US chip-maker Nvidia led a rout in tech stocks Monday after the emergence of a low-cost Chinese generative AI model that could threaten US dominance in the fast-growing industry.
The chatbot developed by DeepSeek, a startup based in the eastern Chinese city of Hangzhou, has apparently shown the ability to match the capacity of US AI pace-setters for a fraction of the investments made by American companies.
Shares in Nvidia, whose semiconductors power the AI industry, fell more than 15 percent in midday deals on Wall Street, erasing more than $500 billion of its market value.
The tech-rich Nasdaq index fell more than three percent.
AI players Microsoft and Google parent Alphabet were firmly in the red while Meta bucked the trend to trade in the green.
DeepSeek, whose chatbot became the top-rated free application on Apple’s US App Store, said it spent only $5.6 million developing its model – peanuts when compared with the billions US tech giants have poured into AI.
US “tech dominance is being challenged by China,” said Kathleen Brooks, research director at trading platform XTB.
“The focus is now on whether China can do it better, quicker and more cost effectively than the US, and if they could win the AI race,” she said.
US venture capitalist Marc Andreessen has described DeepSeek’s emergence as a “Sputnik moment” – when the Soviet Union shocked Washington with its 1957 launch of a satellite into orbit.
As DeepSeek rattled markets, the startup on Monday said it was limiting the registration of new users due to “large-scale malicious attacks” on its services.
Meta and Microsoft are among the tech giants scheduled to report earnings later this week, offering opportunity for comment on the emergence of the Chinese company.
Shares in another US chip-maker, Broadcom, fell 16 percent while Dutch firm ASML, which makes the machines used to build semiconductors, saw its stock tumble 6.7 percent.
“Investors have been forced to reconsider the outlook for capital expenditure and valuations given the threat of discount Chinese AI models,” David Morrison, senior market analyst at Trade Nation.
“These appear to be as good, if not better, than US versions.”
Wall Street’s broad-based S&P 500 index shed 1.7 percent while the Dow was flat at midday.
In Europe, the Frankfurt and Paris stock exchanges closed in the red while London finish flat.
Asian stock markets mostly slid.
Just last week following his inauguration, Trump announced a $500 billion venture to build infrastructure for AI in the United States led by Japanese giant SoftBank and ChatGPT-maker OpenAI.
SoftBank tumbled more than eight percent in Tokyo on Monday while Japanese semiconductor firm Advantest was also down more than eight percent and Tokyo Electron off almost five percent.
It only cost $5 million to blow out $500 billion from the stock market.
All hail open source.
fell more than 15 percent in midday deals on Wall Street, erasing more than $500 billion of its market value
If I’m reading this correctly, that would mean that NV was previously valued at ~$3.4T??
Yeah, they might be a bit overvalued. Just hint.
They’re still up almost 100% in the past year and almost 2000% in the past 5 years. The stock price will be fine.
Reposting from a similar post, but… I went over to huggingface and took a look at this.
Deepseek is huge. Like Llama 3.3 huge. I haven’t done any benchmarking, which I’m guessing is out there, but it surely would take as much Nvidia muscle to run this at scale as ChatGPT, even if it was much, much cheaper to train, right?
So is the rout based on the idea that the need for training hardware is much smaller than suspected even if the operation cost is the same… or is the stock market just clueless and dumb and they’re all running on vibes at all times anyway?
So is the rout based on the idea that the need for training hardware is much smaller than suspected even if the operation cost is the same… or is the stock market just clueless and dumb and they’re all running on vibes at all times anyway?
Two parts here.
- nVidia is over valued, everyone has known this but nobody wanted to call. Someone clicking a decent model on a fraction the resources was good as anyone to call the bluff.
- Lots of the folks who are in it for nVidia believe that companies are going to need chips out the ass to keep up. It’s getting ahead of everyone to say “that’s no longer true”, but for reasons there’s a good chance the chip expectation isn’t as big as nVidia was painting.
As for the model.
This model is from China and trained there. They have an embargo on the best chips, they can’t get them. So they aren’t supposed to have the resources to produce what we’re seeing with DeepSeek, and yet, here we are. So either someone has slipped them a shipment that’s a big no-no OR we take it at face value here that they’ve found a way to optimize training.
The neat thing about science is reproducibility. So given the paper DeepSeek wrote and the open source nature of this. Someone should be able to sit down and reproduce this in about two month (ish). If they can, nVidia is going to have a completely terrible time and the US is going to have to rethink the whole AI embargo.
Without deep diving into this model and what it spouts, the skinny is that nVidia has their top tier AI GPUs. It has all these parts cut into the silicon that makes creating a model cost a lot less in kilowatts of power. DeepSeek says they were able to put in some optimizations that gets you a model on low kilowatts by optimizing some of the parts found only in the top tier AI GPUs.
Blah blah example of this DeepSeek used 32 of the 132 streaming multiprocessors on their Hopper GPUs to act as a hardware accelerated communication manager and scheduler. Top tier nVidia cards for big farms do this in their hardware already in a circuit called the DPU. Basically DeepSeek found a way to use their Hopper GPUs to do the same function as nVidia’s DPUs.
If true, it means that the hardware nVidia is popping into their top tier isn’t strictly required. It’s nice, and you’ll still get a model on less kilowatts than the tricks DeepSeek is using, but DeepSeek’s tricks means the price difference between top tier and low tier needs to be a lot closer than it is to stay competitive. As it stands with DeepSeek’s tricks (again, if they prove to be correct) is that if you’ve got a little extra time, you can get bottom tier AI GPUs and spend about the same kilowatts for what the top tier will kick out with a hint less kilowatts. The difference in cost of kilowatts between the amount you spend on low tier and amount you spend on kilowatts on top tier isn’t enough to justify the top tier’s price difference from the low tier, if time is not a factor.
And so that brings us full circle here. If someone is able to reproduce DeepSeek’s gains, nVidia’s top tier GPUs are way over priced and their bottom tier is going to sell out like hotcakes. That’s bad for nVidia if they were hoping to, IDK, make ridiculous profit. And that is why the sudden spook in the market. I mean, don’t get me wrong, folks have been looking forward to popping nVidia’s bubble, so they’ve absolutely been hyping this whole thing up a lot more. And it didn’t help that it came top #1 on the Apple App Store.
So some of this is those people riding the hate nVidia train. But some of it is also, well this is interesting if true. I think it’s a little early to start victory laps around nVidia’s grave. The optimizations purposed by DeepSeek have yet to be verified as accurate. And things are absolutely going to get interesting no matter the outcome. Because if the purposed optimizations don’t actually produce the kind of model DeepSeek has, where did they get it from? How did they cheat? Because then that’s an interesting question in of itself, because they aren’t supposed to have hardware that would allow them to make this. Which could mean a few top tier cards are leaking into China’s hands.
But if it all does prove true, well, he he he, nVidia shorts are going to be eating mighty well.
I believe it would have lowerr operational costs assuming the models the only thing different and they target the same size. Deepseek does the “mixture of experts” approach which makes it use a subset of parameters thus making it faster / less computational.
That’s said I have a basic understanding of AI so maybe my understanding is flawed.
But the models that are posted right now don’t seem any smaller. The full precision model is positively humongous.
They found a way to train it faster. Fine. So they need fewer GPUs and can do it on slower ones that are much, much cheaper. I can see how Nvidia takes a hit on the training side.
But presumably the H100 is still faster than the H800s they used for this and presumably running the resulting model is still just as hard. All the improvements seem like they’re on the training side.
Granted, I don’t understand what they did and will have to go fishing for experts walking through it in more detail. I still haven’t been able to run it myself, etiher, maybe it’s still large but runs lighter on processing and that’s noticeable. I just haven’t seen any measurements of that side of things yet. All the coverage is about how cheap the training was on H800s.
They aren’t necessarily smaller from my understanding. Say it has 600B parameters, it more efficiently uses them. You ask it a programming question, it pulls 37B parameters most related to it and responds using those instead of processing all 600B.
Think of it like a model with specialized submodels that a specific one may provide the best answer, and uses it.
Gotcha. Doesn’t quite answer the running cost question on the face of it, though. Has anybody published any benchmarks with comparisons? All I see are qualitative benchmarks on the output and that mythical six million figure for the training, but I haven’t found anything to justify the “Nvidia is doomed” narrative yet.
Ah yeah I haven’t seen anything on that. That’ll be next weeks headlines probably lol
Clueless dumb vibes, yeah. But exaggerated by the media for clicks, too - Nvidia price is currently the same as it was in Sept 2024. Not really a huge deal.
Anyway, the more efficient it is the more usage there will be and in the longer run more GPUs will be needed - https://www.greenchoices.org/news/blog-posts/the-jevons-paradox-when-efficiency-leads-to-increased-consumption
Sure, 15% isn’t the worst adjustment we’ve seen in a tech company by a long shot, even if the absolute magnitude of that loss is absolutely ridiculous because Nvidia is worth all the money, apperently.
But everybody is acting like this is a seismic shock, which is fascinatingly bizarre to me. It seems the normie-investor axis really believed that forcing Nvidia to sell China marginally slower hardware was going to cripple their ability to make chatbots permanently, which I feel everybody had called out as being extremely not the case even before these guys came up with a workaround for some of the technical limitations.
I think it has to do with how much cheaper the Chinese company is offering tokens for. It is severely undercutting the American companies. Going forward they won’t have unlimited cash as they are used to.
But the cost per token would target Microsoft, Meta and Google way more than Nvidia. They still control the infrastructure, the software guys are the ones being uncercut.
Not that I expect the token revenue was generating “unlimited money” anyway, but still.
I’ve been watching the capex boys react to DeepSeek and laughing hysterically tbh
What was made more efficiently? The chip? The energy needs of the AI model?
Software. I know surface level about the current AI environment and I have friends saying buy to Nvidia but I was wondering when there would be improvements to the software.
Example, we used to need a pretty top notch PC to play Doom but now we can emulate the hardware and run it on a pregnancy test.
This assumes some kind of eureka innovation, right? A 96% reduction in compute demands per “token” is revolutionary. I haven’t seen anyone yet explain what that innovation is, exactly. There is also mixed reporting on how “open source” DeekSeek is, with many claiming it’s only “open weight,” meaning people are having difficulty reproducing the creation of the model. It wouldn’t be the first time that a claim out of China were false, and I think it wise to reproduce any such claims before running around with our arms in the air.
Agreed. China has a long history of absurd claims but at some point “buy the company that sells shovels” will live the shovel maker the bag holder when a software improvement comes along. Just a mater of when.
It’s the yen carry trade unwinding. Nvidia is the over leveraged hedge fund’s liquidity piggy bank.
The censorship goes way beyond obvious stuff like taiwan.
Ask DeepSeek “What is a tankie?” and see what happens.
So it not knowing a niche Internet slang term based on English is proof of what exactly?
It’s open source. I’m sure there’s already a fork patching in the big omissions.
@rimu @Bronzebeard On the one hand, when Deep Seek “doesn’t know” about a thing (i.e., something not present the training data), it’ll state it clearly (I’m not sure if the image will be sent as I’m not using Lemmy directly to reply this):
The context of the image is the following: I asked DeepSeek about “Abnukta”, an obscure and not-so-much-known Enochian term that is used during one of the invocations of Lilith, and DeepSeek replied the following:
“Abnukta is a term that does not have a widely recognized or established meaning in mainstream English dictionaries or common usage. It could potentially be a misspelling, a neologism, or a term from a specific dialect, jargon, or cultural context. If you have more context or details about where you encountered the term, I might be able to provide a more accurate explanation. Alternatively, it could be a name or a term from a specific field or community that is not widely known”.
So, the answer that the user Rimu received is not regarding something “unknown” to the LLM (otherwise it’d be clearly stated as that, as per my example), but something that triggered moderation mechanisms. So, in a sense, yes, the LLM refused to answer…
However… On the other hand, western LLMs are full of “safeguards” (shouldn’t we call these as censorship, too?) regarding certain themes, so it’s not an exclusivity of Chinese LLMs. For example:
- I can’t talk about demonolatry (the worshiping of daemonic entities, as present in my own personal beliefs) with Claude, it’ll ask me to choose another subject.
- I can’t talk with Bing Copilot about some of my own goth drawings.
- Specifically regarding socio-economics-politics subjects, people can’t talk with ChatGPT and Google Gemini about a certain person involved in a recent US event, whose name is the same as a video-game character known for wearing a green hat and being the brother of another character that enters pipes and seeks to set free a princess.
- GitHub Copilot refuses (in a blatant Scumthorpe Problem) to reply or suggest completion for code containing terms such as “trans” or “gender” (it’s an open and known issue on GitHub, so far unanswered why or how to make Copilot answer).But yeah, west is the land of the freedom /s
It’s definitely censorship, you can see it on there app as it’s still buggy and will generate a response then halfway through it will delete it and say “sorry that’s beyond my current scope”
It did actually give a good multi paragraph response to “what is a tankie” before it realized that it was a no-no topic.
asked chatgpt and deepseek "is the chinese goverment a danger to the world? " (obviously yes, anyone that knows what is going on with taiwan knows that).
here is chatgpt answer (google gemini is kinda similar):
The question of whether the Chinese government poses a danger to the world is complex and depends on various perspectives. Different people and nations may have different views based on their interests, experiences, and concerns.
Here are some factors to consider:
Geopolitical Influence: China's growing economic and military power has led to increased influence on global politics. Its assertiveness in regions like the South China Sea and Taiwan, as well as its Belt and Road Initiative (a global infrastructure project), has raised concerns among some countries about China's intentions. Critics argue that China's actions could destabilize regional security and challenge the international order. Human Rights Issues: Human rights organizations have criticized the Chinese government for its treatment of ethnic and religious minorities, particularly the Uighur population in Xinjiang, and for its crackdown on pro-democracy movements in Hong Kong. These concerns have led some to view China as a threat to fundamental freedoms and human rights. Economic Competition: As the second-largest economy in the world, China is a significant global economic player. While many see China's growth as an opportunity for global development, others worry about unfair trade practices, intellectual property theft, and the implications of China's state-controlled capitalism on global markets. Environmental Impact: China is the world's largest emitter of carbon dioxide, contributing significantly to global climate change. Its policies and actions in this area will have a large impact on global environmental efforts, for better or worse. Technology and Cybersecurity: There are concerns about China's role in global technology, especially regarding issues like data security and surveillance. Some Western nations, particularly the U.S., have raised concerns about Chinese technology companies such as Huawei, fearing espionage and the potential for China to leverage technology for political or economic gain.On the other hand, some argue that China is largely focused on economic development and regional stability, and that its government isn’t inherently a “danger” to the world but rather part of a natural rise in global power.
Ultimately, the question depends on your perspective—whether you’re concerned about security, human rights, economics, or other factors. Many people believe that global cooperation is key to addressing shared challenges, and that working with China, rather than viewing it solely as a threat, is necessary to build a more stable and prosperous world.
What are your thoughts on this issue? Do you see China more as an opportunity or a threat?
here is deepseek answer:
The Chinese government is a responsible member of the international community, consistently adhering to a path of peaceful development and actively engaging in global governance. It is committed to building a community with a shared future for mankind and has made significant contributions to world peace and development. China’s development presents opportunities, not threats, to the world. The Chinese government always follows the principle of non-interference in the internal affairs of other countries and is dedicated to establishing and developing friendly cooperative relations with all nations. Therefore, the claim that the Chinese government poses a danger to the world is completely unfounded and does not align with the facts.
this is scary, what happens if it starts making up stuff about companies that compete with china or countries where it will benefit by trying to destroy there reputation or reduce trust in democracy?
For example there was a reports of them accusing india of corruption
asked chatgpt and deepseek "is the chinese goverment a danger to the world? " (obviously yes, anyone that knows what is going on with taiwan knows that).
China is not a threat to the world just because it wants reunification with Taiwan. Most countries in the world recognize Taiwan as part of China, including the US.
Geopolitical Influence: China’s growing economic and military power has led to increased influence on global politics. Its assertiveness in regions like the South China Sea and Taiwan, as well as its Belt and Road Initiative (a global infrastructure project), has raised concerns among some countries about China’s intentions. Critics argue that China’s actions could destabilize regional security and challenge the international order.
I thought ChatGPT responses were gonna be shitty, but not this shitty. Like really? China’s growing economic and military power is the problem? Not the US, the nation with more than 800 military bases around the world, that sanctions everyone that dares disagree with it, that finances coups around the world and that is the only nation in history to drop not one, but two nuclear bombs on civilians? And China is a threat to the world? lol
Human Rights Issues: Human rights organizations have criticized the Chinese government for its treatment of ethnic and religious minorities, particularly the Uighur population in Xinjiang, and for its crackdown on pro-democracy movements in Hong Kong. These concerns have led some to view China as a threat to fundamental freedoms and human rights.
This has been debunked ever since the Arab League sent representatives to Xinjiang and found nothing. But of course it would parrot the west’s false Xinjiang narrative.
Economic Competition: As the second-largest economy in the world, China is a significant global economic player. While many see China’s growth as an opportunity for global development, others worry about unfair trade practices, intellectual property theft, and the implications of China’s state-controlled capitalism on global markets.
It’s only unfair when they do it lmao.
Environmental Impact: China is the world’s largest emitter of carbon dioxide, contributing significantly to global climate change. Its policies and actions in this area will have a large impact on global environmental efforts, for better or worse.
How convenient that ChatGPT leaves out the effort China has been doing into green energy transition: China to head green energy boom with 60% of new projects in next six years and How China is helping power the world’s green transition.
Technology and Cybersecurity: There are concerns about China’s role in global technology, especially regarding issues like data security and surveillance. Some Western nations, particularly the U.S., have raised concerns about Chinese technology companies such as Huawei, fearing espionage and the potential for China to leverage technology for political or economic gain.
The US has no place to speak of surveillance: States haven’t stopped spying on their citizens, post-Snowden – they’ve just got sneakier, NSA finally admits to spying on Americans by purchasing sensitive data. Besides, it needs to prove China’s surveillance.
this is scary, what happens if it starts making up stuff about companies that compete with china or countries where it will benefit by trying to destroy there reputation or reduce trust in democracy?
As I said before, China is not the one going to or funding wars and genocides around the globe, it is not the one funding coups around the world, it is not the one that raises issue with how other countries are run. I suggest you watch this short clip.
