[彻夜难眠●不敢相信] Nvidia, Super Micro Computer all 惨重大跌.... whats happening to AI theme?

[project_00]

Later market open will have another round of sell off.

Then after lunch time the real sell off will come.

I hope you all have already sold all your stocks when I warn about this crash 1 month ago.

Thanks for the tip
What stocks can buy?

 

[Anghtj]

US stock markets will crash

 

[Humster]

"Deepseek R1 is one of the most amazing and impressive breakthroughs I've ever seen," said Marc Andreessen, the Silicon Valley venture capitalist who has been advising President Trump, in an X post on Friday."

"DeepSeek said training one of its latest models cost $5.6 million, compared with the $100 million to $1 billion range cited last year by Dario Amodei, chief executive of the AI developer Anthropic, as the cost of building a model."

"Barrett Woodside, co-founder of the San Francisco AI hardware company Positron, said he and his colleagues have been abuzz about DeepSeek. "It's very cool," said Woodside, pointing to DeepSeek's open-source models in which the software code behind the AI model is made available free."

"Anthony Poo, co-founder of a Silicon Valley-based startup using generative AI to predict financial returns, said his company moved to DeepSeek from Anthropic's Claude model in September. Tests showed DeepSeek performed similarly for around one-fourth of the cost."

I think faster sell your nvda before the crash from red to abyss

Uh.. its says nothing about whats powering DeepSeek.
Using Nvidia cards? AMD? Daisy chain yesteryear hardware?
$5.6 million is only the compute training, it doesn't include the cost of research, human resources, other related stuff like hardware. Unless those things are free I hardly see how its that cheap.

 

[kage]

China will reverse engineer Nvidia H100 chips. That’s how dangerous China copycat is. Trump must take quick action to stop it. He must also look at which countries are indirectly letting China to get hold of the chips. Sanctions must be imposed on these countries.

China reverse engineering is spectacular, anything under the sun ...

Take for example LEEGO .... 1 minifigure official sell almost $10, china sell 8 for less then $3 when on sale ... the quality is very good, they just say its a kids toy but compatible wif LEEGO ....

It further improvised to have many more themes, like characters from romance of the 3 kingdom, Qin's emperor, roman legion, samurai .... etc ... very good quality .

To those bread and butter consumers, it certainly is not a bad thing.

Healthy competition will brings the price more affordable and frenly to consumers.

 

[selemuse]

What is the hell selloff to do with Nvidia? Nvidia is a hardware provider, and if DeepSeek can get more of Nvidia's high-end GPU, it can do much greater thing and scale larger with more sophisticated model. Nivida, Buy, Buy, Buy Nivida stock. Wish those who buy huat.

Did people not realize that Nivdia is significantly instrumental in creating Deepseek advanced model?

 

[firebrand83]

Come out play, sooner or later must pay

 

[doppypoppy]

very painful dip reminds me of smci

 

[zuppeur]

soun gg down 16%

 

[Jirachi]

soun gg down 16%

What stock is that?

 

[zuppeur]

What stock is that?

SoundHound AI Inc

 

[StoicGuy]

Deepseek only need so little computing power to achieve the same AI model means all upstream hardware supplier all die cock stand...

 

[Jirachi]

I asked your question to deepseek, R1 and Search switched on:


The recent plunge in NVIDIA's stock price, attributed to the rise of Chinese AI startup DeepSeek, reflects investor concerns about structural shifts in the AI industry. While NVIDIA specializes in hardware and DeepSeek in software, their relationship is more competitive than complementary due to **DeepSeek's disruptive efficiency innovations**, which reduce reliance on high-end NVIDIA chips. Here's a detailed analysis:

---

### 1. **DeepSeek’s Efficiency Reduces Demand for High-End NVIDIA Chips**
DeepSeek’s AI models, such as **R1** and **V3**, achieve performance comparable to OpenAI’s models but with **30–45x lower computational costs** and **3–5% of the operational expenses**. Key innovations include:
- **Mixed-Precision Training (FP8):** Native 8-bit floating-point training reduces memory usage, enabling training on smaller GPU clusters. For example, DeepSeek-V3 was trained on 2,000 NVIDIA H800 chips, while similar U.S. models required "tens of thousands" of advanced H100 chips.
- **Reinforcement Learning (RL) and Mixture-of-Experts (MoE):** These techniques allow selective activation of model parameters, cutting computational overhead. RL enables autonomous reasoning without costly supervised datasets.
- **Distillation:** Smaller models inherit capabilities from larger ones, reducing inference costs. This challenges the industry’s reliance on brute-force scaling with expensive hardware.

These advancements suggest that AI developers can achieve high performance with fewer, less advanced chips—directly threatening NVIDIA’s revenue from premium GPUs like the H100.

---

### 2. **Geopolitical and Market Dynamics Amplify the Threat**
- **U.S. Chip Export Restrictions:** NVIDIA’s inability to sell H100/H200 chips to China forced companies like DeepSeek to optimize for older H800/A800 GPUs. Ironically, this scarcity-driven innovation has made Chinese models **more efficient** and **less dependent on cutting-edge hardware**.
- **Partnership with AMD:** DeepSeek collaborates with AMD, NVIDIA’s rival, to optimize models for AMD Instinct GPUs and ROCm software. This diversification reduces reliance on NVIDIA’s ecosystem.
- **Open-Source Models:** DeepSeek’s open-source strategy (e.g., R1 on Hugging Face) democratizes access to efficient AI, pressuring U.S. firms to lower prices. Hugging Face’s "Open R1" project further accelerates this trend.

---

### 3. **Investor Anxiety Over NVIDIA’s Growth Trajectory**
NVIDIA’s stock surge in recent years was fueled by the perception that AI progress depends on its hardware. DeepSeek’s breakthroughs challenge this narrative:
- **Lower Training Costs:** DeepSeek trained V3 for $5.6 million vs. $100M–$1B for U.S. rivals, proving that expensive hardware isn’t mandatory for state-of-the-art models.
- **Market Sentiment Shift:** Analysts warn that if DeepSeek’s methods are widely adopted, demand for NVIDIA’s high-margin chips could stagnate. The Nasdaq Composite fell 2% on January 27 amid these fears.
- **Long-Term Risks:** Microsoft, Google, and Amazon are developing custom AI chips, further eroding NVIDIA’s dominance.

---

### 4. **Why DeepSeek and NVIDIA Aren’t Symbiotic**
While DeepSeek uses NVIDIA’s H800 chips, their innovations reduce the **quantity** and **quality** of chips needed:
- **Fewer Chips Per Model:** DeepSeek’s optimized training pipelines require smaller GPU clusters.
- **Shift to Cheaper Hardware:** Efficient models can run on older or less powerful chips, reducing demand for NVIDIA’s latest products.
- **AMD Partnership:** DeepSeek’s collaboration with AMD signals a potential shift away from NVIDIA in the long term.

---

### 5. **Broader Implications for the AI Industry**
- **Price Wars:** DeepSeek’s low-cost API ($0.55/million tokens vs. OpenAI’s $15) pressures U.S. firms to slash prices, squeezing margins.
- **Sustainability Focus:** Energy-efficient AI models align with global sustainability goals, making DeepSeek’s methods attractive.
- **Geopolitical Reckoning:** U.S. export controls intended to stifle China’s AI growth have backfired, spurring innovation. As Microsoft CEO Satya Nadella noted, "We should take developments out of China very seriously".

---

### Conclusion
NVIDIA’s stock decline reflects fears that DeepSeek’s software-driven efficiency could decouple AI progress from reliance on advanced hardware. While NVIDIA remains critical to AI infrastructure, DeepSeek’s rise highlights a paradigm shift where **algorithmic ingenuity compensates for hardware limitations**. Investors now question whether NVIDIA’s growth can sustain if the industry prioritizes cost and efficiency over raw computational power.

Oh DeepSeek is FP8 quantisation. There are actually so many LLMs on Ollama which I used that runs this. I really think the DeepSeek thing is a misunderstanding of what people think it is.

 

[paperplane1943]

Can buy the dip?

 

[Zinna]

What is the hell selloff to do with Nvidia? Nvidia is a hardware provider, and if DeepSeek can get more of Nvidia's high-end GPU, it can do much greater thing and scale larger with more sophisticated model. Nivida, Buy, Buy, Buy Nivida stock. Wish those who buy huat.

Did people not realize that Nivdia is significantly instrumental in creating Deepseek advanced model?

Don't think too much, either faster panic sell or buy the dip

 

[0nePunchm@n]

er..npnt

 

[ckt1978]

Ppl doing Sell the News.
Calm down for a moment.
Right now ppl still not fully understand how Deepseek actually works, i.e, the machinery behind( is it running on air? What cards? Daisy chain?)

running on lower resources and can do it at free.
so no need super powerful gpu liao.
fundamentals all changed liao.
could be the Netscape moment when browsers are suddenly free.

 

[Nuclear Boy]

Why panic sell and realize the loss? It's not like Nvidia will fold next week. Soon, it'd just be an aberrant blip in your stock valuation.

 

[project_00]

What is the hell selloff to do with Nvidia? Nvidia is a hardware provider, and if DeepSeek can get more of Nvidia's high-end GPU, it can do much greater thing and scale larger with more sophisticated model. Nivida, Buy, Buy, Buy Nivida stock. Wish those who buy huat.

Did people not realize that Nivdia is significantly instrumental in creating Deepseek advanced model?

DeepSeek shows you don't need as much capital investment as you think
They also open sourced their code as others can see how they did it

 

[haoren]

Things r bound to advanced where u can do more with cheaper chips.

 

[Jirachi]

Why panic sell and realize the loss? It's not like Nvidia will fold next week. Soon, it'd just be an aberrant blip in your stock valuation.

Margin trading. Traders need to close else risk margin call