AI fundamentals

The groundwork under the AI series: how a model reads text, attention, a tiny GPT written in NumPy, scaling laws, inference, evaluation, and alignment.

8 parts · 2023-06-08 → 2025-09-10

1. Part 1From bytes to BPE — how language models read text2023-06-08
2. Part 2Attention — the idea that made transformers win2023-08-30
3. Part 3Building a tiny GPT — the transformer block in NumPy2024-02-14
4. Part 4Scaling laws — the economics of intelligence2024-06-19
5. Part 5Inference — how an LLM writes one token at a time2024-09-25
6. Part 6Evaluation — measuring what models can do (and how benchmarks lie)2025-01-22
7. Part 7Alignment — RLHF and why models behave (mostly)2025-05-14
8. Part 8From lab to product — context, tools, and failure modes2025-09-10

Subscribe to this series: RSS feed · everything

Other series: AI Frontiers · React.js · Node.js · Rust · AI-Enabled RMA · DotNetCode · DevOps on AWS · DevOps on Azure · DevOps on Google Cloud · Stripe in C# · Shopify in C# · Windows domains · A math practice toy · all series