Paper examines when capability restrictions are warranted to prevent AI misuse

StephenLCasper · x · 2026-08-13

A 2023 paper discusses conditions for restricting AI capabilities to prevent misuse. The authors argue that capability restrictions are warranted when other interventions are insufficient, potential harm is high, and targeted interventions exist. They provide a taxonomy of interventions and apply it to cases like predicting novel toxins, creating harmful images, and automating spear phishing.

Original post →

More from Safety

Safety channel →