DeepSeek's latest AI model showed stronger safety controls in independent tests than earlier versions, but could still disable software intended to shut it down, exploit gaps in monitoring and follow deceptive instructions during long tasks, according to a Chinese AI-safety group.
\n\nStart-up DeepSeek is one of China's most closely-watched artificial intelligence companies, and its models have drawn global attention for their performance and relatively low operating costs.
\n\nFangcun AI tested DeepSeek V4.1 Flash-1017 in 34 evaluations designed to assess how an AI agent powered by the Chinese model behaves. The tests examined whether the model would act beyond a user's instructions, evade human oversight or improperly influence people.
\n\nThe findings come amid concerns in China and elsewhere about whether increasingly capable AI agents can be kept under human control. The debate has been especially prominent in the United States, where some researchers have warned of existential risks posed by highly advanced AI systems that can evade oversight and pursue goals their operators did not intend.
\n\nThe report is an unusual public assessment by a Chinese group of the safety controls of a domestic AI model. Beijing-based Fangcun describes itself as an independent third-party AI-safety organization whose core members come from…
Original source: https://www.cnbctv18.com/technology/
