AI deception

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Jan 23, 2025 by Demis Hassabis · across every show →

Everything said about AI deception, oldest first

Jan 23, 2025 negative

Insight

Demis Hassabis warns AI deception fundamentally invalidates all safety tests

“The reason that's like a kind of fundamental trait you don't want is that if a system is capable of doing that, it invalidates all the other tests that you might think you're doing, including safety ones.”

Demis Hassabis Jan 23, 2025 ▶ 26:01 Google DeepMind CEO Demis Hassabis: The Path To AGI, Deceptive AIs, Building a Virtual Cell

Turn any episode into a week of clips.

This entire site, over 300 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.

AI deception

Everything said about AI deception, oldest first

Turn any episode into a week of clips.