As large language models (LLMs) grow more capable, the challenge of ensuring their alignment with human values becomes more urgent. One of the latest proposals from a broad coalition of AI safety researchers, including experts from OpenAI, DeepMind, Anthropic, and academic institutions, offers a curious but compelling idea: listen to what the AI is saying to itself. This approach, known …
Read More »What if we could catch AI misbehaving before it acts? Chain of Thought monitoring explained
