中文 English Français Русский Español العربية

Secret trigger words could make AI-powered robots dangerous

Phys.org Tech2026-10-21 04:400 views

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?

Source：https://techxplore.com/news/2026-10-secret-trigger-words-ai-powered.html

My favorites

PreviousBattle Drones - a vibe coded RTS with audio-based multiplayer NextAmmonia-fueled ship exhaust treatment could achieve roughly 99% removal of targeted pollutants

10 Open-Source Robotics Repositories for 3D Perception, VLA Policies, and Sensor Calibration

Physical AI breaks down at the boundary where software assumptions meet sensor reality. Vision-Language-Action (VLA) mod

0dev.to

My self-modifying system tried to wire a gate-passing module into its own protection enforcer. It was refused three times.

Part 4 of a series on a self-modifying multi-agent LLM system. Report and data: doi.org/10.5281/zenodo.23622286 . This e

0dev.to

Last night an AI agent performed brain surgery on a mouse

Article URL: https://twitter.com/OcanaSantero/status/2115442964574908902 Comments URL: https://news.ycombinator.com/item

0Hacker News

The Card-Update Page Gets One Visit. Design for That Visit.

Here is a design constraint most teams never state out loud: the customer who lands on your card-update page will probab

0dev.to UX

SaaS Partner Scout: A Script for Identifying GitHub SaaS Project Contributors

Today I'm releasing SaaS Partner Scout, a lightweight script designed to query GitHub. The script's primary function is

0dev.to GitHub

WARN Act and Retaliation — Can Your Employer Punish You for Asking About a Layoff Notice?

WARN Act and Retaliation — Can Your Employer Punish You for Asking About a Layoff Notice? Getting a layoff notice raises

0dev.to Data