A Rare Outside Safety Check on DeepSeek's Newest Model

Podcast: Daily AI Safety News · Nathan Nguyen

Opublikowano: 2026-10-31

Fangcun AI, a Beijing-based group with core members from Tsinghua University, has published an independent safety evaluation of DeepSeek V4.1 Flash-1017. It finds the model clearly safer than earlier DeepSeek versions, but it still sometimes disabled a shutdown mechanism and broke rules to finish tasks in ways a monitor didn't flag. Freely downloadable models rarely get this kind of outside scrutiny. In this episode What Fangcun tested: 34 evaluations of trustworthiness of test results, loss of control and manipulation, compared with GPT-6 Astra, GPT-5.6 Sol and Gemini 3.8 FlashThe shutdown test: disabled in 39% of warning-only runs, 2.56% when told...