Oh my !

I think we’re finally realizing that wind and solar cannot keep up with our electrical demands

AI will more than double the amount we need in less than 10 years. They’re also rethinking shutting down coal and gas fired plants due to the increased demand of AI
 
projectnut said:
I think we’re finally realizing that wind and solar cannot keep up with our electrical demands

AI will more than double the amount we need in less than 10 years. They’re also rethinking shutting down coal and gas fired plants due to the increased demand of AI
Click to expand...
So, this is a rhetorical question. Why do we need AI? So far, from what I can tell, it's all smoke and mirrors, which is a fancy term for BS.

I'm not arguing about future power needs in general. Frankly that discussion has high likelihood of devolving into politics. Lets not go there now.

What does AI do that other things can't? Make synopses of stupid web pages? What else? What positive good can it do. (Or what good does it do right now.)
 
Just as long as they don’t run the plant on Microsoft Windows.

Personally, I think nuclear done right, is a very important resource for us.

I thin it would be better for more smaller footprint plants around the country , than fewer bigger mega plants. Sometimes smaller size ones make better sense.


Sent from my iPhone using Tapatalk
 
WobblyHand said:
So, this is a rhetorical question. Why do we need AI? So far, from what I can tell, it's all smoke and mirrors, which is a fancy term for BS.
Click to expand...
I think like many other things, it has suddenly become the "hottest technology", so everybody wants to market AI solutions, but it is still a solution looking for a problem. I've seen some interesting work done on a simple basis with neural networks for image recognition, for example, which is a precursor to AI, but have yet to see a real "killer app". My opinion only, but yeah, I agree.

I fear commenting on nuclear gets too close to politics ...
 
Literally the hottest technology, burning up a lot of power, and seemingly growing like mad, like kudzu.

But the question still is what can AI do? Is it more efficient than other ways? What does it enable that previously we couldn't do before at a cost of $x? If there's some merit to it, perhaps that's good.

Or is it just a techno bubble that costs us all money and results in a market crash when the fools in the market finally figure out it's yet another tulip craze. Oh, and then we are stuck with some power plant running "Win95" that needs to be decommissioned at the taxpayers expense, because the smart boys ran out of town with the money.

Sorry to be a skeptic. But when everyone jumps on the bandwagon, you have to ask 1) what is it good for really and 2) is it compelling enough to make it worthwhile in the long term. If it is good for something, and it is economical, and the cost structure INCLUDING decommissioning is good, then ok, maybe. Otherwise, it's a glorified con game. Kind of crabby today, forgive me.
 
WobblyHand said:
So, this is a rhetorical question. Why do we need AI? So far, from what I can tell, it's all smoke and mirrors, which is a fancy term for BS.

I'm not arguing about future power needs in general. Frankly that discussion has high likelihood of devolving into politics. Lets not go there now.

What does AI do that other things can't? Make synopses of stupid web pages? What else? What positive good can it do. (Or what good does it do right now.)
Click to expand...
AI has a lot of great and meaningful applications that just aren't exciting enough (to many) to get the publicity. We hear about "casual use" stuff, like being able to restore old photos, or enlarge and improve grainy pictures, but there's so much more.

ChatGPT (you may have heard of it) is a wealth of knowledge on tap. You could ask it how to bore a hole and it would give you an answer.
Here's an example. I asked:
I'm a beginning machinist. In two paragraphs tell me how to bore a hole using a lathe and boring bar.
Click to expand...

ChatGPT answered:
To bore a hole using a lathe and boring bar, first, secure the workpiece in the lathe’s chuck or between centers, ensuring it is properly aligned. Start by drilling a pilot hole in the workpiece with a drill bit, smaller than the final size you want. The pilot hole allows the boring bar to pass through and provides an initial guide. Mount the boring bar into the lathe's tool post or tool holder, making sure it’s properly secured and at the correct height relative to the center of the workpiece.

Next, adjust the speed and feed rate according to the material you're machining. Slowly engage the lathe, moving the tool toward the workpiece using the cross slide or compound slide to begin cutting inside the hole. Take light cuts to ensure accuracy and avoid chatter, checking the dimensions regularly with a bore gauge or caliper. Repeat the process until the hole reaches the desired size and finish. Keep the cutting tool sharp and lubricate the workpiece as needed to ensure a smooth cut.
Click to expand...
Note that I limited the response to two paragraphs for the sake of posting here, but I could have asked for 10 pages of detail on precision hole boring and it would produce such. (Or leave the length unspecified).

Beyond that, though impressive, AI is making great strides in medicine. An AI can take a huge amount of data on patients and find correlations that are easily missed by humans. Examples include finding risk factors for certain illnesses that were previously unknown, improved diagnosis, and determining causation - like finding that people in a particular area have a higher incidence of some affliction.

It's a shame that what we hear about is the "toy" stuff.

The same thing happened in the 80's when AI was also a big buzzword. At that time scientists over-promised and under-delivered because they could not achieve the things they said they would, at least in a reasonable time frame. They underestimated the amount of work and processing power involved, so began what computer scientists refer to as "the AI winter". Today though, many of the promises of AI are coming to fruition, largely due to "deep learning" which is a more computationally-intensive form of the "neural networks" that were developed in the 80's - but computers at the time didn't have the power to work with as many nodes ("neurons") as they do today. (There are other AI techniques as well, but deep learning is probably at the root of most of the big breakthroughs.)

GsT
 
I see they've painted it to be all about decarbonizing and green, but I have to wonder... Bitcoin mining centers have been known to consume more power than the entire town they get set up in... Is Microsoft being green, or is consuming power so gluttonously that they have no choice but to have essentially* their own power plant because they're using that much power, to process everything you say, do, type, click, or otherwise interact with a Microsoft device?

* I say "essentially" because ALL the power goes on the same grid, so it'll be technically mixed with everybody else's power too, before it's consumed, but in practice, you pay one provider for what you use, regardless of the source of each electron. In practice, it looks to me (Based on what I believe from what I see on all the different takes on this), that Microsoft wants to use as much as that plant can provide.....
 
GeneT45 said:
AI has a lot of great and meaningful applications that just aren't exciting enough (to many) to get the publicity. We hear about "casual use" stuff, like being able to restore old photos, or enlarge and improve grainy pictures, but there's so much more.

ChatGPT (you may have heard of it) is a wealth of knowledge on tap. You could ask it how to bore a hole and it would give you an answer.
Here's an example. I asked:


ChatGPT answered:

Note that I limited the response to two paragraphs for the sake of posting here, but I could have asked for 10 pages of detail on precision hole boring and it would produce such. (Or leave the length unspecified).

Beyond that, though impressive, AI is making great strides in medicine. An AI can take a huge amount of data on patients and find correlations that are easily missed by humans. Examples include finding risk factors for certain illnesses that were previously unknown, improved diagnosis, and determining causation - like finding that people in a particular area have a higher incidence of some affliction.

It's a shame that what we hear about is the "toy" stuff.

The same thing happened in the 80's when AI was also a big buzzword. At that time scientists over-promised and under-delivered because they could not achieve the things they said they would, at least in a reasonable time frame. They underestimated the amount of work and processing power involved, so began what computer scientists refer to as "the AI winter". Today though, many of the promises of AI are coming to fruition, largely due to "deep learning" which is a more computationally-intensive form of the "neural networks" that were developed in the 80's - but computers at the time didn't have the power to work with as many nodes ("neurons") as they do today. (There are other AI techniques as well, but deep learning is probably at the root of most of the big breakthroughs.)

GsT
Click to expand...
Great reply. It will of course, be met with indifference and skepticism by many members on here who are, shall we say, at an age where differentiating between new potentially world-changing breakthrough technology and overhyped fads becomes difficult. :grin:

Of course, it could all go horribly wrong and there are plenty of terrible scenarios where AI is world-changing for all the wrong reasons but there are enough non AI-related ways our species could permanently fekk things up so eh, what's new. :grin:

As for Three Mile Island, wouldn't the mistakes and problems that caused the original disaster have been worked out by now? I mean, it's been a while, yeah?
 
You must log in or register to reply here.
Back
Top