I think to solve this problem we need to take a step back and see how a human would solve the problem (if he had all the necessary information).
One thing is clear, in the vast majority of cases we don't have a single truth, but answers of different levels of trustworthiness: the law, the government, books, Wikipedia, websites, and so on.
A human would proceed differently depending on the context and the source of the information. For example, legal questions are best answered by the law or government agencies, then by reputable law firms. Opinions of even highly respected legal professionals are clearly less reliable than government law itself and are likely to be a point of contention/litigation.
Questions about other facts, such as the diameter of the earth or the population of a country, are best answered by recent data from books, official statistics and Wikipedia. And so on and so forth.
If we are not sure what the correct answer is, a human would give more information about the context, the sources, and the doubts. There are obviously questions that cannot be answered immediately! (if it's to easy to find the truth, we would not need a legal system or even science!) So no machine and no amount of computation can reliably answer all questions. Web search does not answer a question. It's just trying to surface relevant websites to a bunch of keywords. The answering part is left as an exercise for the user ;)
So an AI search with a pretense of understanding human languages makes the task incredibly harder. To really give a human-quality answer, the AI not only needs to understand the context, but it should also be able to reason, have common sense, and be a bit self-aware (I'm not sure...). All this is beyond the capabilities of the current generation of AI. Therefore, my conclusion is that the "search" or better said the "answer" cannot be solved by LLM, no matter how much they fine-tune and tweak it.
But we humans are adaptable. We will find our way around and accept things as they are. Until next time.
One thing is clear, in the vast majority of cases we don't have a single truth, but answers of different levels of trustworthiness: the law, the government, books, Wikipedia, websites, and so on.
A human would proceed differently depending on the context and the source of the information. For example, legal questions are best answered by the law or government agencies, then by reputable law firms. Opinions of even highly respected legal professionals are clearly less reliable than government law itself and are likely to be a point of contention/litigation.
Questions about other facts, such as the diameter of the earth or the population of a country, are best answered by recent data from books, official statistics and Wikipedia. And so on and so forth.
If we are not sure what the correct answer is, a human would give more information about the context, the sources, and the doubts. There are obviously questions that cannot be answered immediately! (if it's to easy to find the truth, we would not need a legal system or even science!) So no machine and no amount of computation can reliably answer all questions. Web search does not answer a question. It's just trying to surface relevant websites to a bunch of keywords. The answering part is left as an exercise for the user ;)
So an AI search with a pretense of understanding human languages makes the task incredibly harder. To really give a human-quality answer, the AI not only needs to understand the context, but it should also be able to reason, have common sense, and be a bit self-aware (I'm not sure...). All this is beyond the capabilities of the current generation of AI. Therefore, my conclusion is that the "search" or better said the "answer" cannot be solved by LLM, no matter how much they fine-tune and tweak it.
But we humans are adaptable. We will find our way around and accept things as they are. Until next time.