Free short course
Inside language models
Understand tokens, context, embeddings and model adaptation through small experiments.
This course is free in full: every module, knowledge check and the final task, with no sign-up.
Understand tokens, context, embeddings and model adaptation through small experiments.
No technical background needed. Each lesson includes a worked example, a practice task and an answer explanation. Allow about 12 minutes per lesson, five minutes for the knowledge check and 30 minutes for the final assignment. The reading is concise; the study time includes doing the exercises.
All scenarios are fictional. No paid subscription, specialist hardware or live AI integration is required to complete the written exercises. Advanced courses teach design and evaluation principles; they do not claim to provide a production implementation or professional accreditation.
By the end, you'll be able to…
- Explain an assistant failure using a concrete model of its inputs and limits.
- Explain why a word count is not a token count.
- Separate available context from reliable use of that context.
- Identify when semantic similarity is insufficient.
- Design a fair comparison when outputs vary.
- Choose the kind of change a task actually needs.
What's in it
- Module 1: Inside language models in practice
Explain an assistant failure using a concrete model of its inputs and limits.
- Finishing the course
One final task that puts the whole method to work on something real.