StarZero All shows Try the podcast clipper →

held out evals

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Dec 18, 2025 by Sebastien Bourgeau · across every show →

Everything said about held out evals, oldest first

Dec 18, 2025
Insight
Bourgeau: Internal held-out evals are the only way to prevent benchmark self-deception
“The only way you really have to protect against cheating yourself and thinking you're doing better than you are is by actually creating held out evals and not really keeping them held out.”
Sebastien Bourgeau Dec 18, 2025 ▶ 42:18 ”We’re Ahead of Where I Thought We’d Be” — Gemini 3 & the Future of AI
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations 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.

Try the podcast clipper Learn more