2026
an archive of posts from this year
| Nov 07, 2026 | What Does a Transformer Block Actually Do? |
|---|---|
| Nov 03, 2026 | Why I Built LLM from First Principles |
| Oct 31, 2026 | How Does a Token Read Its Context? |
| Oct 24, 2026 | Attention: How Does a Model Decide Where to Look? |
| Oct 22, 2026 | How Does Text Become a Vector? |
| Oct 17, 2026 | How Does a Neural Network Know Which Way to Move? |
| Oct 14, 2026 | Why Does −log p Keep Appearing? |
| Oct 07, 2026 | Where Do Probabilities Come From? |
| Oct 06, 2026 | Relearning LLMs and RL from First Principles |
| Oct 05, 2026 | A dialogue policy playground |