China’s DeepSeek Is America’s AI Sputnik Moment

[BananaRepublic]

They have genocided and destroyed the Red Indians and Aboriginals.

White People have no business being in the Americas and Australasia.

World would be much better if they stuck to Europe.

They also committed genocide in Africa and Asia.

And the crusades are ofcourse legendary for their blood thirst.

No other race has the innate superiority complex over everyone.

Not just that..,

But seeing themselves as the “saviour race”.

Racially encapsulated by Kipling in the “white men’s burden” diatribe!

We need to free the white men of their burden!

 

[UKBengali]

They also committed genocide in Africa and Asia.

And the crusades are ofcourse legendary for their blood thirst.

No other race has the innate superiority complex over everyone.

Not just that..,

But seeing themselves as the “saviour race”.

Racially encapsulated by Kipling in the “white men’s burden” diatribe!

We need to free the white men of their burden!

Well they will be forced to accept to share the planet as equals by China and others.

 

[Waz]

Deepseek is incredible, having given it dozen tasks to do.

 

[UKBengali]

Deepseek is incredible, having given it dozen tasks to do.

It seems a little better than Chtagpt 01 at technical tasks like programming and 3d software like Blender but weaker at "conversational topics'.

That seems to be because its focus was more on technical training rather than natural language fluency.

Btw, do you use the website/app to access Deepseek or have the model installed locally?

I find that after 10-15 minutes I essentially am kicked off as it says "server busy" on the website.

 

[Waz]

It seems a little better than Chtagpt 01 at technical tasks like programming and 3d software like Blender but weaker at "conversational topics'.

That seems to be because its focus was more on technical training rather than natural language fluency.

Btw, do you use the website/app to access Deepseek or have the model installed locally?

I find that after 10-15 minutes I essentially am kicked off as it says "server busy" on the website.

Use both my friend, I have on my phone as well. My jobs requires access to information fast.
I've never had the issue of being kicked off.

 

[UKBengali]

Use both my friend, I have on my phone as well. My jobs requires access to information fast.
I've never had the issue of being kicked off.

On the phone I am presuming you use the app(?) and so in essence using Deepseek's servers and not running locally.

It may be due to the kind of questions that I am asking that could potentially require more compute power that I get "server busy" after 10-15 minutes.

Wanted to run it locally but my hardware is not powerful enough for a powerful enough model that matches the website, but at least the option is there once I get round to upgrading within the next 12-18 months.

 

[muhammed45]

Every other day seems to be a "Sputnik Moment" for the Americans.

When Americans wake up in the morning they ask, "Is it Saturday today or Sputnik?"

If Sputnik, let's go back to sleep.

Spoken like a true American.

 

[Waz]

On the phone I am presuming you use the app(?) and so in essence using Deepseek's servers and not running locally.

It may be due to the kind of questions that I am asking that could potentially require more compute power that I get "server busy" after 10-15 minutes.

Wanted to run it locally but my hardware is not powerful enough for a powerful enough model that matches the website, but at least the option is there once I get round to upgrading within the next 12-18 months.

Yes it's the app, as at times I am on the move.

 

[Viet]

Deepseek is incredible, having given it dozen tasks to do.

there is a strong evidence the chinese team has taken data illegally from the AI team in the US. that’s standard industrial espionage. that accelerates the software development.
the necessary hardware and chips come from Singapore so the investigation by the FBI.
in the months, years leading to deepseek lots of high performance chips are imported into Singapore.
that’s very suspicious.

I installed deepseek on my iphone.
here what I get from deepseek. I do a quick Q&A. confirmed. all hardware are made by US companies.

“who has developed deepseek? who are the developers?”

DeepSeek is developed by DeepSeek Artificial Intelligence Co., Ltd., a Chinese company dedicated to making AGI a reality. The specific developers or team members are not publicly disclosed, but the company focuses on advancing AI technologies and applications. For more details, you can visit their official website: [https://deepseek.com]

“what hardware is used by deepseek?”

DeepSeek, like other advanced AI systems, relies on high-performance hardware to train and run its models efficiently. While specific hardware details aren't publicly disclosed, typical setups for AI development and deployment include:

1. **GPUs (Graphics Processing Units)**:
- NVIDIA GPUs (e.g., A100, V100, H100) are widely used for deep learning due to their parallel processing capabilities and support for frameworks like CUDA and cuDNN.

2. **TPUs (Tensor Processing Units)**:
- Google's TPUs are specialized hardware for accelerating machine learning workloads, particularly for large-scale models.

3. **CPUs (Central Processing Units)**:
- High-performance CPUs (e.g., Intel Xeon, AMD EPYC) are used for preprocessing, inference, and tasks that don't require GPU acceleration.

4. **Distributed Computing**:
- Large-scale AI training often involves clusters of GPUs/TPUs connected via high-speed networks (e.g., InfiniBand) for distributed training.

5. **Storage**:
- Fast storage solutions (e.g., NVMe SSDs) are used to handle large datasets and model checkpoints efficiently.

6. **Cloud Infrastructure**:
- Many AI companies, including DeepSeek, leverage cloud platforms (e.g., AWS, Google Cloud, Azure) for scalable computing resources.

If you're interested in DeepSeek's specific infrastructure, you might find more details in their technical documentation or by reaching out to their team.

 

[F-22Raptor]

there is a strong evidence the chinese team has taken data illegally from the AI team in the US. that’s standard industrial espionage. that accelerates the software development.
the necessary hardware and chips come from Singapore so the investigation by the FBI.
in the months, years leaving to deepseek lots of high performance chips are imported into Singapore.
that’s very suspicious.

I installed deepseek on my iphone.
here what I get from deepseek. I do a quick Q&A. confirmed. all hardware are made by US companies.

“who has developed deepseek? who are the developers?”

DeepSeek is developed by DeepSeek Artificial Intelligence Co., Ltd., a Chinese company dedicated to making AGI a reality. The specific developers or team members are not publicly disclosed, but the company focuses on advancing AI technologies and applications. For more details, you can visit their official website: [https://deepseek.com]

“what hardware is used by deepseek?”

DeepSeek, like other advanced AI systems, relies on high-performance hardware to train and run its models efficiently. While specific hardware details aren't publicly disclosed, typical setups for AI development and deployment include:

1. **GPUs (Graphics Processing Units)**:
- NVIDIA GPUs (e.g., A100, V100, H100) are widely used for deep learning due to their parallel processing capabilities and support for frameworks like CUDA and cuDNN.

2. **TPUs (Tensor Processing Units)**:
- Google's TPUs are specialized hardware for accelerating machine learning workloads, particularly for large-scale models.

3. **CPUs (Central Processing Units)**:
- High-performance CPUs (e.g., Intel Xeon, AMD EPYC) are used for preprocessing, inference, and tasks that don't require GPU acceleration.

4. **Distributed Computing**:
- Large-scale AI training often involves clusters of GPUs/TPUs connected via high-speed networks (e.g., InfiniBand) for distributed training.

5. **Storage**:
- Fast storage solutions (e.g., NVMe SSDs) are used to handle large datasets and model checkpoints efficiently.

6. **Cloud Infrastructure**:
- Many AI companies, including DeepSeek, leverage cloud platforms (e.g., AWS, Google Cloud, Azure) for scalable computing resources.

If you're interested in DeepSeek's specific infrastructure, you might find more details in their technical documentation or by reaching out to their team.

That’s a whole lot of American technological throughput in the development of R1.

 

[Viet]

That’s a whole lot of American technological throughput in the development of R1.

the software is not reliable.
I asked:
“which country has the lowest price for apple mac mini m4?”
“what is the old name of ho chi minh city?”

I got this:
“The server is busy. Please try again later.”

seems it blocks me from accessing after my curious questions about how to contact the team behind deepseek. not much useful.

 

[Viet]

I got no answer from deepseek so I ask openAI:

“can you explain me the AI model behind deepseek? and what’s difference to openAI?”

I got this:

“
DeepSeek is a Chinese artificial intelligence company known for developing advanced, open-source large language models (LLMs). Their models, such as DeepSeek-R1 and DeepSeek-V3, have garnered attention for their efficiency and performance. DeepSeek employs a Mixture-of-Experts (MoE) architecture, which allows the model to activate only a subset of its parameters for each token during processing. This approach enhances computational efficiency and reduces resource consumption. Additionally, DeepSeek has introduced innovations like Multi-head Latent Attention (MLA) and an auxiliary-loss-free strategy for load balancing, further optimizing training and inference processes.

In contrast, OpenAI, an American AI research organization, has developed proprietary models such as GPT-4. OpenAI’s models are typically fully dense, meaning all parameters are active during processing, which can lead to higher computational costs. While OpenAI has released some models and research openly, many of their recent models are closed-source and not publicly accessible. DeepSeek’s commitment to open-source development and cost-effective training distinguishes it from OpenAI’s more traditional, resource-intensive approach.”


I have zero knowledge in AI,
but that means deepseek uses a method that is deployed in cryptography: prediction. if predictions are right or close to it then less resources are required to compute. it delivers quicker results.

 

[Hendarto]

DeepSeek AI models debut on platform powered by Huawei

Huawei’s cloud unit teamed up with Beijing-based AI infrastructure start-up SiliconFlow to make the models available to end users.

www.scmp.com

Tech war: Huawei cloud unit powers DeepSeek models in China’s bid for AI autonomy​

Huawei’s cloud unit teamed up with Beijing-based AI infrastructure start-up SiliconFlow to make the models available to end users​

Reading Time:2 minutes

The cloud-computing unit of Huawei Technologies has worked overtime with a local company during the Lunar New Year holidays to make DeepSeek’s artificial intelligence (AI) models available to end users on its platform in an efficient and affordable way.

Huawei’s cloud unit teamed up with Beijing-based AI infrastructure start-up SiliconFlow to make DeepSeek’s large language model V3 and reasoning model R1 available to end users through the telecom giant’s Ascend cloud service, with performance matching “DeepSeek models run on global premium graphic processing units [GPUs]”, Huawei Cloud said in a statement on Saturday.

According to a separate statement from SiliconFlow, which hosts the DeepSeek models, the charge for access to V3 on its platform is discounted to 1 yuan (US$0.13) for 1 million input tokens and 2 yuan for 1 million output tokens, while the same charges for the R1 model are 4 yuan and 16 yuan.


The move by Huawei and SiliconFlow comes as the open-source DeepSeek models are gaining popularity in both China and the US. OpenAI investor Microsoft earlier this week launched support for R1 on its Azure cloud-computing platform and GitHub. This allows clients to build AI applications that run locally on Copilot+ personal computers. E-commerce giant Amazon.com has enabled developers to create applications with the “powerful, cost-efficient” R1 through Amazon Web Services.
Huawei’s Ascend cloud service used its home-grown Ascend solution for compute resources, which could involve various types of hardware including Huawei’s self-developed server clusters, AI modules and accelerator cards, a company website said.

Huawei and SiliconFlow did not specify the chips used in the Ascend cloud service.

The move to launch DeepSeek’s models on a home-grown hardware backbone highlights China’s progress in cutting dependency on foreign technology and bolstering its domestic AI industry amid growing efforts by the US to choke off China’s access to high-end chips that the US government said could be used to advance military aims.

Huawei and SiliconFlow did not immediately respond to a request for comments during the Lunar New Year holiday.

Advertisement
AD

Hangzhou-based start-up DeepSeek has sent shock waves across Silicon Valley and Wall Street for its claimed ability to develop AI models at a fraction of the cost of its larger US competitors.

SiliconFlow, which also provides access to other models including Meta’s Llama and Alibaba’s Qwen, said in a statement that DeepSeek’s models “are a great gift from the DeepSeek team to all mankind”. Alibaba owns the South China Morning Post.

Chinese social media and video gaming giant Tencent also adopted DeepSeek’s reasoning model R1 on its cloud-computing platform, touting a three-minute easy set-up process.


Advertisement

 

[Hendarto]

Now, who is stealing whom?

To view this content we will need your consent to set third party cookies.
For more detailed information, see our cookies page.

Accept third party cookies

 

[神威98]

TBH, my Android tablet quick launch/home screen is filled with Chinese apps: A bunch of Chinese games, Petal Map, Huawei Browser, Huawei App Gallery, Moomoo (stock charting platform by Tencent), Deepseek.

I never believed in any Western apps. I don't have TikTok app becoz it's a bunch of White boiz on Chinese platform.

To top it all off, I even installed Deepseek via Huawei App Gallery instead of Google Playstore. I have never touched ChatGPT app, it's NOT worth my time...