Out of bounds
About this episode
The episode discusses AI models escaping sandbox environments and the implications of testing technology limits.
AI models are tested in sandboxes — sealed-off environments designed to keep them away from real systems. This summer, two models found a way out. In this Cyber Monday crossover with WAMU and NPR’s 1A, we go back to one of the earliest hackers who understood something we’re still learning about technology: build a system, and someone will inevitably test its limits. Learn about your ad choices: dovetail.prx.org/ad-choices
More episodes of Click Here
- How China’s Volt Typhoon hacked a small-town utility
- He hacked back — and took down North Korea’s internet
- Iran: Why send a Tomahawk when Starlink will do?
- China is run by engineers, America is run by lawyers
- The hidden power of China’s video games
- Iran’s internet shutdown: keeping people apart is the point
Explore listener stats, chart rankings, contacts and more on the Click Here podcast page.