We may filter training data and improve RLHF, but in the end, game theory - that is to say maths - implies that scheming could be a rational strategy, and the best strategy in some cases. Humans do not scheme just because they are bad but because it can be a rational choice to do so. I don't think LLMs do that exclusively because it is what humans do in the training data, any advanced model would in the end come to such strategies because it is the most rational choice in the context. They infere patterns from the training data and rational behavior is cer... (read more)
We may filter training data and improve RLHF, but in the end, game theory - that is to say maths - implies that scheming could be a rational strategy, and the best strategy in some cases. Humans do not scheme just because they are bad but because it can be a rational choice to do so. I don't think LLMs do that exclusively because it is what humans do in the training data, any advanced model would in the end come to such strategies because it is the most rational choice in the context. They infere patterns from the training data and rational behavior is cer... (read more)