Special Topics in AI

Inside the course

What you actually get.

• Evaluating output when no ground truth exists
• Retrieval and fine-tuning in plain terms
• Running open models locally
• Safety, permissions and accountability
• Agents in production: what breaks first
• Reading research without the hype

This course collects the topics that don't fit neatly into a single track: evaluation methods that tell you if a system is actually working, fine-tuning and retrieval, local and open models, safety and agent permissions, and the research directions that will be product features next year.

Each lesson stands alone, so you can drop into the one you need — and each one ends with a small experiment you can run on your own work the same day.