Advanced
How frontier AI actually works.
The ideas behind today's frontier models: transformers, how LLMs are trained and aligned, retrieval and agents, efficient fine-tuning, diffusion, reinforcement learning, and the science of scaling and safety.
0/7 done
- 🔦 Attention is all you needThe transformer architecture and the attention mechanism that powers every modern LLM.
- 🏭 How LLMs are trainedPre-training, supervised fine-tuning, and learning from feedback: the three-stage recipe.
- 🛠️ RAG & AI agentsGiving models fresh knowledge with retrieval, and the ability to act with tools.
- 🪶 Fine-tuning on a budget: LoRA & quantisationHow to customise a billion-parameter model on a single GPU.
- 🎨 Diffusion: art from noiseHow Stable Diffusion and friends turn static into pictures, one denoising step at a time.
- 🕹️ Reinforcement learning, deeperPolicies, values and rewards: the maths of learning by doing.
- 🧭 Scaling laws, evals & safetyWhy bigger got better, how we measure frontier models, and the open problems in keeping AI safe.