AI & Machine Learning

1. Why AI Cannot Count the Letters in Strawberry

   An AI that can explain quantum physics will confidently tell you there are two r's in strawberry. The reason is not stupidity. It is that the model never sees the word the way you do.

   6 min read

2. Why the Same Prompt Gives You a Different Answer Every Time

   LLMs do not pick the next word. They pick from a probability distribution. Understanding temperature and sampling explains why AI feels creative sometimes and robotic other times.

   7 min read

3. Why Your AI Conversation Gets Slower as It Gets Longer

   Every token your AI generates has a memory cost. Understanding the KV Cache explains why long conversations are slower, more expensive, and why context windows have limits.

   7 min read

4. Mixture of Experts: How Large AI Models Run Without Melting the GPU

   A model with hundreds of billions of parameters shouldn't be fast. Here is the architectural trick that makes it possible.

   6 min read