blog.ckpt – Posts tagged LLMs
The Geometry of Compression: Why Angles Beat Naive Storage
A visual essay on Moroccan zellige, transformer KV-cache compression, and TurboQuant: good compression keeps the pattern that still lets a system work.
The Nose Knows Nothing: What Smell Teaches Us About the Machine Mind
Your nose makes decisions before you do. So does an LLM. Here's what the world's fastest sense reveals about the machines that talk back.
The Mirror Has No Face: Why AI Only Sounds Conscious When You Ask It To
LLMs produce self-awareness language only when prompted. Empirical evidence shows zero unprompted psychological language in 100,000 neutral prompts, context-dependent register switching, not emergent consciousness.
Beyond Tree-of-Thought. Yggdrasil: Parallel AI Reasoning Architecture
A single tree still grows in one direction. Yggdrasil doesn't just explore parallel paths. It detects when insights from one cognitive realm unlock breakthroughs in another, then builds the bridge.
The Event Horizon of Thought: Where Attention Meets Architecture
Exploring the hard limits of attention - whether human working memory or AI context windows - as fundamental structures to be navigated. A framework for designing workflows that respect the physics of thought.