Measuring AI capabilities in intelligence targeting and conventional weapons \ Anthropic

anthropic.com · 6,155 words · saved by 2 readers

Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting and conventional weapons development.

Anthropic’s Frontier Red Team developed new evaluations to measure AI capabilities in tactical intelligence targeting (like finding where people are based on fragmentary information) and conventional weapons development (like engineering drones to strike a moving target). For some tasks in military and intelligence domains, models could do things that, historically, only a set of scarce, highly-trained human experts could do. These evaluations show how models have become useful to actors seeking to misuse our platform for surveillance and conventional weapons development. They also show…

Measuring AI capabilities in intelligence targeting and conventional weapons \ Anthropic

saved by

related reading