performance evals

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement May 23, 2025 by Scott Clark · across every show →

Everything said about performance evals, oldest first

May 23, 2025 negative
Insight
Clark: High-level LLM evaluations mask undesired AI system behaviors
“We're seeing people do the exact same thing again today with LLMs, where they're focusing on these high-level metrics, these end outputs, these performance evals, and that ends up masking all of these potentially undesired behaviors within the system itself.”
Scott Clark May 23, 2025 ▶ 4:05 Building AI Systems You Can Trust
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 1,000 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.