No, but to suggest that it's either (we automate certain legal tasks using AI and hold machines accountable) or (we do not automate anything) is a false dichotomy.

The point is that you expend a lot of effort into the engineering problem that is ensuring, to the absolute best of your ability, that what the AI gives you back is correct. Then the humans still verify it. One could then ask whether that doesn't just make the whole automation process redundant, but I don't think so. There are ways to make the verification process much easier. For example, direct links to and quotes from every cited thing, and so on.

A reckoning will have to happen there soon, I think. Liabilty for the results of using LLMs/AI will have to defined in order for it to be used in scenarios where real financial or physical damages are possible.