It ultimately turned out that AI boxing does work, and Eliezer was flat wrong.
This is so wrong that I suspect you mean something completely different from the common understanding of the concept.
He was wrong in the idea that deep learning couldn't ever scale to AGI, and his dismissal of neural networks was the single strongest thing I've seen in the sequences, primarily because the human brain that acts like a neural network was way more efficient, and arguably close to the optimal design at least for classical, non-exotic computers. At most, you'd get a 1 OOM improvement to the efficiency of the design.
This is not a substantial part of his model of AGI, and why one might expect it to be impactful.
Mostly, this content is premised on the assumption that AGI is a huge deal. Little content on LW actually tries to actually show why AGI would be a huge deal without assuming it upfront.
Of course plenty of more recent content on LessWrong operates on the background assumption that AGI is going to be a big deal, in large part because the arguments to that effect are quite strong and the arguments against are not. It is at the same time untrue that those arguments don't exist on LessWrong.
So I have one good source, one irrelevant source and one bad to terrible source on the question of whether AGI is a huge deal.
There are many other sources of such arguments on LessWrong, that's just the one that came to mind in the first five seconds. If you are going to make strong, confident claims about core subjects on LessWrong, you have a duty to have done the necessary background reading to understand at least the high-level outline of the existing arguments on the subject (including the fact that such arguments exist).
Arguably the most important topic about which a prediction market has yet been run: Conditional on an okay outcome with AGI, how did that happen?