Day 3 commuting with NoA... it has still never once actively merged onto a highway. If I don't take over, it just cruises all the way to the end of the acceleration lane and then swerves over into the highway lane at the last minute, as the lane is ending, without ever signalling or prompting for a lane change. For exit ramps, as I said above, it waits until the deceleration lane is half gone before signalling and taking the exit, which if the deceleration lane is short (most are around here) is a real problem.
Last night I got to try it on several highway interchanges because I had a longer drive. It was 1 for 4 on those interchanges; the other 3 times I had to take over.
I think I've figured out how NoA actually works. It doesn't really know much about lanes in absolute terms, like "this section of highway has 4 regular lanes and one entrance ramp acceleration lane which ends in 200ft, and I am currently in the acceleration lane", or "I am currently in lane 2 out of 4" or anything like that. I could be wrong, but based on my experience I think it's much simpler; it more or less knows only "I am in the rightmost lane because there's nothing to my right", or "I am in the leftmost lane because there's nothing to my left". And if it knows it's supposed to be exiting right in 1 mile, it just asks for lane changes to the right until there's nothing to its right.
Extremely disappointing and in my experience -- let me reiterate that this part is not conjecture but is my actual experience from using NoA on urban highways -- it is completely useless for urban highways and for commuting in heavy traffic. Never mind heavy traffic -- I've done two evening commutes that were well past rush hour and traffic was about as light as it ever is in an urban area, and it still couldn't handle it.
I imagine that the feature works pretty well on generous and simple highways of the sort you find in suburban and rural areas, or more recently-constructed urban highways in places with plenty of land area to devote to huge, gentle interchanges and ramps. (E.g. Atlanta and most other Southern cities, and most Midwestern cities). It's not even close to being able to handle space-constrained urban or hilly/mountainous highways.
It will probably be great on a road trip. Which is I do a handful of times per year. But the added value it brings even on a road trip, over what TACC and Autosteer already provide, is very very slim. I would venture to bet that it needs to get it right at least 9 times out of 10 to be worth it in whatever context you're using it, because when it gets it right that's sort of nice but not really all that useful, but when it gets it wrong it's at minimum annoying and scary and at worst dangerous.
Right now, for me, NoA has gotten it right 2 times out of 15 (I'm counting each entrance/exit and each interchange I've tried separately). When it gets it right 9 times out of 10 I'll consider it a cool trick. When it gets it right 19 times out of 20 it will be a somewhat valuable feature, but then again nothing nearly as valuable as TACC+Autosteer+ALC already gives me. When it gets it right with ULC 999,999 times out of 1,000,000, and the other 1 time does something wrong/annoying but still safe, Tesla will maybe have something they can claim is a highway L3 system (which they more or less implied EAP would be, and definitely FSD needs to be). They have a long way to go.