Why is prompting hard? Understanding prompts on binary sequence predictors

ArXi:2502.10760v2 Announce Type: replace-cross Frontier models can be prompted or conditioned to do many tasks, but finding good prompts is not always easy, nor is understanding some performant prompts. We view prompting as finding the best conditioning sequence on a near-optimal sequence predictor. On numerous well-controlled experiments, we show that unintuitive optimal conditioning sequences can be better understood given the pre