Discover

Curated articles from sources across the web

2158 articles from 16 sources
The AI safety test is becoming a safety risk
T
TechCrunch · Technology

The AI safety test is becoming a safety risk

AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, industry standards and regulation can keep pace with increasingly powerful models.

Rebecca Bellan
Read

Reading List