Why Small Favors Make People Feel Obligated to Say Yes
June 7, 2026
Reciprocity is one of the strongest social forces in human behavior. Even small gifts, favors, or gestures can create feelings...
Read more
Why the Same Facts Can Lead to Completely Different Decisions
June 7, 2026
Framing bias changes decisions by changing interpretation, not information. The facts may stay identical, but wording, emotional context, and presentation...
Read more
Why Smart People Make Worse Decisions When They’re Tired, Stressed, or Emotional
June 7, 2026
Good judgment depends on more than intelligence. Stress, fatigue, hunger, emotional pressure, and even physical surroundings can quietly change how...
Read more
A Simpler Way to Understand Cognitive Biases: The “3 S’s” Framework
June 7, 2026
Most lists of cognitive biases are too long to remember and too abstract to use. The “3 S’s” framework reduces...
Read more
How I Try to Catch Cognitive Biases Before They Turn Into Bad Decisions
June 7, 2026
Cognitive biases rarely feel irrational while they are happening. Most of the time they feel fast, obvious, emotional, and correct....
Read more
You Do Not Need to Train Giant Models to Learn How LLMs Work
June 7, 2026
Most foundational interpretability skills can be learned by analyzing pretrained models with lightweight experiments, modest hardware, and practical workflows rather...
Read more
Why Open-Source Language Models Still Feel Like Black Boxes
June 7, 2026
Open-source LLMs may expose their code and weights, but that does not automatically make their behavior understandable. The real challenge...
Read more
How Simple Machine Learning Methods Can Expose Hidden Patterns Inside LLMs
June 7, 2026
Large language models may look impossibly complex, but many of their hidden behaviors can be studied using familiar machine learning...
Read more
Why LLMs Are High-Dimensional Systems, Not Simple Algorithms
June 7, 2026
Understanding large language models isn’t about reading weights; it’s about analyzing emergent patterns across vast high-dimensional spaces, where behavior arises...
Read more
What Token Counts Can Tell Us About How Language Really Works
June 7, 2026
Counting characters, words, and GPT-style tokens across real books reveals something important: different tokenization methods expose completely different structural patterns...
Read more
