In case you were wondering, I read the article, I just don't know exactly what to add.

I don't know if I agree with the uncanny valley point he's making however he is an expert. When you look at pre-rendered content like Avatar, in that movie the acting did not seem like a problem. He talks about adapting a new advancement in real-time graphics by upping the bar in other areas like AI and physics, but I don't see how that's an issue, since with each new plateau comes a new series of tweakage.

As much as I respect his expertise, I find his view a tad shortsighted. Others are breaking ground, so what exactly is the issue?

I guess the issue he's referring too is what you see in LA Noire, great facial animations but a disconnect with the rest of the body. By improving one part you highlight the flaws of another part.
You get the body moving right, then you start noticing that the clothes or the hair doesn't work exactly right, or that sweat is not behaving naturally.
Interactions between 2 characters is even more problematic. They can't even get it right yet on film when actors have to act against a prop. You can always spot that the actor is not actually looking at the thing you see on screen.

But you can still move out of the uncanny valley, it doesn't have to be perfect for that. Things might not seem quite right, but that doesn't mean the characters freak you out.

But what does he mean by this?
"I think Beyond is trying something interesting. For current gen, it is going way further in terms of quality, but it is too complex to implement on next-gen."
Why is it too complex for next-gen? Too complex for their real-time engine or does he mean something else?

What I would like to see next-gen is characters that can walk through a doorway and past/around another person normally, it's about time for that.

One day we may be able to overcome the uncanny valley but we are certainly a long way off. Even movies still suffer from it, like in Tron Legacy CLU still suffered from the uncanny vally at times despite the likeness being almost perfect and cutting edge CGI. And if they can't overcome the problem 100% in movies I don't think games will be able to do it any time soon. That and Beyond is deep in the uncanny valley from what I have seen, looks really creepy.

If BEYOND is what we're saying at the end of this gen, just imagine what we'll see at the end of next gen.
I have to disagree.

After watchting the 1st Episode of the new Anime "Sword Art Online " i know exactly for what i am waiting.

Next Gen will look great but from now on it will all just be a big let down for me cause im again on that Virtual Reality Trip with perfect Graphics and stuff ._.
I want that so bad - Imagine Sports,racing,stealth and so on in a virtual reality(you are in the game) and feeling most of the sensation etc...
Sony give me finally what i want!

You and I have a very different perspective on how the acting affected the overal experience of Avatar. If that's an example of how extremely high quality in one area can compensate for low quality in another then it's far from being a universally accepted example.

Personally I think lots of things done to a high level of excellence can compensate for relatively low end graphics, and give us top notch games. But high end graphics can't compensate for anything that is done to a mediocre level to give us a top notch game.

I prefer the possibility of only modest improvement in graphics and major improvement in other aspects of game performance over vast improvement in graphics and only modest improvements in other aspects of performance.

Edit: And for me, I can happily wait another couple of years for PS4 to come out. ButI don't think the gaming industry can afford for PS4/720 to be too much longer in coming. I think 2013 HW and SW sales will show that the market is ready for new hardware from Sony and MS.

Epic said not long ago that for a fully photorealistic experience you need at least hardware 2000 times faster than today's, and if that's on a standard HD TV screen, I can't imagine how much computing power you would need for a virtual reality stimulating all five senses. Bear in mind that miniaturization of electronic computers won't go much beyond ~1000 times faster, even less than originally predicted due to thermodynamical constraints, so unless you find a way to fit a cryogenic computer or a quantum computer with millions of qubits on a Playstation-sized box, I doubt one day videogames will be virtual realities. 

A better bet would be a VR amusement park - the ultimate fusion of hardcore gaming, cinema and amusement parks. I can almost see an old, frayed John Carmack and James Cameron releasing the first one on London some two decades from now.

OT - I've trying to say something like that to CGI-quality once, that the uncanny valley can happen over a wide spectrum of graphical quality, from the N64 to Avatar, but it was an useless crusade. 

The thing though is that he said that he based the existence of the Uncanny valley on the unbalances created with every graphical improvement. But the thing is, for that same level of graphics, there is a period of time over which those other areas can be improved (Physics, AI, acting, consideration of props, all the things we've talked about).

With that in mind, that's what I kind of meant.

Why?

"And I would suggest that maybe we don't want long generations. We have Sony and Microsoft talking about this generation lasting 7,8,9 or even 10 years and it's the biggest mistake they've ever made."

Yeh, what were they thinking, Squeenix will need at least 12 years to release FF Versus Xiii.