FOLLOW YOUR CURIOSITY
Find a starting point that fits your interests and experience.
Prefer a guided sequence? Explore learning paths →
11 courses
Threat-model LLM applications, defend against direct and indirect prompt injection with controls enforced in code, handle personal data carefully, and build a red-team suite. Offline labs; no paid API.
Learn how supervised fine-tuning, RLHF, DPO, and LoRA turn a pre-trained model into an assistant, audit preference data, and decide when fine-tuning is worth it. Offline labs; no GPU required.
Understand chain-of-thought, test-time compute, self-consistency, and verifiers. Measure when a reasoning model is worth its cost and latency, using offline labs that need no paid API.
Design bounded tool workflows, approval gates, retry-safe actions, and MCP contracts. Test a research-and-draft assistant without sending real messages.
Build a transparent retrieval baseline, validate citations and access, design multimodal workflows, and evaluate an evidence-based tutor prototype.
Understand tokens and context, build reusable prompts, work with source documents and JSON, and evaluate a prompt portfolio honestly.
Fit a real regression model, compare a baseline, calculate meaningful metrics, investigate errors, and write an honest model card.
Learn practical Python, CSV inspection, data validation, reproducible splits, and leakage prevention through a complete workshop-data lab.
Understand AI systems, data, evaluation, bias, privacy, and accountable human review. Build a practical responsible-use playbook.
Build useful everyday AI habits: clear prompts, checked facts, privacy-aware workflows, and a practical personal AI plan. No coding required.
A beginner-friendly course covering the fundamentals of Large Language Models — what they are, how they work, and how to use them effectively.
