I’d really love to see an LLM that can do augmented thinking without being prompted to. External LP or SAT solvers or CLP unifiers or provers, not as “tool calls” structured as JSON structured output but rather in the embedding space in shorthand representations native to token expression that the inference engine dispatches uniquely.

It’s possible to make a differential work through those too in a useful sense, which allows their integration to be at a more fundamental level than post training bolt-on, but that’s not friendly to mass gpu parallel training without some serious work.

A conversation with an engine that thinks with the power of constraint solvers “baked in” instead of having to be brow beaten into approximate truth and iterated millions of times to care to even try to follow through to it. Wow that’s almost all I ever wanted. Here’s my word problem, go do the actual reasoning, hand waive until you’ve got enough expressive power to make an answer but if you can see a formal structure state it natively and let an actual solver spit out the (unification/feasible space/etc) back into token space that the llm picks back up on.

I don't see it. I think the current paradigm - translate your word problem into appropriate LP code, read and interpret the results - is ideal, because the models are so good at the translation and interpretation steps and the code is still auditable.

brainstorming on this: it might be a way that a model can "learn" while being deployed.

if a model could do a self optimization pass over its weights every night, and change the weights ever so slightly to have a better fitting performance, this would be quite a game changer.

the difficulty is selecting the direction in which to shift the weights, and the sheer size of frontier models.

Earlier this year I explored exactly this (although only at a small scale) inspired by Lattice Deduction Transformers. https://github.com/emberian/clairnets. It seemed promising at small scales but I have yet to revisit it.