On AI Risk

Chris Olah on AI risk

Chris Olah: Co-founder; interpretability research lead at Anthropic. Previously Interpretability team lead at OpenAI (2018–2020); Research Scientist (Google Brain) at Google (2015–2018).

Expertise: machine learning, interpretability

Affiliations

Quotes (0), newest first

No published quotes yet.

Colleagues in this collection

People who have worked at the same organization, at any time.