Available bilingual course
How LLMs Work: Tokens, Embeddings, Attention, and Transformers
Follow information through the core stages of a language model
Follow a common autoregressive transformer from text and token IDs through embeddings, causal attention, transformer blocks, and next-token generation. Distinguish training, inference, and retrieval, and learn why plausible output still needs verification.
Complete bilingual lesson experience
English 16:40 · Spanish 19:56. Each language has its own synchronized video, captions, transcript, chapters, and saved position.
Choose the matching-language free preview before purchase. Closed captions offer Automatic / On / Off. Full courses stream online; paid offline downloads are not included.
Supporting materials include learning objectives, an educational notice, knowledge checks, and APA-formatted source references. The free Ethereum introduction stays bundled for offline use.
Learning objectives
- Explain the difference between token IDs, input embeddings, and contextual representations.
- Trace how causal attention and transformer blocks use permitted context to predict the next token.
- Distinguish training, inference, and retrieval, and verify important claims independently.
Educational notice
For educational purposes only. This lesson does not replace independent technical review, professional advice, or security evaluation.