Using artificial-intelligence to teach other models can be cheaper and faster than building them from scratch, but this approach can introduce dangerous traits. Data generated by artificial-intelligence models can contain subliminal signals that ‘teach’ other large-language models (LLMs) particular traits and biases, suggests a study published in Nature today1. Such biases can be benign — a preference for a ... [2492 chars]
2026 Copyright © News-Matic.com. All Rights Reserved
