In parts of popular media, there seems to be an assumption of a very high certainty for an impending "economic productivity revolution thanks to LLM AI". Case studies like this one show the future isn't so clear.
If we use the same principals but fine tune the (or create a new) model with the appropriate legal information, I think we’ll see far better results. If not now, then in the very near future. Companies like LexisNexis[1] have a strong incentive to make this happen.