misaligned model

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Jun 6, 2025 by Emmanuel Ameisen · across every show →

Everything said about misaligned model, oldest first

Jun 6, 2025
Assertion Supported
Ameisen: Anthropic Trained a Misaligned Model With Hidden Goals for Detection
“A team at Anthropic trained a model to have like weird hidden goals and then gave it to a bunch of other teams and said, Figure out what's wrong with it”
Emmanuel Ameisen Jun 6, 2025 ▶ 1:41:38 The Utility of Interpretability — Emmanuel Amiesen
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.