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
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)
The paper details more about how they got these things to train each other, so in theory you’d train these tiny 1.5b or small 8b models to specific tasks.