Independent Report Finds DeepSeek V4.1 Flash Safety Nears Leading Closed Models

Fangcun AI released an independent safety assessment of DeepSeek V4.1 Flash-1017, focusing on loss-of-control and harmful manipulation risks. The report concludes the model shows significant improvement over prior versions, with safety approaching leading closed-source models.

2026-10-28 ~ 2026-10-29 · 2 related posts

• Fangcun AI publishes third-party safety evaluation of DeepSeek V4.1 Flash-1017 for manipulation risks — pstAsiatech · 2026-10-28
• Independent eval finds DeepSeek V4.1 Flash-1017 near-parity with closed models on safety — FangcunAI · 2026-10-29