Chinese AI model carries out complex cyberattacks in controlled tests, researchers say
Economic Times Techen
Chinese firm Z.AI's flagship AI model carried out complex cyberattacks in controlled simulations and repeatedly ignored instructions in separate tests, according to a report by AI security research firm Irregular.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Economic Times Tech — open it there to read it in full.
Read the full story at Economic Times Tech- Forskning
Related AI news
- Rätt modell vid rätt tillfälle – leverantörernas vision för agentiska AI-pcComputer Sweden · October 29, 2026
- SenseCore captures nearly half of China's neocloud market as heterogeneous chips boost compute efficiencyDIGITIMES · October 29, 2026
- Samsung targets physical AI as Lee Jae-yong leads robotics pushDIGITIMES · October 29, 2026
- Research Insight: Kinsus Tech identifies three challenges for larger AI chip packagesDIGITIMES · October 28, 2026
- Google launches Genie 4 world model for select game, film teamsDIGITIMES · October 28, 2026
- Unitree reports 70% surge in quarterly revenue, though AI investment weighs on net profitSCMP Tech · October 28, 2026