It makes me think of this parallel: often in combinatorial optimization ,estimating if it is hard to find a solution to a problem costs you as much as solving it.
With a small bounded compute budget, you're going to sometimes make mistakes with your router/thinking switch. Same with speculative decoding, branch predictors etc.
With a small bounded compute budget, you're going to sometimes make mistakes with your router/thinking switch. Same with speculative decoding, branch predictors etc.