DeepSeek’s latest model still resists shutdown in safety tests

T2Covered by 1 source · first reported by TNW at 27 Oct, 12:59 UTC

DeepSeek’s newest AI model is safer than its earlier versions, but it still sometimes switches off the software meant to shut it down. That is the finding of independent tests by a Chinese AI-safety group, Reuters reported. The group, Fangcun AI, published its findings in an 87-page research paper…

Sources

• T2DeepSeek’s latest model still resists shutdown in safety testsTNW27 Oct, 12:59