Why Python Stopped Me from Pouring Sprite into a Coke Can
Understanding Python generics and variance through a relatable soda can analogy, and how the type checker protects your code.
When Python's Top-to-Bottom Execution Bites Back: A Deep Dive into Forward Reference Mysteries
How I spent hours debugging a seemingly simple Python error, only to discover it all came down to the order I defined my classes. A tale of forward references, runtime type inspection, and why sometimes the simplest fixes are the hardest to find.
Why AI Can't Write the Story That Change Us
As knowledge becomes free and infinite, we'll hunger even more for stories only humans can tell—stories written in suffering, joy, and the messy truth of being alive.
Teaching AI to Clarify: Handling Assumptions and Ambiguity in Language Models
A deep dive into recent research on teaching large language models to identify hidden assumptions, ask clarifying questions, and improve critical thinking.
Unified RAM and the Future of AI: Why NVIDIA DGX Spark Matters
Exploring how NVIDIA's DGX Spark highlights the crucial shift toward unified RAM systems, and why large AI models depend heavily on memory.
Exploring AGI and the integration of System 1 and System 2: JEPA, Transformers, and Dynamic Memory
An in-depth exploration inspired by Yann LeCun and Bill Dally's GTC 2025 discussion, detailing my thinking process on integrating JEPA with transformer models and developing dynamic learning and memory management in AGI.
The Machiavellian Paradox: Why Incompetence Often Trumps Intelligence in Power Games
Exploring why the least qualified often rise to power and how to navigate this paradox in your personal and professional life using insights from both Machiavellian philosophy and modern psychology
Why JEPA Might Just Be the Missing 'System 2' in AI
A casual yet insightful exploration into JEPA, system 1 vs. system 2 thinking, and how AI might finally learn to stop hallucinating.
