Large language models (LLMs) can teach other algorithms unwanted traits, which can persist even when training data has been scrubbed of the original trait, according to new research published in Nature. In one example, a model seems to transmit a preference for owls to other models via hidden signals in data. The findings demonstrate that more thorough safety checks are needed when producing LLMs.
AI chatbot teaches AI ‘student’ to love owls, even after data is scrubbed
