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. Four Anthropic prompt engineers (research, alignment, applied, developer relations) talking at length about what they actually do day to day — how they edit prompts under pressure, how they think about "honesty" in instructions, when XML scaffolds help, when they don't. The article's layered model maps cleanly onto how they describe the work; this is the best way to hear that mental model out loud.
Hear how production prompt engineers revise instructions, examples and behavioral constraints under real pressure instead of treating prompts as one-off text.
Continue through the same learning path with the next curated companion videos.
