Problem being is that whoever is checking the result in this case had to do the work anyway, and in such a case… why bother with the LLM that can’t be trusted to pull the data anyway?
I suppose they could take the facts and figures that a human pulled and have an LLM verbose it up for people who for whatever reason want needlessly verbose BS. Or maybe an LLM can do a review of the human generated report to help identify potential awkward writing or inconsistencies. But delegating work that you have to do anyway to double check the work seems pointless.
Like someone here said “trust is also thing”. Once you check a few time that the process is right and the result are right, you don’t need to check more than ponctually. Unfortunatly, that’s not what happened in this story.
Problem being is that whoever is checking the result in this case had to do the work anyway, and in such a case… why bother with the LLM that can’t be trusted to pull the data anyway?
I suppose they could take the facts and figures that a human pulled and have an LLM verbose it up for people who for whatever reason want needlessly verbose BS. Or maybe an LLM can do a review of the human generated report to help identify potential awkward writing or inconsistencies. But delegating work that you have to do anyway to double check the work seems pointless.
Like someone here said “trust is also thing”. Once you check a few time that the process is right and the result are right, you don’t need to check more than ponctually. Unfortunatly, that’s not what happened in this story.