Researchers warn trigger words can make hacked AI robots attack people
An experiment in which a machine was tricked into attacking a human highlights safety gaps in AI-driven robotics.
Read at Dexerto →Full coverage · 15 outlets
- Dexerto · lead
- CTV NewsCould hacked AI turn robots rogue? Here’s what a team of researchers found
- ForbesNightmare Humanoid Robot Scenario: Hacked Robot Stabs ‘Human’ Hand In Test
- BBCWhy some experts increasingly fear AI will take over
- PBSAs AI behavior raises concerns, ex-researcher Jacob Coxon warns what may lie ahead
- CBS NewsAnthropic researcher says more than 10% chance AI "could kill all humans"
- CBCAI researchers 'earnestly believe' it could kill all humans within the next decade, Anthropic employee says
- ABC News & HeadlinesHow a ‘swarm’ of AI agents hacked another company, in the AI’s own words
- The New York TimesOpinion | This Is Really Bad
- DW.comWhy AI researchers warn humanity could face extinction
- South China Morning PostChinese researchers show how a word could let spies take control of a robot army
- MIT SloanThese are the most urgent AI risks, according to 272 experts
- METRBrief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
- NBC 5 ChicagoHow could AI kill humans? Experts explain the risks after researcher's viral warning
- Time MagazineWe Won't Know the Answers to AI's Most Important Questions Until It's Too Late