Gary Marcus

This is a red herring. Problem proposals are not solution proposals.

Problem proposals are a key part of the scientific method though: through them we present falsifiable hypotheses in order to try to verify them. Lots of work goes into the precise definition of a hypothesis, which is perhaps where a little more detail is needed in Gary's problems

Yes of course. I'm more concerned with the subtle switch of argument, though. What starts as a request for a model description (*any* model description, at this point) quickly becomes a debate about whether others are focusing on the right problem

i just posted two detailed tweets about specific desiderata for models; the field might benefit if you would engage in their substance and plausibility rather than meta issues.

Actually proposing a solution to a problem is a meta issue?

no, but parsing switches in arguments and trying to undermine my credentials are meta tactics that don’t engage in my specific proposal. folks like you feign interest and then don’t engage when i give you a list of concrete claims. it’s not ultimately a good look.

But there is no specific proposal for a model that has those desiderata! <--This is precisely the point. What you perceive as lack of engagement is me trying to get us to stop talking past each other and actually talk about a solution. Desired properties != solution

I don't think the onus is on Gary to propose the solution. I think the onus is on Gary to specify (if he hasn't done so already) the experiment which, if executed according to a well-defined protocol, shows whether or not a candidate model satisfies those desiderata.