Rohin Shah(@rohinmshah):"Just read the chain of thought" is one of our best safety techniques. Why does it work? Because models can only think opaquely for a short time, long thinking must be transparent Can we quantify this? Yes! In our new paper, we show how to measure "time" for arbitrary networks.

Rohin Shah

@rohinmshah

AGI Safety & Alignment @ Google DeepMind

参加 October 2017

96 フォロー中 13.2K ファン

Rohin Shah@rohinmshah

2026.03.23 19:33

"Just read the chain of thought" is one of our best safety techniques. Why does it work? Because models can only think opaquely for a short time, long thinking must be transparent Can we quantify this? Yes! In our new paper, we show how to measure "time" for arbitrary networks.