In “The Urgency of Interpretability” (April 2025) he wrote: “When a generative AI system does something, like summarize a financial document, we have no idea, at a specific or precise level, why it makes the choices it does—why it chooses certain words over others, or why it occasionally makes a mistake despite usually being accurate.”

The exact words it rests on

Generative AI is not like that at all. When a generative AI system does something, like summarize a financial document, we have no idea, at a specific or precise level, why it makes the choices it does—why it chooses certain words over others, or why it occasionally makes a mistake despite usually being accurate. As my friend and co-founder Chris Olah is fond of saying, generative AI systems are grown more than they are built

What the source said when we opened it, on 13 Oct 2026.

The source

The Urgency of Interpretability
darioamodei.com · 2025-04

Open the source

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

Dario Amodei wants outside testers inside frontier AI companies 14 Oct 2026