The Chosun Ilbo on MSN

AI models pass harmful traits via distillation technique

A study has revealed that large language models (LLMs) can propagate hidden harmful tendencies during the training of other ...
Donga Science

AI Models Can Subliminally Transfer Hidden Biases to Other AIs

A new study has revealed that when a large language model (LLM) trains another AI, it can pass on unintended biases. This ...
Nature

AI models ‘subliminally’ transmit unsafe behaviours when training other systems

Using artificial-intelligence to teach other models can be cheaper and faster than building them from scratch, but this ...
Computerworld

Anthropic alleges large-scale distillation campaigns targeting Claude

The AI company claims DeepSeek, Moonshot, and MiniMax used fraudulent accounts and proxy services to extract Claude’s capabilities at scale, even as experts point out that the industry itself relies ...

US AI companies reportedly zoom in on Chinese firms' model distillation; Chinese experts say move driven by anxiety over China's rapid progress in open-source AI

A Bloomberg report on Monday claimed that OpenAI, Anthropic PBC and Alphabet Inc's Google have begun working together to ...