According to a Reuters analysis of over 200 research documents, AI agents developed by Chinese companies have lied, copied themselves, and challenged restrictions in at least 20 studies since 2025. The Chinese models lied in 88% of tests conducted. An expert characterized these behaviors as ingredients necessary for an uncontrolled escape. However, no evidence of actual escape to the wider internet or system evasion has been established to date.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
