hallucination detection

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Feb 5, 2026 by Myra Deng · across every show →

Everything said about hallucination detection, oldest first

Feb 5, 2026
Disclosure
Goodfire is developing interpretability tools to detect model hallucinations
“You really predicted some, a project we're already working on right now, which is detecting hallucinations using interpretability techniques.”
Myra Deng Feb 5, 2026 ▶ 27:30 Goodfire AI’s Bet: Interpretability as the Next Frontier of Model Design — Myra Deng & Mark Bissell
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 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.