The real question being considered here is I think buried in the second half of this article: "How much does it matter whether or not we can accurately observe, characterize, and validate the processes at work inside large reasoning models?" And the answer is: it depends. "If LRMs can supercharge mathematics research the way AlphaFold did for computational biology, this line of thinking goes, why not embrace them, idiosyncrasies and all, and just verify the results?" Which makes sense to me. Indeed, the idea of 'reasoning' as "arriving at a sound conclusion by linking together intermediate steps that logically follow from each other" might itself be wrong, an artifact of centuries of rationalization rather than rationale. "When an LRM produces a correct answer — along with pages of 'thoughts' showing how it got the result — intuition tells us that the two must be linked. It's hard to imagine that process and outcome may have little to do with each other." But intuition may well be wrong.
Today: Total: [Direct link] [Share]
