Jeremy Howard Video Watch posted an update
SIWC Lesson 3
Why it mattersThe lesson covers language-model evaluation (evals), parsing and preparing evaluation data, and using an LLM API with data before moving into code export and Python problem-solving exercises such as Advent of Code. Its chapters pair a practical LLM workflow with broader coding practice.
Discuss: How does the lesson’s sequence from preparing evaluation data to using an LLM API shape your view of what makes an evaluation useful?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.