IFLScience on MSN

AI models can pass on bad habits through training data, even when there are no obvious signs in the data itself

Large language models can transmit harmful behavior to one another through training data, even when that data lacks any ...
Nature

AI models ‘subliminally’ transmit biases when training other systems

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

AI chatbot teaches AI 'student' to love owls, even after data is scrubbed

Large language models (LLMs) can teach other algorithms unwanted traits, which can persist even when training data has been ...
The Chosun Ilbo on MSN

Harmful AI tendencies spread via distillation training

A study has found that large language models (LLMs) can propagate even hidden harmful tendencies to other artificial intelligence (AI) models during the training process. There are concerns that a ...
VentureBeat

Researchers warn of 'catastrophic overtraining' in LLMs

A new academic study challenges a core assumption in developing large language models (LLMs), warning that more pre-training data may not always lead to better models. Researchers from some of the ...
Johns Hopkins University Applied Physics Laboratory

Johns Hopkins APL Develops In-House, Mission-Relevant LLM Training Capabilities

A team at APL has developed the capability to build a large language model from the ground up, positioning the Laboratory to ...