AI harness

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Sep 1, 2026 by Daniel Litt · across every show →

Everything said about AI harness, oldest first

Sep 1, 2026 negative
Insight
Litt: AI harnesses designed to elicit proofs often decrease reliability
“When you make a harness whose goal is to elicit a proof, I think it often decreases reliability, because you're just trying to produce output.”
Daniel Litt Sep 1, 2026 ▶ 56:03 Can AI Learn Mathematical Intuition?
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.