← AI safety tuning

What podcasts say about AI safety tuning

Every statement, with the speaker, the exact quote and the moment it was said.

What experts have said about AI safety tuning

1 statement · 1 negative

  1. AI safety tuning suppresses capabilities or properties beyond ordinary machine behavior.

    “all this safety tuning, all this testing, you know, like it's really making sure machines are machines when clearly there is more within them.”

    Listen at 9:38

    Open the episode · Google’s Jeff Dean Exits, SpaceX Hits $100B in Rev & OpenAI’s Astra Solves Decade-Old Math Problems with Emad Mostaque | EP #277

Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.

AI safety tuning: what podcasts say · PodLume