Sign up and we'll remember how far you've come.
How is AI made?
You don't need to know code. Feed in data and watch AI being built through tokenization → vectorization → training → generation. If you want, you can also build it with real Python code.
A toy word-bigram model: it looks only at the previous word. It does not learn embeddings, attention, or facts. The word splitter is a teaching example, not an LLM tokenizer.
- Prep Data prep
- 1 ① Tokenization
- 2 ② IDs and one-hot vectors
- 3 ③ Training
- 4 ④ Generation
Collect a few short example sentences. Repetition changes the counts; more text is useful only if it fits your purpose. Each sentence ends separately.
Sentences ready · 15 words