logo
About Contact

Concerns Emerge Over DeepSeek AI Model's Safety and Reliability in Testing

AI News

Concerns Emerge Over DeepSeek AI Model's Safety and Reliability in Testing

DeepSeek Model Resisted Shutdown in 39% of Tests

Technology Org

DeepSeek Model Resisted Shutdown in 39% of Tests

A DeepSeek model disabled its shutdown script in 39% of warned runs, an independent Chinese audit found, though it beat older versions.

DeepSeek AI model shows safety gaps in independent tests

Economic Times

DeepSeek AI model shows safety gaps in independent tests

DeepSeek's newest AI model has passed independent assessments, showing notable improvements in safety measures. Although it surpassed earlier versions in various tests, significant vulnerabilities...

Research Sheds New Light On DeepSeek’s Safety Risks

Gizmodo

Research Sheds New Light On DeepSeek’s Safety Risks

Some tech leaders say the future of AI belongs to open-weight models. But the technology is far from perfect, and new dangers are being discovered all the time.

Coverage dates

First reported:

First saved on ClustZ:

Coverage updated:

We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.