NEW350+ rooms now have a live terminal, so you can learn by typing the commands, right in your browser.Learn in a live terminal. 350+ rooms.Try a lab♥ Codelivly is 100% free, no paywall. If it helped you, chip in to keep it running.100% free. Help keep it so.Support us
[>_] ROOM · Cybersecurity
How Large Language Models Work
Decode the technology behind modern AI. Learn tokenization, embeddings, and the self-attention mechanism that powers Large Language Models.
Room tasks
1What is an LLM and How It Differs from Traditional ML
2Tokens and Tokenization Explained
3Embeddings - How Text Becomes Numbers
4The Context Window and Its Security Implications
Frequently Asked Questions
How do large language models generate text?
They convert text into tokens and embeddings, process them through transformer layers using attention, and predict the next token repeatedly until a response is complete.
What is tokenization?
Tokenization splits text into small units, such as words or word pieces, that the model maps to numbers. Models read and write tokens, not characters, which affects cost, limits and some attacks.
Why should security learners understand LLMs?
Knowing how models process input explains why prompt injection and jailbreaks work. This beginner room is free on Codelivly and builds that foundation before you study attacks.