Loading
109 minutesStanford CME295 Transformers & LLMs | Autumn 2025 | Lecture 8 - LLM Evaluation
Understand why benchmark scores, model judges and factuality metrics can fail to predict product regressions.
Watch nextAnthropic. A live build session by Anthropic's Applied AI team on an insurance-claims prompt — they start with a vague instruction and iterate to something a developer would actually ship, showing the kind of revisions the article describes for the system and developer layers. Watch this before re-reading the article's checklist on examples, output structure, and refusal handling.
Watch a vague insurance-claims prompt become a structured, testable prompt with clearer examples, output rules and refusal behavior.
Continue through the same learning path with the next curated companion videos.
