            new_source = mapping[source]
            new_target = mapping[target]
            G.add_edge(new_source, new_target)
            edge_colors[(new_source, new_target)] = 'lightgrey'

    # Define and add black edges manually with correct node names
    numbered_nodes = list(mapping.values())
    black_edge_list = [
        (numbered_nodes[3], numbered_nodes[6]),  # 4 -> 7
        (numbered_nodes[6], numbered_nodes[8]),  # 7 -> 9
        (numbered_nodes[8], numbered_nodes[10]), # 9 -> 11
        (numbered_nodes[10], numbered_nodes[12]), # 11 -> 13
        (numbered_nodes[10], numbered_nodes[13]), # 11 -> 14
        (numbered_nodes[10], numbered_nodes[14]), # 11 -> 15
        (numbered_nodes[10], numbered_nodes[15]), # 11 -> 16
        (numbered_nodes[10], numbered_nodes[16])  # 11 -> 17
    ]

    for src, tgt in black_edge_list:
        G.add_edge(src, tgt)
        edge_colors[(src, tgt)] = 'black'

    # Draw the graph
    plt.figure(figsize=(12, 8))
    nx.draw(
        G, pos, with_labels=True, node_color=node_colors, 
        edge_color=[edge_colors.get(edge, 'lightgrey') for edge in G.edges],
        node_size=3000, font_size=9, connectionstyle="arc3,rad=0.2"
    )
    
    plt.title("EcoGreen: Reclaiming Agricultural Self", fontsize=18)
    plt.show()

# Run the visualization
visualize_nn()

Fig. 4 Fact, Speculation, Narrative, Reason, History. Oscar Wilde’s The Rise of Historical Criticism (1879) maps the evolution of Greek historical thought through a neural network lens. The “Tragedy” layer captures the initial Aufklärung, recognizing patterns in myth. “History” filters superstition, as Herodotus sifts fact from fable. “Epic” synthesizes this into rational narratives via Euhemeros and Thucydides. “Drama” pits belief against reason, refined by Plato and Aristotle. “Comedy” resolves it in Polybius’s scientific history. Wilde’s analysis mirrors a network’s progression from input to output, highlighting the enduring rationality of Greek critique.