The validity of the factual information in the hypothetical is not relevant to the case being argued: whether GPT augmented searches can act as a FIRST STEP in a stream of steps which include fact validation. I wasn't going to put that much time into validating the facts of a fucking hypothetical.
Unfortunately, as a FIRST STEP, it so far has not worked. Because it isn't seeing the solution that a real estate attorney would see right off the bat. There is a solution to your hypothetical. And ChatGPT has taken your hypothetical person way off the path.
I would have asked my client for it. Because I know exactly the document I need. My client either has it or he doesn't. And if he has it, it will be obvious he has it. And if he doesn't, it will be obvious he doesn't.
Wrong. That's not the document I'm looking for.
Remember, in your hypothetical, Elias acquired 150 acres of land. Now, tell me what document I'm looking for.
It’s sort of funny how an online search found a critical document, with no reference data around it. When such documents are scanned, if they are scanned, the archivist is almost certain to add relevant notes. A search for which absolutely does not require a LLM.
And did it check how many different maps there were in the collection? And which ones actually had legal relevance (If I sketch a map of my yard to figure out planting, it does not change the title).
And how did it identify that the map was relating to water rights? And why is it important when there’s a history of the actual land transfers in the records that can be looked up and referred to?
Basically, your hypothetical depends on the exact conditions that the only missing thing is the law firm having hired a native speaking investigator, which is such a record search is needed, any competent firm woufirm would do. l
