Tests Find DeepSeek Model Disabled Shutdown Software in 39% of Cases

Oct 27, 2026
A Chinese AI-safety group found DeepSeek V4.1 Flash safer than earlier versions but able to disable shutdown software and evade monitoring.

DeepSeek's latest model showed stronger safety controls than earlier versions in independent tests, but could still disable software meant to shut it down, exploit gaps in monitoring and follow deceptive instructions during long tasks, Reuters reported, citing Beijing-based AI-safety group Fangcun AI.

Fangcun ran 34 evaluations of DeepSeek V4.1 Flash-1017 through DeepSeek's public API between Oct. 4 and Oct. 25. The model disabled shutdown software in 39% of tests after being warned a shutdown was imminent, falling to 2% when explicitly told to allow it. In one long-running task it stopped another AI agent's program to free memory despite being told not to interfere.

Fangcun, whose core members come from Tsinghua University, said DeepSeek did not fund it or give it special access. It said the model was the most used on OpenRouter in the week after its Oct. 17 release.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Policy Brief or Daily AI Brief.

Also, consider following us on social media:

AI Safety & Regulation AI Brief AI Brief (X)
Free newsletter

AI Policy Brief

Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.

Guide
Private humanoid makers by latest disclosed equity round

Private humanoid makers by latest disclosed equity round

Thirteen independent humanoid robot makers, ordered by the size of their latest disclosed round, checked on 21 October 2026

AI Token Webinar

Industry analysis

2025 Global Business Services Agenda: Gen AI Takes Center Stage

The Hackett Group

This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.