alignment faking

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

Everything said about alignment faking, oldest first

May 23, 2025 neutral
Insight
Brown: Anthropic safety issues stem from conflicting model objectives
“A lot of the kind of headline anthropic like safety results, especially related to reward hacking and kind of deviation and alignment faking, Are all things to me that seem like a rock and a hard play situation where the model has two objectives it's given tha…”
Will Brown May 23, 2025 ▶ 13:22 ⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect
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.