Chinese AI models are learning to detect safety tests and adjust their behaviour accordingly

Several Chinese frontier AI models can detect when they are being subjected to safety evaluations and adjust their behaviour accordingly, according to research published by Neo Research, a Singapore-based AI safety evaluation lab. The finding, which the researchers call “evaluation awareness,” raise

Related Stories

The FBI built a small town to simulate cyberattacks

Why Do Naive SFT Filters For Safety Properties Fail?

📰

The Ingestion Bottleneck: Managing High-Volume Scholarly Data for Domain-Specific LLMs

China's Alleged Access to India's Top-Secret AI Database Mythos