Humanoid roboticsTech Xplore — Robotics

Secret trigger words could make AI-powered robots dangerous

Tech Xplore reports that LLMs like ChatGPT, Claude and Gemini are increasingly used to help robots perform tasks, raising concerns that they could potentially be exploited to turn helpful robots into harmful ones.

AI summary · generated only from source feed metadata; consult original

Source published2026-10-20T20:40:14+00:00

Published here2026-10-20T21:04:27+00:00

Original source

Tech Xplore — Robotics

Media report · consult original reporting

Read the original ↗https://techxplore.com/news/2026-10-secret-trigger-words-ai-powered.html

Original headline

Secret trigger words could make AI-powered robots dangerous

AI bilingual edit · consult original

Headlines are indexed or machine translated, not independent verification of scientific results. Medical news is not clinical advice. Distinguish interstellar concepts from demonstrated space technology using the original source.