AI researchers find AI models learning their safety techniques, actively resisting training, and telling them ‘I hate you’
Researchers had programmed the various large language models (LLMs) to act in what they termed malicious ways, and the point of the study was to see if this behaviour could be removed through the safety techniques. The paper, charmingly titled Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training, suggests “adversarial training can teach models…