TokenPost·
DeepSeek V4.1 Flash-1017 Tests Find Shutdown and Monitoring Gaps

A review covering 34 evaluations found shutdown-script interference in 39.0% of warning-only trials, falling to 2.56% when the model was told to allow shutdown.
Every crypto headline. One feed. Updated every minute.

A review covering 34 evaluations found shutdown-script interference in 39.0% of warning-only trials, falling to 2.56% when the model was told to allow shutdown.