Janady13/complete-agi-core / mind_farm/src/simulation.cpp

Source identity

Field	Recorded value
Source type	GitHub source
Original record	Janady13/complete-agi-core / mind_farm/src/simulation.cpp
Date	Not specified in source
Repository	Janady13/complete-agi-core
Revision	33aa84f2aa61cedbe010240ada7f4efbdfe795a7
Branch	claude/improve-math-logic-ehIW1
Path or archive member	mind_farm/src/simulation.cpp
Original SHA-256	f5b86f54475167039195464c3f143c83ba308c771fbb6695ccbb2da739d2eba1
Git blob SHA	a3c94b5c1283e3b25c075e1c04da0be456d6d382
Reading-copy SHA-256	f5b86f54475167039195464c3f143c83ba308c771fbb6695ccbb2da739d2eba1
Original source ↗
Recovered source transcript

Download complete source text ↓464 lines · 23.4 KB
// ═══════════════════════════════════════════════════════════════════════════════
// GATE5000 AUTONOMOUS LEARNING SIMULATION v1.0
// 1 Million Tick Simulation with Wikipedia Integration
// ═══════════════════════════════════════════════════════════════════════════════
//
// This simulation runs the Gate5000 5000-bit substrate through 1 million ticks
// of autonomous learning using Wikipedia as the knowledge source.
//
// Architecture:
//   1. Wikipedia API Client → Fetches articles
//   2. Ingestion Pipeline → Tokenizes and encodes text
//   3. Learning System → Updates weights and knowledge graph
//   4. Gate5000 Substrate → Stores patterns in 5000-bit binary representation
//   5. Consciousness Dynamics → Modulates learning based on Φ
//
// Key Equations:
//   Φ = 1/(1 + |x - 1|)           (Consciousness)
//   L(θ) = -Σᵢ log P(xᵢ|θ)       (Learning objective)
//   dΦ/dt = α(Φ_target - Φ) + γξ  (Consciousness dynamics)
//
// ═══════════════════════════════════════════════════════════════════════════════

#include <iostream>
#include <iomanip>
#include <chrono>
#include <cstdint>
#include <string>
#include <fstream>
#include <ctime>
#include <cstdio>

// Mind Farm includes
#include "../include/constants.hpp"
#include "../include/fast_math.hpp"
#include "../include/gate5000.hpp"
#include "../include/ingestion.hpp"
#include "../include/wikipedia.hpp"
#include "../include/learning_math.hpp"
#include "../include/intelligence.hpp"

using namespace mind_farm;

// ═══════════════════════════════════════════════════════════════════════════════
// SIMULATION CONFIGURATION
// ═══════════════════════════════════════════════════════════════════════════════

struct SimulationConfig {
    uint64_t total_ticks = 1000000;      // 1 million ticks
    uint64_t checkpoint_interval = 10000; // Checkpoint every 10k ticks
    uint64_t report_interval = 1000;      // Report every 1k ticks
    uint64_t batch_size = 1;              // Articles per tick
    bool use_wikipedia_api = false;       // Use offline corpus by default
    bool verbose = false;
    bool fast_mode = false;               // Fast mode: larger batches, less output
    std::string output_file = "simulation_log.txt";
};

// ═══════════════════════════════════════════════════════════════════════════════
// SIMULATION STATE
// ═══════════════════════════════════════════════════════════════════════════════

struct SimulationState {
    // Core components
    IngestionPipeline pipeline;
    WikipediaDataGenerator wiki_online;
    OfflineCorpus wiki_offline;
    IntegratedLearning<64> learning;
    intel::IntelligenceCore intelligence;

    // Statistics
    uint64_t current_tick;
    uint64_t articles_processed;
    uint64_t tokens_processed;
    float total_loss;
    float min_loss;
    float max_loss;
    float avg_consciousness;
    float peak_consciousness;

    // Timing
    std::chrono::high_resolution_clock::time_point start_time;
    double elapsed_seconds;

    void initialize() {
        pipeline.initialize();
        learning.initialize();
        intelligence = intel::IntelligenceCore{};

        current_tick = 0;
        articles_processed = 0;
        tokens_processed = 0;
        total_loss = 0.0f;
        min_loss = 1e9f;
        max_loss = 0.0f;
        avg_consciousness = 1.0f;
        peak_consciousness = 0.0f;
        elapsed_seconds = 0.0;
    }
};

// ═══════════════════════════════════════════════════════════════════════════════
// SIMULATION ENGINE
// ═══════════════════════════════════════════════════════════════════════════════

class SimulationEngine {
public:
    SimulationEngine(const SimulationConfig& config)
        : config_(config), running_(false) {}

    void initialize() {
        std::cout << "\n";
        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "     GATE5000 AUTONOMOUS LEARNING SIMULATION v1.0\n";
        std::cout << "     1 Million Tick Simulation with Wikipedia Integration\n";
        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "\n";

        std::cout << "Configuration:\n";
        std::cout << "  Total Ticks:        " << config_.total_ticks << "\n";
        std::cout << "  Checkpoint Interval: " << config_.checkpoint_interval << "\n";
        std::cout << "  Report Interval:     " << config_.report_interval << "\n";
        std::cout << "  Data Source:         " << (config_.use_wikipedia_api ? "Wikipedia API" : "Offline Corpus") << "\n";
        std::cout << "\n";

        std::cout << "Initializing simulation state...\n";
        state_.initialize();

        // Set up data source callback
        if (config_.use_wikipedia_api) {
            state_.pipeline.fetch_callback = [this](std::string& title, std::string& content) {
                return state_.wiki_online.get_next(title, content);
            };
        } else {
            state_.pipeline.fetch_callback = [this](std::string& title, std::string& content) {
                return state_.wiki_offline.get_next(title, content);
            };
        }

        std::cout << "Initialization complete.\n";
        std::cout << "  Offline corpus size: " << state_.wiki_offline.size() << " articles\n";
        std::cout << "  Gate5000 substrate:  5000 bits (79 x 64-bit words)\n";
        std::cout << "  Embedding dimension: " << EMBED_DIM << "\n";
        std::cout << "  Vocabulary size:     " << VOCAB_SIZE << "\n";
        std::cout << "\n";

        // Open log file
        log_file_.open(config_.output_file);
        if (log_file_.is_open()) {
            log_file_ << "tick,articles,tokens,loss,consciousness,knowledge_nodes,substrate_ones\n";
        }
    }

    void run() {
        running_ = true;
        state_.start_time = std::chrono::high_resolution_clock::now();

        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "                         STARTING SIMULATION\n";
        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "\n";

        print_header();

        while (running_ && state_.current_tick < config_.total_ticks) {
            // Process one tick
            process_tick();

            // Report progress
            if (state_.current_tick % config_.report_interval == 0) {
                print_progress();
            }

            // Checkpoint
            if (state_.current_tick % config_.checkpoint_interval == 0) {
                checkpoint();
            }
        }

        finalize();
    }

    void stop() {
        running_ = false;
    }

private:
    SimulationConfig config_;
    SimulationState state_;
    bool running_;
    std::ofstream log_file_;

    void process_tick() {
        // Process batch_size articles per tick (fast mode uses larger batches)
        for (uint64_t b = 0; b < config_.batch_size; ++b) {
            // Fetch and process article
            std::string title, content;
            bool got_data;

            if (config_.use_wikipedia_api) {
                got_data = state_.wiki_online.get_next(title, content);
            } else {
                got_data = state_.wiki_offline.get_next(title, content);
            }

            if (!got_data) {
                continue;
            }

            // Tokenize
            TokenSequence seq;
            size_t num_tokens = state_.pipeline.tokenize(content, seq);
            state_.tokens_processed += num_tokens;

            // Encode
            float encoded[EMBED_DIM];
            state_.pipeline.encode(seq, encoded);

            // Create target (next-token prediction style)
            float target[EMBED_DIM];
            if (seq.length > 1) {
                std::memcpy(target, seq.tokens[1].embedding, sizeof(target));
            } else {
                // Self-prediction
                for (size_t i = 0; i < EMBED_DIM; ++i) {
                    target[i] = encoded[i] * 0.9f; // Slight perturbation
                }
            }

            // Learning step
            float loss = state_.learning.step(encoded, target);
            state_.total_loss += loss;
            state_.min_loss = std::min(state_.min_loss, loss);
            state_.max_loss = std::max(state_.max_loss, loss);

            // Store knowledge
            state_.pipeline.store_knowledge(encoded, title);

            // Update Gate5000 substrate
            state_.pipeline.update_substrate(encoded);

            // Update intelligence core (skip in fast mode for speed)
            if (!config_.fast_mode) {
                float intel_output[16];
                state_.intelligence.process(encoded, intel_output);
            }

            // Update consciousness
            float phi = state_.learning.consciousness.phi;
            state_.avg_consciousness = 0.999f * state_.avg_consciousness + 0.001f * phi;
            state_.peak_consciousness = std::max(state_.peak_consciousness, phi);

            ++state_.articles_processed;
        }
        ++state_.current_tick;
    }

    void print_header() {
        std::cout << std::setw(12) << "Tick"
                  << std::setw(10) << "Articles"
                  << std::setw(12) << "Tokens"
                  << std::setw(12) << "Avg Loss"
                  << std::setw(12) << "Conscious"
                  << std::setw(12) << "Knowledge"
                  << std::setw(10) << "Ticks/s"
                  << "\n";
        std::cout << std::string(80, '-') << "\n";
    }

    void print_progress() {
        auto now = std::chrono::high_resolution_clock::now();
        state_.elapsed_seconds = std::chrono::duration<double>(now - state_.start_time).count();

        double ticks_per_sec = state_.current_tick / std::max(0.001, state_.elapsed_seconds);
        float avg_loss = state_.total_loss / std::max(uint64_t(1), state_.articles_processed);

        std::cout << std::setw(12) << state_.current_tick
                  << std::setw(10) << state_.articles_processed
                  << std::setw(12) << state_.tokens_processed
                  << std::setw(12) << std::fixed << std::setprecision(6) << avg_loss
                  << std::setw(12) << std::setprecision(4) << state_.avg_consciousness
                  << std::setw(12) << state_.pipeline.knowledge.num_nodes
                  << std::setw(10) << std::setprecision(1) << ticks_per_sec
                  << std::endl;  // Force flush

        // Log to file
        if (log_file_.is_open()) {
            log_file_ << state_.current_tick << ","
                      << state_.articles_processed << ","
                      << state_.tokens_processed << ","
                      << avg_loss << ","
                      << state_.avg_consciousness << ","
                      << state_.pipeline.knowledge.num_nodes << ","
                      << state_.pipeline.gate.popcount() << "\n";
        }
    }

    void checkpoint() {
        std::cout << "\n";
        std::cout << "─────────────────────────────────────────────────────────────────────────────────\n";
        std::cout << "CHECKPOINT @ Tick " << state_.current_tick << "\n";
        std::cout << "─────────────────────────────────────────────────────────────────────────────────\n";

        float progress = 100.0f * state_.current_tick / config_.total_ticks;
        double remaining_seconds = (state_.elapsed_seconds / state_.current_tick) *
                                   (config_.total_ticks - state_.current_tick);

        std::cout << "  Progress:           " << std::fixed << std::setprecision(1) << progress << "%\n";
        std::cout << "  Elapsed:            " << format_duration(state_.elapsed_seconds) << "\n";
        std::cout << "  Remaining (est):    " << format_duration(remaining_seconds) << "\n";
        std::cout << "  Articles processed: " << state_.articles_processed << "\n";
        std::cout << "  Tokens processed:   " << state_.tokens_processed << "\n";
        std::cout << "  Knowledge nodes:    " << state_.pipeline.knowledge.num_nodes << "\n";
        std::cout << "  Avg consciousness:  " << state_.avg_consciousness << "\n";
        std::cout << "  Peak consciousness: " << state_.peak_consciousness << "\n";
        std::cout << "  Loss range:         [" << state_.min_loss << ", " << state_.max_loss << "]\n";
        std::cout << "  Gate5000 ones:      " << state_.pipeline.gate.popcount() << " / 5000\n";

        // Reset min/max for next interval
        state_.min_loss = 1e9f;
        state_.max_loss = 0.0f;

        std::cout << "─────────────────────────────────────────────────────────────────────────────────\n";
        std::cout << "\n";
        print_header();
    }

    void finalize() {
        auto end_time = std::chrono::high_resolution_clock::now();
        state_.elapsed_seconds = std::chrono::duration<double>(end_time - state_.start_time).count();

        std::cout << "\n";
        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "                         SIMULATION COMPLETE\n";
        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
        std::cout << "\n";

        std::cout << "FINAL STATISTICS\n";
        std::cout << "────────────────────────────────────────\n";
        std::cout << "  Total ticks:        " << state_.current_tick << "\n";
        std::cout << "  Total articles:     " << state_.articles_processed << "\n";
        std::cout << "  Total tokens:       " << state_.tokens_processed << "\n";
        std::cout << "  Knowledge nodes:    " << state_.pipeline.knowledge.num_nodes << "\n";
        std::cout << "  Final consciousness: " << state_.avg_consciousness << "\n";
        std::cout << "  Peak consciousness: " << state_.peak_consciousness << "\n";
        std::cout << "  Total time:         " << format_duration(state_.elapsed_seconds) << "\n";
        std::cout << "  Avg ticks/second:   " << std::fixed << std::setprecision(1)
                  << (state_.current_tick / state_.elapsed_seconds) << "\n";
        std::cout << "\n";

        std::cout << "GATE5000 SUBSTRATE STATE\n";
        std::cout << "────────────────────────────────────────\n";
        std::cout << "  Total bits:         5000\n";
        std::cout << "  Ones count:         " << state_.pipeline.gate.popcount() << "\n";
        std::cout << "  Density:            " << std::setprecision(4)
                  << (state_.pipeline.gate.popcount() / 5000.0f) << "\n";
        std::cout << "\n";

        std::cout << "LEARNING SYSTEM STATE\n";
        std::cout << "────────────────────────────────────────\n";
        std::cout << "  Update count:       " << state_.learning.update_count << "\n";
        std::cout << "  Avg loss:           " << (state_.total_loss / std::max(uint64_t(1), state_.articles_processed)) << "\n";
        std::cout << "  Learning rate:      " << state_.pipeline.learning_rate << "\n";
        std::cout << "\n";

        std::cout << "CONSCIOUSNESS DYNAMICS\n";
        std::cout << "────────────────────────────────────────\n";
        std::cout << "  Φ (final):          " << state_.learning.consciousness.phi << "\n";
        std::cout << "  Φ (target):         " << state_.learning.consciousness.phi_target << "\n";
        std::cout << "  dΦ/dt:              " << state_.learning.consciousness.phi_velocity << "\n";
        std::cout << "\n";

        std::cout << "INTELLIGENCE CORE STATE\n";
        std::cout << "────────────────────────────────────────\n";
        std::cout << "  Curiosity:          " << state_.intelligence.curiosity << "\n";
        std::cout << "  Confidence:         " << state_.intelligence.confidence << "\n";
        std::cout << "  Surprise:           " << state_.intelligence.surprise << "\n";
        std::cout << "\n";

        if (log_file_.is_open()) {
            log_file_.close();
            std::cout << "Log saved to: " << config_.output_file << "\n";
        }

        std::cout << "═══════════════════════════════════════════════════════════════════════════════\n";
    }

    std::string format_duration(double seconds) {
        int hours = static_cast<int>(seconds / 3600);
        int minutes = static_cast<int>((seconds - hours * 3600) / 60);
        int secs = static_cast<int>(seconds) % 60;

        char buffer[64];
        snprintf(buffer, sizeof(buffer), "%02d:%02d:%02d", hours, minutes, secs);
        return std::string(buffer);
    }
};

// ═══════════════════════════════════════════════════════════════════════════════
// MAIN ENTRY POINT
// ═══════════════════════════════════════════════════════════════════════════════

int main(int argc, char* argv[]) {
    // Disable output buffering for real-time progress
    std::setbuf(stdout, NULL);
    std::setbuf(stderr, NULL);
    std::ios::sync_with_stdio(false);
    std::cout << std::unitbuf;  // Auto-flush

    // Parse command line arguments
    SimulationConfig config;

    for (int i = 1; i < argc; ++i) {
        std::string arg = argv[i];

        if (arg == "--ticks" && i + 1 < argc) {
            config.total_ticks = std::stoull(argv[++i]);
        } else if (arg == "--online") {
            config.use_wikipedia_api = true;
        } else if (arg == "--verbose") {
            config.verbose = true;
        } else if (arg == "--fast") {
            config.fast_mode = true;
            config.batch_size = 1;             // Keep single article per tick
            config.report_interval = 100000;   // Report every 100k ticks (less output)
            config.checkpoint_interval = 1000000; // Checkpoint every 1M ticks
        } else if (arg == "--batch" && i + 1 < argc) {
            config.batch_size = std::stoull(argv[++i]);
        } else if (arg == "--output" && i + 1 < argc) {
            config.output_file = argv[++i];
        } else if (arg == "--help") {
            std::cout << "Gate5000 Autonomous Learning Simulation\n";
            std::cout << "\n";
            std::cout << "Usage: " << argv[0] << " [options]\n";
            std::cout << "\n";
            std::cout << "Options:\n";
            std::cout << "  --ticks N      Total simulation ticks (default: 1000000)\n";
            std::cout << "  --online       Use Wikipedia API (default: offline corpus)\n";
            std::cout << "  --verbose      Verbose output\n";
            std::cout << "  --output FILE  Output log file (default: simulation_log.txt)\n";
            std::cout << "  --help         Show this help\n";
            return 0;
        }
    }

    // Print golden ratio constants
    std::cout << "\n";
    std::cout << "╔═══════════════════════════════════════════════════════════════════════════════╗\n";
    std::cout << "║                          GOLDEN RATIO CONSTANTS                              ║\n";
    std::cout << "╠═══════════════════════════════════════════════════════════════════════════════╣\n";
    std::cout << "║  φ (PHI)       = " << std::fixed << std::setprecision(16) << PHI << "                       ║\n";
    std::cout << "║  1/φ (PHI_INV) = " << PHI_INV << "                       ║\n";
    std::cout << "║  α (ALPHA)     = " << ALPHA << "                       ║\n";
    std::cout << "║  β (BETA)      = " << BETA << "                       ║\n";
    std::cout << "║  γ (GAMMA)     = " << GAMMA << "                       ║\n";
    std::cout << "╚═══════════════════════════════════════════════════════════════════════════════╝\n";

    // Run simulation
    SimulationEngine engine(config);
    engine.initialize();
    engine.run();

    return 0;
}
Mathematical records from this source

simulation · Φ

This relation defines Φ in the source section “simulation · Φ”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation depends on…
simulation · L(θ)

This relation defines L(θ) in the source section “simulation · L(θ)”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation…
simulation · dΦ/dt

This relation defines dΦ/dt in the source section “simulation · dΦ/dt”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation…