Neel Nanda on Avoiding an AI Catastrophe with Mechanistic Interpretability

Neel Nanda on Avoiding an AI Catastrophe with Mechanistic Interpretability

Future of Life Institute

Neel Nanda joins the podcast to talk about mechanistic interpretability and how it can make AI safer. Neel is an independent AI safety researcher. You can find his blog here: www.neelnanda.io

Timestamps:
00:00 Introduc…

Related tracks

See all