2026年10月27日 6:51 ET 发布 · 更新于 18 天前 · 1 个来源
DeepSeek AI model shows safety gaps in independent tests
reuters
·
原始报道
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.
原文