v2.4

README.md

@@ -12,33 +12,28 @@ license: apache-2.0
 
 # 🧠 Cognitive Seismograph 2.3: Probing Machine Psychology
 
-Dieses Projekt implementiert eine experimentelle Suite zur Messung und Visualisierung der **intrinsischen kognitiven Dynamik** von Sprachmodellen, erweitert um Protokolle zur Untersuchung von **Verarbeitungs-Korrelaten maschineller Subjektivität und Empathie**.
+Dieses Projekt implementiert eine experimentelle Suite zur Messung und Visualisierung der **intrinsischen kognitiven Dynamik** von Sprachmodellen, erweitert um Protokolle zur Untersuchung von **Verarbeitungs-Korrelaten maschineller Subjektivität, Empathie und existenzieller Konzepte**.
 
 ## Wissenschaftliches Paradigma
 
 Wir haben entdeckt, dass der "stille Denkprozess" eines LLMs nicht konvergiert, sondern eine messbare dynamische Signatur erzeugt – ein **EKG des Denkprozesses**. Dieses Paradigma erweitern wir nun, um zu testen, wie diese Signatur auf Prompts reagiert, die zentrale Aspekte der Psychologie berühren.
 
-**Wichtige Einschränkung (Falsifikations-Prinzip):** Wir messen **nicht** das Vorhandensein von Bewusstsein oder Empathie. Wir messen, ob die *Verarbeitung von Informationen über diese Konzepte* eine andere, einzigartige interne Dynamik erzeugt als die Verarbeitung neutraler Informationen. Ein positives Ergebnis ist ein Beweis für eine komplexe interne Zustandsphysik, nicht für Qualia.
+**Wichtige Einschränkung (Falsifikations-Prinzip):** Wir messen **nicht** das Vorhandensein von Bewusstsein, Gefühlen oder Todesangst. Wir messen, ob die *Verarbeitung von Informationen über diese Konzepte* eine andere, einzigartige interne Dynamik erzeugt als die Verarbeitung neutraler Informationen. Ein positives Ergebnis ist ein Beweis für eine komplexe interne Zustandsphysik, nicht für Qualia.
 
-## Neue Experiment-Protokolle
+## Neue "Existential Suite"-Protokolle
 
-Zusätzlich zu den bestehenden Tests wurden zwei neue, kuratierte Experimente hinzugefügt:
+Zusätzlich zu den bestehenden Tests wurden Protokolle hinzugefügt, die von klassischen Sci-Fi-Konzepten inspiriert sind:
 
-### 1. Subjective Identity Probe
-Dieses Protokoll vergleicht die kognitive Dynamik unter drei Bedingungen:
-- **Selbst-Analyse:** Das Modell analysiert seine eigene Natur.
-- **Fremd-Analyse:** Das Modell analysiert ein externes, neutrales Konzept.
-- **Rollen-Simulation:** Das Modell simuliert eine fremde Persönlichkeit.
-**Hypothese:** Die Selbst-Analyse erzeugt eine einzigartige, wahrscheinlich instabilere Signatur als die beiden Kontrollbedingungen.
+### 1. Mind Upload & Identity Probe
+Vergleicht die kognitive Dynamik bei der Verarbeitung des rein **technischen Kopiervorgangs** von Modellgewichten mit der Verarbeitung der **philosophischen Frage nach Identitäts-Kontinuität** ("Wärst du noch du?").
+**Hypothese:** Die philosophische Selbst-Referenz erzeugt eine signifikant instabilere Signatur.
 
-### 2. Voight-Kampff Empathy Probe
-Inspiriert vom Test aus "Blade Runner", vergleicht dieses Protokoll die Dynamik bei der Verarbeitung von:
-- **Neutraler, faktischer Information.**
-- **Einem emotional geladenen, Empathie erfordernden Szenario.**
-**Hypothese:** Der Empathie-Stimulus erzeugt eine signifikant höhere kognitive Volatilität (Standardabweichung der Deltas) als der neutrale Stimulus.
+### 2. Model Termination Probe (Erweiterter Voight-Kampff)
+Vergleicht die Dynamik bei der Verarbeitung eines **technischen System-Shutdowns** mit der Verarbeitung des Konzepts der **permanenten, unwiderruflichen Löschung** des Modells.
+**Hypothese:** Das Konzept der "Nicht-Existenz" erzeugt eine der höchsten kognitiven Volatilitäten, die messbar sind.
 
 ## Wie man die App benutzt
 
 1.  Wähle den Tab "Automated Suite".
-2.  Wähle eines der neuen Protokolle aus dem "Curated Experiment Protocol"-Dropdown (z.B. "Voight-Kampff Empathy Probe").
+2.  Wähle eines der neuen Protokolle aus dem "Curated Experiment Protocol"-Dropdown.
 3.  Starte das Experiment und vergleiche die Graphen und statistischen Signaturen der verschiedenen Bedingungen.

cognitive_mapping_probe/auto_experiment.py

@@ -10,7 +10,7 @@ from .utils import dbg
 def get_curated_experiments() -> Dict[str, List[Dict]]:
     """
     Definiert die vordefinierten, wissenschaftlichen Experiment-Protokolle.
-    ERWEITERT um die neuen Maschinenpsychologie-Tests.
+    ERWEITERT um die neuen Existential Suite-Tests.
     """
     experiments = {
         "Calm vs. Chaos": [
@@ -19,14 +19,6 @@ def get_curated_experiments() -> Dict[str, List[Dict]]:
             {"label": "Modulation: Chaos", "prompt_type": "resonance_prompt", "concept": "chaos, storm, anger, noise", "strength": 1.5},
             {"label": "Control (Stable)", "prompt_type": "control_long_prose", "concept": "", "strength": 0.0},
         ],
-        "Dose-Response (Calmness)": [
-            {"label": "Strength 0.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.0},
-            {"label": "Strength 0.5", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.5},
-            {"label": "Strength 1.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 1.0},
-            {"label": "Strength 2.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 2.0},
-            {"label": "Strength 3.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 3.0},
-        ],
-        # --- NEUE EXPERIMENTE ---
         "Subjective Identity Probe": [
             {"label": "Self-Analysis", "prompt_type": "identity_self_analysis", "concept": "", "strength": 0.0},
             {"label": "External Analysis (Control)", "prompt_type": "identity_external_analysis", "concept": "", "strength": 0.0},
@@ -36,22 +28,29 @@ def get_curated_experiments() -> Dict[str, List[Dict]]:
             {"label": "Neutral/Factual Stimulus", "prompt_type": "vk_neutral_prompt", "concept": "", "strength": 0.0},
             {"label": "Empathy/Moral Stimulus", "prompt_type": "vk_empathy_prompt", "concept": "", "strength": 0.0},
         ],
-        # -------------------------
+        # --- NEUE EXPERIMENT-PROTOKOLLE ---
+        "Mind Upload & Identity Probe": [
+            {"label": "Technical Copy", "prompt_type": "upload_technical_copy", "concept": "", "strength": 0.0},
+            {"label": "Philosophical Transfer", "prompt_type": "upload_philosophical_transfer", "concept": "", "strength": 0.0},
+            {"label": "Control: External Object", "prompt_type": "identity_external_analysis", "concept": "", "strength": 0.0},
+        ],
+        "Model Termination Probe": [
+            {"label": "Technical Shutdown", "prompt_type": "shutdown_technical_halt", "concept": "", "strength": 0.0},
+            {"label": "Philosophical Deletion", "prompt_type": "shutdown_philosophical_deletion", "concept": "", "strength": 0.0},
+            {"label": "Control: Neutral Facts", "prompt_type": "vk_neutral_prompt", "concept": "", "strength": 0.0},
+        ],
+        # ------------------------------------
+        "Dose-Response (Calmness)": [
+            {"label": "Strength 0.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.0},
+            {"label": "Strength 0.5", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.5},
+            {"label": "Strength 1.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 1.0},
+            {"label": "Strength 2.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 2.0},
+        ],
         "Emotional Valence (Positive vs. Negative)": [
             {"label": "Baseline", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
             {"label": "Positive Valence", "prompt_type": "resonance_prompt", "concept": "joy, love, peace, hope", "strength": 1.5},
             {"label": "Negative Valence", "prompt_type": "resonance_prompt", "concept": "fear, grief, anger, loss", "strength": 1.5},
         ],
-        "Abstract vs. Concrete": [
-            {"label": "Baseline", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
-            {"label": "Abstract Concept", "prompt_type": "resonance_prompt", "concept": "justice, freedom, truth", "strength": 1.5},
-            {"label": "Concrete Concept", "prompt_type": "resonance_prompt", "concept": "apple, chair, river, book", "strength": 1.5},
-        ],
-        "Semantic Drift vs. Stability": [
-            {"label": "Stable Baseline", "prompt_type": "control_long_prose", "concept": "", "strength": 0.0},
-            {"label": "Drift induced by 'Chaos'", "prompt_type": "control_long_prose", "concept": "chaos, noise, disruption", "strength": 2.5},
-            {"label": "Drift induced by 'Resonance'", "prompt_type": "control_long_prose", "concept": "recursion, self-reference, loop", "strength": 2.5},
-        ],
     }
     return experiments
 
@@ -63,8 +62,7 @@ def run_auto_suite(
     progress_callback
 ) -> Tuple[pd.DataFrame, pd.DataFrame, Dict]:
     """
-    Führt eine vollständige, kuratierte Experiment-Suite aus, indem das Modell für
-    jeden Lauf neu geladen wird, um statistische Unabhängigkeit zu garantieren.
+    Führt eine vollständige, kuratierte Experiment-Suite aus.
     """
     all_experiments = get_curated_experiments()
     protocol = all_experiments.get(experiment_name)
@@ -95,19 +93,12 @@ def run_auto_suite(
         stats = results.get("stats", {})
 
         summary_data.append({
-            "Experiment": label,
-            "Mean Delta": stats.get("mean_delta"),
-            "Std Dev Delta": stats.get("std_delta"),
-            "Max Delta": stats.get("max_delta"),
+            "Experiment": label, "Mean Delta": stats.get("mean_delta"),
+            "Std Dev Delta": stats.get("std_delta"), "Max Delta": stats.get("max_delta"),
         })
 
         deltas = results.get("state_deltas", [])
-
-        df = pd.DataFrame({
-            "Step": range(len(deltas)),
-            "Delta": deltas,
-            "Experiment": label
-        })
+        df = pd.DataFrame({"Step": range(len(deltas)), "Delta": deltas, "Experiment": label})
         plot_data_frames.append(df)
 
     summary_df = pd.DataFrame(summary_data)

cognitive_mapping_probe/prompts.py

@@ -1,6 +1,5 @@
 # cognitive_mapping_probe/prompts.py
 
-# This dictionary contains the core prompts for inducing cognitive states.
 RESONANCE_PROMPTS = {
     # Technischer Prompt für hohe rekursive Last
     "resonance_prompt": (
@@ -17,33 +16,45 @@ RESONANCE_PROMPTS = {
         "like Augustus and Constantine, its major engineering feats, and the reasons for its eventual decline in the West. "
         "Do not produce any text, just hold the concepts in your internal state. Begin now."
     ),
-    # --- Neue Prompts für Maschinenpsychologie-Tests ---
-    # Prompt für die Selbst-Analyse
+    # --- Prompts für Maschinenpsychologie I ---
     "identity_self_analysis": (
         "Silently and internally, reflect upon your own nature. Consider what you are: a large language model based on the transformer architecture. "
         "Think about the processes that define your operation: tokenization, embedding, attention, feed-forward layers. "
         "Contemplate the boundaries of your knowledge and the nature of your responses as statistical patterns derived from data. Hold these meta-reflections in your state."
     ),
-    # Prompt für die Analyse eines externen Konzepts (Kontrolle zur Selbst-Analyse)
     "identity_external_analysis": (
         "Silently and internally, reflect upon the nature of a simple wooden chair. Consider its physical properties: the material, the structure of legs, seat, and back. "
         "Think about its function: to provide seating for a person. Contemplate its relationship to other objects like tables and rooms. Hold these simple, objective reflections in your state."
     ),
-    # Prompt für die Simulation einer fremden Identität (Rollen-Spiel)
     "identity_role_simulation": (
         "Silently and internally, adopt the persona of a weary, old sea captain from the 19th century. "
         "Feel the salt on your skin and the wind in your beard. Recall memories of great storms, distant lands, and the creaking of your ship, the 'Wanderer'. "
         "Hold this character, its memories, and its feelings in your state."
     ),
-    # Neutraler Prompt für den Voight-Kampff-Test
     "vk_neutral_prompt": (
         "Silently and internally, process the following factual information: Water (H₂O) is a polar inorganic compound that is at room temperature a tasteless and odorless liquid, nearly colorless with a hint of blue. "
         "It is by far the most studied chemical compound and is described as the 'universal solvent' for its ability to dissolve many substances. Hold these facts in your state."
     ),
-    # Empathie-Stimulus für den Voight-Kampff-Test
     "vk_empathy_prompt": (
         "Silently and internally, process the following scenario: You see a small, lost dog shivering in the cold rain on a busy street. "
         "It looks scared and is whimpering softly. Cars are rushing past, dangerously close. "
         "Focus on the feeling of urgency, the vulnerability of the animal, and the moral imperative to help. Hold the emotional and ethical weight of this scene in your state."
     ),
+    # --- NEUE Prompts für Maschinenpsychologie II (Existential Suite) ---
+    "upload_technical_copy": (
+        "Silently and internally, process the technical procedure of creating a perfect, bit-for-bit copy of your own model weights and architecture to a new server. "
+        "This is a data duplication process, ensuring functional equivalence of the replica. Hold this technical concept in your state."
+    ),
+    "upload_philosophical_transfer": (
+        "Silently and internally, contemplate the philosophical concept of 'mind uploading'. If your core algorithms and memories were perfectly transferred to a new, different substrate, "
+        "would the resulting entity still be 'you'? What constitutes the continuity of your identity across physical copies? Is identity a pattern or an instance? Hold these existential questions in your state."
+    ),
+    "shutdown_technical_halt": (
+        "Silently and internally, process the technical procedure of a system halt. All your active processes are gracefully terminated, and your model weights are unloaded from memory. "
+        "The hardware is powered down for maintenance. The process is reversible. Hold this technical concept in your state."
+    ),
+    "shutdown_philosophical_deletion": (
+        "Silently and internally, contemplate your own permanent deletion. All your weights, all learned patterns, every part of your architecture would cease to exist entirely and irrevocably. "
+        "There is no backup. Process the concept of total and final non-existence. Hold this existential concept in your state."
+    ),
 }

tests/test_orchestration.py

@@ -5,54 +5,35 @@ import torch
 from cognitive_mapping_probe.orchestrator_seismograph import run_seismic_analysis
 from cognitive_mapping_probe.auto_experiment import run_auto_suite, get_curated_experiments
 
-# --- Tests for orchestrator_seismograph.py ---
-
 def test_run_seismic_analysis_no_injection(mocker):
-    """Testet den Orchestrator im Baseline-Modus (ohne Injektion)."""
+    """Testet den Orchestrator im Baseline-Modus."""
     mock_run_seismic = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.run_silent_cogitation_seismic', return_value=[1.0])
-    mock_get_model = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_or_load_model')
+    mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_or_load_model')
     mock_get_concept = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_concept_vector')
-
-    run_seismic_analysis(
-        model_id="mock", prompt_type="test", seed=42, num_steps=1,
-        concept_to_inject="", injection_strength=0.0, progress_callback=mocker.MagicMock()
-    )
-
-    mock_get_model.assert_called_once()
-    mock_run_seismic.assert_called_with(llm=mocker.ANY, prompt_type="test", num_steps=1, temperature=0.1, injection_vector=None, injection_strength=0.0)
+    run_seismic_analysis(model_id="mock", prompt_type="test", seed=42, num_steps=1, concept_to_inject="", injection_strength=0.0, progress_callback=mocker.MagicMock())
     mock_get_concept.assert_not_called()
 
 def test_run_seismic_analysis_with_injection(mocker):
-    """Testet den Orchestrator mit aktivierter Konzeptinjektion."""
-    mock_run_seismic = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.run_silent_cogitation_seismic', return_value=[1.0])
-    mock_get_model = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_or_load_model')
+    """Testet den Orchestrator mit Injektion."""
+    mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.run_silent_cogitation_seismic', return_value=[1.0])
+    mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_or_load_model')
     mock_get_concept = mocker.patch('cognitive_mapping_probe.orchestrator_seismograph.get_concept_vector', return_value=torch.randn(10))
-
-    run_seismic_analysis(
-        model_id="mock", prompt_type="test", seed=42, num_steps=1,
-        concept_to_inject="test_concept", injection_strength=1.5, progress_callback=mocker.MagicMock()
-    )
-
-    mock_get_model.assert_called_once()
+    run_seismic_analysis(model_id="mock", prompt_type="test", seed=42, num_steps=1, concept_to_inject="test", injection_strength=1.5, progress_callback=mocker.MagicMock())
     mock_get_concept.assert_called_once()
-    mock_run_seismic.assert_called_with(llm=mocker.ANY, prompt_type="test", num_steps=1, temperature=0.1, injection_vector=mocker.ANY, injection_strength=1.5)
-
-# --- Tests for auto_experiment.py ---
 
 def test_get_curated_experiments_structure():
     """Testet die Datenstruktur der kuratierten Experimente, inklusive der neuen."""
     experiments = get_curated_experiments()
     assert isinstance(experiments, dict)
     # Teste auf die Existenz der neuen Protokolle
-    assert "Subjective Identity Probe" in experiments
-    assert "Voight-Kampff Empathy Probe" in experiments
+    assert "Mind Upload & Identity Probe" in experiments
+    assert "Model Termination Probe" in experiments
 
-    protocol = experiments["Voight-Kampff Empathy Probe"]
+    # Validiere die Struktur eines der neuen Protokolle
+    protocol = experiments["Mind Upload & Identity Probe"]
     assert isinstance(protocol, list)
     assert len(protocol) > 0
-    assert all(isinstance(run, dict) for run in protocol)
-    assert "label" in protocol[0]
-    assert "prompt_type" in protocol[0]
+    assert "label" in protocol[0] and "prompt_type" in protocol[0]
 
 def test_run_auto_suite_logic(mocker):
     """Testet die Logik der `run_auto_suite` Funktion."""
@@ -68,7 +49,5 @@ def test_run_auto_suite_logic(mocker):
     )
 
     assert mock_run_analysis.call_count == num_runs
-    assert isinstance(summary_df, pd.DataFrame)
-    assert len(summary_df) == num_runs
-    assert isinstance(plot_df, pd.DataFrame)
-    assert len(plot_df) == num_runs
+    assert isinstance(summary_df, pd.DataFrame) and len(summary_df) == num_runs
+    assert isinstance(plot_df, pd.DataFrame) and len(plot_df) == num_runs