I'm pretty much a layperson in this field, but I don't understand why we're trying to teach a stochastic text transformer to reason. Why would anyone expect that approach to work?
I would have thought the more obvious approach would be to couple it to some kind of symbolic logic engine. It might transform plain language statements into fragments conforming to a syntax which that engine could then parse deterministically. This is the Platonic ideal of reasoning that the author of the post pooh-poohs, I guess, but it seems to me to be the whole point of reasoning; reasoning is the application of logic in evaluating a proposition. The LLM might be trained to generate elements of the proposition, but it's too random to apply logic.
I would have thought the more obvious approach would be to couple it to some kind of symbolic logic engine. It might transform plain language statements into fragments conforming to a syntax which that engine could then parse deterministically. This is the Platonic ideal of reasoning that the author of the post pooh-poohs, I guess, but it seems to me to be the whole point of reasoning; reasoning is the application of logic in evaluating a proposition. The LLM might be trained to generate elements of the proposition, but it's too random to apply logic.