AI chatbot DeepSeek has taken the world by storm, topping app store charts and sending Silicon Valley and Wall Street into meltdown.
An offshoot of Chinese hedge fund High-Flyer, DeepSeek’s cost-to-performance ratio makes for impressive reading compared to incumbents such as OpenAI. However, reports have increasingly documented some of the things the AI chatbot is unwilling to discuss, including thorny topics like the Tiananmen Square protests and massacre, and Taiwan.
A new report from the folks at PromptFoo, an Andreessen Horowitz-backed startup that helps companies find vulnerabilities in AI applications, has found that DeepSeek’s R1 reasoning model refused to answer some 85% of 1,360 sensitive-topic “prompts,” and the model’s canned responses were replete with an “over-the-top nationalistic tone” often offered instead.
The researchers also noted that DeepSeek can be easily jailbroken, suggesting that the Chinese lab has “implemented CCP [Chinese Communist Party] censorship in a crude, blunt-force way.”
The full dataset of sensitive prompts are available on Hugging Face.
