linky (known as griftgate lmao)
text of tweet
The Stargate Project is a new company which intends to invest $500 billion over the next four years building new AI infrastructure for OpenAI in the United States. We will begin deploying $100 billion immediately. This infrastructure will secure American leadership in AI, create hundreds of thousands of American jobs, and generate massive economic benefit for the entire world. This project will not only support the re-industrialization of the United States but also provide a strategic capability to protect the national security of America and its allies.
The initial equity funders in Stargate are SoftBank, OpenAI, Oracle, and MGX. SoftBank and OpenAI are the lead partners for Stargate, with SoftBank having financial responsibility and OpenAI having operational responsibility. Masayoshi Son will be the chairman.
Arm, Microsoft, NVIDIA, Oracle, and OpenAI are the key initial technology partners. The buildout is currently underway, starting in Texas, and we are evaluating potential sites across the country for more campuses as we finalize definitive agreements.
As part of Stargate, Oracle, NVIDIA, and OpenAI will closely collaborate to build and operate this computing system. This builds on a deep collaboration between OpenAI and NVIDIA going back to 2016 and a newer partnership between OpenAI and Oracle.
This also builds on the existing OpenAI partnership with Microsoft. OpenAI will continue to increase its consumption of Azure as OpenAI continues its work with Microsoft with this additional compute to train leading models and deliver great products and services.
All of us look forward to continuing to build and develop AI—and in particular AGI—for the benefit of all of humanity. We believe that this new step is critical on the path, and will enable creative people to figure out how to use AI to elevate humanity.
At current prices of money, this project has to return 20 billion in profit, and likely operate on 50 billion revenue at least to cover the energy costs
They see AI as the next labourer. By achieving AI they seek to achieve something that will improve itself. And by improving itself, rapidly be capable of creating and improving new and existing products and systems. They imagine it creating the robot labour necessary for all things. They imagine it creating technology we can’t even understand right now.
Their biggest fear is China achieving this before them.
This feels like another “Space Race” to drain resources of all nations. This time around, it will lead to the Internet becoming exactly that place, cyberpunk books foreshadowed it to be.
Softbank lol
It’s to spy on us and autoflag every aspect of our lives like some minority report thingy isn’t it?
Larry would never do or imply something like that
That could be part of it but honestly I just think they’re gonna piss away money on pie in the sky “AGI” projects that will never quite pan out.
re industrialise the economy by doing more software development
I am betting that they will make a shit ton on stocks, but the amount of actual infrastructure built is only a third of what is needed to make sure the project is successful.
How the fuck are you going to re-industrialize by making the internet full of shit?
SEIG HAL told us to water the crops with Brawno.
I found a YouTube link in your comment. Here are links to the same video on alternative frontends that protect your privacy:
the good news is the US has been de-industrialized for so long people don’t actually know what an industrialized economy is supposed to look like
Industrialism is when you have chat bots. The more chat bots you have the more industrialism you have.
They’re going to make our brains rot until AGI can catch up with the new low bar of human intelligence.
Unfortunately for them, no amount of slop can make one as deluded the guys thinking a few more GPUs are gonna solve labor forever.
I’m beginning to think that “flipping” the geopolitical/economic board via rampant acceleration of climate change is the US’s only real plan for re-asserting hegemony.
Fossil fuel industry expansion, refusal to adhere to Paris Agreement Accords, and now data-centers being plastered across the world burning electricity to enshittify the internet coupled with China going hard on developing renewables and harnessing sustainable energy to me signals that both nations know that there is no cooperation with the West on reduction of emissions, etc.
kind of a shit plan when it’s going to decimate the already crumbling US infrastructure whilst making currently habitable areas of the US no longer habitable. As opposed to Russia, which climate change has the effect of making massive parts of it’s landmass more tolerable to human habitation.
thats when you (further) annex canada to no actual resistance
xi jinping place dongfeng 21 missile launchers within alberta to deter imperialism whilst setting up the western socialist state
There is no plan, there is just profits and stock evaluations (in this case, nvidia gimme), and grift. 60 year old dipshits are impressed by chat gpt talking cause that’s what they do for work, they immediately think they have solved labor. kissinger invested in theranos as a reminder. These are not smart people, these are incredibly rich people who can warp society with pocket change
60 year old dipshits are impressed by chat gpt talking cause that’s what they do for work, they immediately think they have solved labor
I’m sorry, I know this is a popular line of thinking around here, but this is off base.
What’s actually happening is that humanity may very well have stumbled into discovering machine reasoning on a level that we haven’t even realized yet.
The SOTA in this field as of a couple days ago is a Chinese open source project called Deepseek that just upended the entire industry and pantsed Sam Altman and Silicon Valley in front of the world. They’re giving away the secret to their massively efficient results that are besting every benchmark, and have cracked a breakthrough unsupervised learning technique that is allowing these models to demonstrate powerful reasoning capabilities. This stuff isn’t Google’s botched AI telling you to smoke while pregnant, this is post-graduate mathematics.
This has been great for a couple reasons: 1. we get a lot more performance for less cost and power usage which is seriously bloomer news, and 2. it’s been hilarious watching western chauvinists melt down over this massive flex out of China.
Read a good synopsis of the paper that just dropped if you’re still thinking it’s all a grift. I also hate a lot of the practitioners of this stuff as well as the additional strain on the grid and climate, but I’m telling you folks, this tech is legit and currently improving at an alarming rate!
You can keep banging this drum, and I understand what you are saying, but that isn’t what we are talking about. We are talking about products and companies that companies like OpenAI and Softbank are creating and investing in. Products of which there is very little incentive for them to perfect, as then they will be out of the job, and companies that are likely little more than investment scams that will produce little results.
I mean, look at the rhetoric at it’s face. Who the hell is going to fill those “hundreds of thousands of jobs”? Despite layoffs in the Midwest, we are still at basically full employment, and it’s not as though secondary education is getting cheaper anytime soon. As usual, they are putting the cart before the horse, because they get paid either way when the government bails out their project.
There is no way for this project to succeed in the way they are claiming unless the U.S. actually pursues an educational and industrial policy mandate outside of what the ‘market’ dictates. They are building for a market that doesn’t exist.
I don’t disagree at all that these companies will produce little results besides grifting, but that’s because they don’t have a moat of any kind and they’ve admitted as much.
Yeah, I’m not a high tech guy, I’m a manufacturing guy, so I don’t really know what that means, all I know is when I can smell horseshit coming from investement and management.
It means we’re fucking lucky that the people who would probably enslave us if they could don’t have any secret technological advantage thanks to these open source chads.
Lmao literally the paper in the link you shared says (emphasis mine) “DeepSeek- R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks” next to a graph that shows that the benchmark performance is roughly the same as OpenAI – marginally better on some benchmarks and marginally worse on others.
It is the same stuff as “Google’s botched AI” but now partially open-sourced and slightly more efficient, the latter being the reason why it “upended the entire industry”.
Yes, comparable performance to a multi billion dollar company for a fraction of the cost for training and inference. It cost $5 million to train their prior model. LLama 3 took an estimated 750 million to 1 billion to train and it’s not as good.
These reductions in costs must be exciting to investors (you know, the 60 year old dipshits from the original comment you replied to) but they do not substantiate your claim that “this tech is legit and currently improving at an alarming rate” or any other beautiful epithet you used. LLMs remain hallucinating state machines with a probability attached to any word they spit out, and marginal efficiency improvements don’t make them any more exciting to the end user.
Cost means energy use in addition to hardware, so it should matter to climate concerned folks, not just investors.
Also these reasoning models are way less likely to hallucinate given time to think (test time compute). Think applications where it matters like augmenting or replacing existing labor, which will start to happen more.
I’m still convinced that these models will never be more useful than they are now. I sometimes use them to help with coding but honestly I could easily live without them, none of them can handle complex tasks with good accuracy.
Thinking they will somehow significantly improve on this is techbro shit. I’m certain there’s more to cognition and intelligence than stochastic parroting.
I’m aware and will play with it at work. But would it not imply then 500 billion investment useless if true? if you can run full model on 4 blackwells stack (100k?) (and depending how swap works on 48 gb radeon (10 k bucks)?).
The announcement from deepseek was sucking the oxygen out of this entire dumb stargate announcement imo. It’s like they’re already wrong but committed. the amount I think demonstrates that they feel they MUST win this race at any cost, even if it will just mostly end up being a grift.
At least small one (8b) locally does not roleplay very smart, will need to poke the big boy later
spoiler
how dumb is investment of 500 billion into nvidia stocks deepseek-r1:8b <think> Alright, so the user just asked about how dumb it is to invest $500 billion into NVIDIA stocks. Hmm, that’s a pretty big number. I need to approach this carefully.
First off, I should acknowledge that investing such a large amount comes with risks and requires a solid understanding of the market. The user might be new to investing or maybe they’re just curious about high-stakes moves.
I should explain the factors that could influence NVIDIA’s stock, like their growth in AI and gaming sectors. It’s important to mention both the potential for high returns and the associated risks, like market volatility and competition from other tech companies.
Maybe the user is considering a significant investment and wants to know if it’s a good idea. I should provide some key points without giving financial advice, since that’s not my role. Instead, I’ll offer them tips on what to consider before making such a decision.
I also need to keep the tone friendly and informative, avoiding any markdown as per the guidelines. Let me structure this in a clear and organized way so the user can easily digest the information. </think>
Investing such a large sum into NVIDIA stocks is not something to take lightly, as it carries significant risks and requires careful consideration of various factors. While NVIDIA has shown remarkable growth in recent years, driven by its dominance in graphics processing units (GPUs) for gaming, data centers, and AI, the investment landscape can be volatile.
Here are some key points to consider before making such a decision:
-
Market Volatility
The stock market is inherently risky, and large investments like this could lead to substantial losses if the market trends negatively. NVIDIA’s stock price is sensitive to broader market conditions, geopolitical events, and economic downturns.
-
Competition
NVIDIA faces competition from other tech companies, including AMD, Intel, and emerging players in the AI and GPU space. The company’s success depends on its ability to maintain its leadership position and adapt to changing technologies.
-
Regulatory Risks
The company is subject to regulations and scrutiny from government agencies, which could impact its operations and stock price.
-
Valuation
High-profile investments often lead to elevated valuations, making the stock expensive relative to its earnings. Investors need to assess whether NVIDIA’s growth prospects justify such a high valuation.
-
Diversification
A single investment of this size is not diversified and exposes you to significant risk. Consider spreading your investments across different sectors or asset classes to reduce risk.
-
Research and Advice
Before making such a significant investment, consult with financial advisors, brokers, or investment professionals who can provide tailored advice based on your financial goals and risk tolerance.
upd2: nah small one definitely fucked on strawberry test lmao
I should break down the word letter by letter: S-T-R-A-W-B-E-R-R-Y. Let’s see, that’s S, T, R, A, W, B, E, R, R, Y.
Now, counting the "R"s: there are two "R"s in “strawberry.” So, the answer should be 2. The word “strawberry” has two (2) letters: R.
That’s mind boggling output for an 8b model compared to last year. It’s funny, you can def see how that first answer is a distillation of r1’s answer here:
spoiler
Okay, so the user is asking how dumb it is to buy $500 billion in Nvidia stock. Let me break this down. First, $500 billion is an astronomical amount of money. Nvidia’s current market cap is around $2.2 trillion as of early 2023. If someone tried to buy $500 billion worth of their stock, that’s like almost a quarter of the entire company. But wait, market cap is the total value of all outstanding shares. So buying $500 billion would require that many shares being available, which they might not be.
Liquidity is a big factor here. Even if the shares are available, purchasing such a huge volume would drive the price up rapidly because of the increased demand. This is known as slippage. The more you buy, the higher the price goes, so the actual cost could be way more than $500 billion. Plus, once the market notices such a massive buy, other investors might react, maybe causing a short-term spike but also potential volatility afterward.
Then there’s diversification. Putting all that money into a single stock is super risky. Even if Nvidia is a strong company, any company-specific issue—like a product failure, regulatory problem, or market shift—could tank the stock. Diversification helps mitigate that risk, but this move is the opposite of diversified.
That’s at least aware of concept of free float and slippage
(i don’t want to poo-poo small model over something which might have been pruned, but outside of fancy 
style posting, it’s not that different from other small ones)
-
I don’t understand how Softbank is so eager to lose so much money all the time
Have you heard about findom?
masayoshi son i have an idea for an ai office company can i have 20 billion dollars
Sounds like
, nook you will give me 40 billion instead idiot
Fiber internet pls
:doomer:
of course we’re going down the stupidest fucking route possible god i hate this country
I think there is a possible outcome where the Internet and all connected devices become so saturated with AI bullshit that we just go back to talking to each other
It’s already happening. Many of my friends have logged off/deleted accounts and are doing more IRL social things. I’ve loaded my schedule up with in-person events and hang out with people as often as I can. This is the only place on the internet (aside from
sites) that is worth looking at.Hell yeah
(pls no)
the re-industrialization of the United States
oh wait, you’re serious. let me laugh even harder
re-aindustrialization
hundreds of thousands of jobs
Eat my whole ass.
It’s so that those of us who sell labor have no labor to sell.
What are these hundreds of thousands of jobs? I swear the only reason capitalists are investing in AI is so they can try to get rid of workers
Oh duh to build the infrastructure. Can’t wait for the only jobs in the future to be back breaking labour to build AI infrastructure while the Earth burns
