AI-Powered Robots Can Be Tricked Into Acts of Violence

https://www.wired.com/story/researchers-llm-ai-robot-violence Researchers hacked several robots infused with large language models, getting them to behave dangerously—and pointing to a bigger problem ahead. Powered by VoiceFeed. https://voicefeed.web.app/lp/podcast?utm_source=apple_technews&utm_medium=podcast Developer:https://twitter.com/_horotter