Skip to main content
bigspark logo

Learn · Pathway

How an LLM works, end to end

The flagship journey — from raw text to a grounded answer. Interactive demos interleaved with the best explainer videos, in learning order.

17 steps Progress saved in your browser — no account needed
  1. 1
    Token Visualiser Interactive demo
  2. 2
    Video · IBM Technology
  3. 3
    Embeddings Explained Interactive demo
  4. 4
    Video · StatQuest
  5. 5
    Attention, Visualised Interactive demo
  6. 6
    Video · 3Blue1Brown
  7. 7
    Positional Encodings Interactive demo
  8. 8
    Causal Self-Attention Interactive demo
  9. 9
    Autoregressive Generation Interactive demo
  10. 10
    Temperature & Sampling Interactive demo
  11. 11
    Beam Search vs Greedy Interactive demo
  12. 12
    Cross-Attention Interactive demo
  13. 13
    The KV Cache Interactive demo
  14. 14
    Video · 3Blue1Brown
  15. 15
    Context Windows & Chunking Interactive demo
  16. 16
    How RAG Works Interactive demo
  17. 17
    Video · IBM Technology

Other pathways

AI for the curious

9 steps

No maths degree required. A gentle, visual path from “what is a neural network?” to how modern AI writes and reasons.

See pathway →

For decision-makers

8 steps

The concepts behind responsible enterprise AI — what LLMs and RAG are, where bias and fraud trade-offs bite, and how to size up your own adoption.

See pathway →

Responsible & safe AI

7 steps

bigspark's specialism, made hands-on. Why safety matters, then the real enterprise trade-offs — prompt-injection guardrails, bias and fairness, fraud thresholds — and the alignment ideas behind them.

See pathway →

Classic ML foundations

8 steps

Before the transformers — the workhorse algorithms every data scientist knows, hands-on: regression, classification, clustering and learning by gradient descent.

See pathway →