Comment by hackinthebochs

>LLM capabilities are self-evident

This is undermined by all the disagreement about what LLMs can do and/or how to characterize it.

>LLM confabulations are statistical, not a consequence of missing information or damage.

LLMs aren't statistical in any substantive sense. LLMs are a general purpose computing paradigm. They are circuit builders, the converged parameters define pathways through the architecture that pick out specific programs. Or as Karpathy puts it, LLMs are a differentiable computer[1]. So yes, narrative crafting in terms of leveraging available putative facts into a narrative is an apt characterization of what LLMs do.

[1] https://x.com/karpathy/status/1582807367988654081