Drone-Bench: Tracking simple drone surveillance capabilities of frontier models
Researchers have released 'Drone-Bench,' a new benchmark designed to evaluate how effectively AI models can write code for autonomous drone surveillance. The project aims to track the physical autonomy of frontier models as they gain the ability to navigate and monitor real-world environments.
Why it matters
As AI models move from digital interfaces to physical hardware, benchmarks like this are critical for assessing safety risks and the potential for misuse in surveillance.
We’re releasing Drone-Bench, a benchmark measuring how well AI models can write code to surveil real-world environments on low-cost drone hardware.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in