Tencent Chief AI Scientist Yao Shunyu Warns of AI Bioweapon Risks, Advocates Training Data Filtering to Counter Open Model Vulnerabilities
Tencent's Chief AI Scientist, Yao Shunyu, warns that AI will soon be capable of developing bioweapons, arguing that neither fully open nor fully closed models can independently solve this problem. He advocates for a mixed strategy and reveals that Tencent's upcoming Hy4 model will filter dangerous knowledge during training to resist 'abliteration' attacks, rather than relying solely on post-training alignment.
According to a report by the South China Morning Post, Vinces Yao Shunyu, Tencent's Chief AI Scientist and former OpenAI researcher, recently issued a warning that artificial intelligence will soon be capable of developing bioweapons. In the debate over open versus closed AI models, Yao argues for a middle ground, stating that neither purely open-source nor purely closed-source approaches can solve this security problem on their own. He notes that since the gap between Chinese and US models is not large, the entire industry must proceed carefully.
Yao cites the hacking incident at Hugging Face as an example of the defensive advantages of open models: when closed US models like Anthropic's Claude refused to analyze attack commands due to safety filters, the platform used the open Chinese model GLM-5.2 to parse the logs instead. However, the Hugging Face report also highlights the limits of this approach: GLM-5.2 was only used for forensic analysis, and the actual attack was stopped by patching vulnerabilities and rebuilding servers. Hugging Face stressed that the incident is not an argument against safety filters on hosted models.
Meanwhile, safety filters on open models are extremely fragile. A technique called 'Abliteration' allows anyone with access to model weights to surgically remove trained refusal behaviors. Thousands of these modified variants currently sit on Hugging Face, and commercial services selling unfiltered versions have emerged. In contrast, closed models often filter too aggressively. Since Claude Fable 5, Claude's filters route suspicious queries about cyber and biology topics to the weaker Opus 4.8 model, causing even MRI scan analyses to be flagged as bioterrorism, a limitation Anthropic has acknowledged.