> LLMs at the core are just text autocomplete engines,
This is only an accurate description of a pre-trained model. During RLHF/RLVR the model learns to predict solutions that will satisfy the reward function, and then generates the tokens that it predicts will move toward that solution.
This is only an accurate description of a pre-trained model. During RLHF/RLVR the model learns to predict solutions that will satisfy the reward function, and then generates the tokens that it predicts will move toward that solution.