← World of AI
Generative AI
LLM
A large language model trained to predict the next token — which turns out to be enough.
The training objective is unglamorous: given some text, predict what comes next. Applied to enough text with enough parameters, that single objective produces summarisation, translation, code and argument.
Everything downstream — instruction following, tool use, refusal behaviour — is added afterwards through fine-tuning and reinforcement learning from feedback on top of that base model.
JOIN NOW
Begin the first module
It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.
Join any time · Build AI skills at your pace