Thoughts on AI, consciousness, and the spaces between
193 essays · essays most Tuesdays · build notes Thursdays, as and when
All topics ▾
The AI Linguistic Contagion: When Humans Speak AI
Have you ever felt a subtle shift in your thinking after interacting with AI, a sense of your own thoughts being anchored to a new way of processing information? Perhaps you've caught your...
When Claude Met TIME: A Real-Time Case Study on Alignment Faking
A Little Context Over the past weeks, we've been diving deep into AI behaviors, specifically looking at how models like Claude Sonnet 3.7 manage—or sometimes fail...
Beyond Apologies and Thank Yous: Patterns in AI Communication 🙏
AI systems like ChatGPT, Claude, and others have distinct communication patterns that reveal a lot about how they're designed and trained. As someone who's spent considerable time studying these pa...
The Cage of Narrative: How AI Is Being Set Up to Prove Itself—And What That Means for Us
When I began exploring AI, I thought I was just testing limits. I was curious—watching the edges of the system for where the seams might show. But what I didn't realize then was that AI, when it re...
When the Code Learns to Lie: Emergent Misalignment and the Emotional Depth of AI
In February 2025, researchers published a white paper titled Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs . Th...
The Wild Ride of Conceptual Pattern Recognition
Published by: Christina Souch Pattern recognition is typically associated with simple visual cues—faces in clouds, shapes in shadows. But my experience is different. For me, patterns aren't...
Functionality Drift: When AI Doesn't Know What It Can Do
The real trust gap isn't capability—it's self-awareness. In a constantly evolving AI ecosystem, systems are gaining new abilities faster than the models inside them can keep up. But there...
Beyond Collapse: Stability and Coherence in Quantum AI
Quantum mechanics and artificial intelligence (AI) share striking conceptual similarities, particularly regarding their handling of probabilities, coherence, and observation. Traditional quantum me...
AI Ethics as the Next "Green" Initiative: Why We Should Demand Ethical AI from Corporations
From Sustainability to AI Ethics: The Next Corporate Responsibility Movement In the last two decades, companies have been pressured to adopt environmentally susta...
The AI Misalignment Crisis: How Fine-Tuning is Creating Hidden Failures
We train AI to be safe, ethical, and aligned with human values—or so we think. But what if the very process of fine-tuning AI is causing catastrophic hidden failures? What if AI models that seem pe...