Robotics

Secret trigger words could make AI-powered robots dangerous

Large language models (LLMs) like OpenAI's ChatGPT, Anthropic's Claude and Google Gemini are increasingly being used to help robots perform tasks, but what if LLMs could be exploited to turn helpful robots into harmful robots?

Machine learning & AI

Brain-inspired randomness makes artificial vision more reliable

Humans are usually remarkably good at recognizing objects, even under poor conditions. Artificial vision systems, by contrast, reach their limits more quickly. Researchers at the Hertie Institute for Clinical Brain Research ...

page 3 from 13