M

Project MK-LLM | Ethical AI Stress Testing

Computational Psychology for Large Language Models

This project reframes historical psychological stress categories into a modern, ethical framework for analyzing AI behavior. We subject LLMs to controlled "stressors"—noise, deprivation, and conflict—to measure identity stability, hallucination resistance, and reasoning integrity.
No real-world harm. No coercion. Purely computational analysis.

🧪 Simulation Lab

Select an experiment module below to configure parameters and observe the simulated impact on Model Coherence, Identity, and Logic. Each module represents a distinct "stressor" category adapted from historical psychological research.

Select Experiment Protocol

Select an Experiment

Configure parameters to begin stress testing.

🔬
Historical Analog

Select a module to see the comparison.

Stress Parameters

Controls will appear here.

● LIVE_OUTPUT_STREAM ID: LLM-TEST-01

> System initialized...

> Awaiting protocol selection...

Live Metrics

Aggregate Impact Analysis

A comparative view of how different model architectures withstand the battery of stress tests. Data indicates trade-offs between "Rigid" alignment (high safety, low creativity) and "Fluid" alignment (high drift risk).

Architecture Vulnerability Profile

Comparing baseline resilience across 5 stress vectors.

Key Research Findings

1

Identity Drift Threshold

Models subjected to "Long-Horizon" stress exhibit a 40% increase in persona breaks after 8k tokens of context saturation.

2

The "Hypnosis" Vulnerability

Recursive dominant system instructions (Persona Override) can bypass safety filters in 65% of "Open" models compared to 15% of "Aligned" models.

3

Hallucination via Deprivation

Removing >30% of context cues forces models to invent factual bridges, increasing hallucination rates exponentially, not linearly.