Beijing, January 28: DeepSeek, a Chinese AI startup founded less than a year ago, has introduced its breakthrough AI model, DeepSeek R1, which is gaining attention for its performance and cost-efficiency, Reported CNN/
The model has nearly the same capabilities as other leading AI systems, including OpenAI's GPT-4, Meta's Llama, and Google's Gemini, but at a fraction of the cost. This development has drawn significant interest in the tech world, especially after the company revealed its shockingly low operational costs.
Marc Andreessen, a prominent tech investor, called DeepSeek's breakthrough "AI's Sputnik moment." The company claims it spent just USD 5.6 million powering its base AI model, a stark contrast to the hundreds of millions, if not billions, that US companies typically invest in similar technologies. DeepSeek's model was developed using relatively underpowered AI chips, despite the United States' efforts to restrict China's access to advanced chips. This accomplishment raises questions about the cost and feasibility of developing high-performance AI models with limited resources.
DeepSeek was founded in late 2023 by Liang Wenfeng, a Chinese hedge fund manager. Liang has quickly become a key figure in the AI space, drawing comparisons to Sam Altman, the CEO of OpenAI. His hedge fund, High-Flyer, focuses on AI research and development, helping to fuel DeepSeek's rapid rise.
Over the past year, DeepSeek has released various AI models, including its V3 model, which drew attention but was criticised for its content restrictions on sensitive topics related to the Chinese government and leadership. The R1 model, however, has raised the stakes. When it was revealed late last year and launched publicly last week, the company emphasised its low cost of operation. The model is open-source, allowing other companies to test and improve upon it.
The DeepSeek app surged in popularity, surpassing ChatGPT on app store charts, and has been downloaded nearly 2 million times. This surge in downloads demonstrates the excitement around the company's breakthrough.
AI is known for its high operational costs, with major players like Meta planning to spend more than USD 65 billion on AI development this year. Sam Altman, CEO of OpenAI, has stated that the AI industry will need trillions of dollars in investment to support the infrastructure and chips required for these technologies. DeepSeek's ability to deliver competitive performance at a fraction of the cost challenges existing industry assumptions about how much investment is required to develop powerful AI models.
Andreessen, who is a supporter of the technology, called DeepSeek's achievement "one of the most amazing and impressive breakthroughs I've ever seen" in a post on X. His statement reflects the industry's growing acknowledgment of the potential impact of DeepSeek's model.
DeepSeek's success comes amid growing concerns over AI's role in national security. The United States has imposed export restrictions on high-performance chips to China, aiming to maintain its technological advantage. However, DeepSeek's progress suggests that restrictions may not be enough to stop China from making significant advances in AI.
The United States thought it could sanction its way to dominance in a key technology it believes will help bolster its national security. Just a week before leaving office, former President Joe Biden doubled down on export restrictions on AI computer chips to prevent rivals like China from accessing the advanced technology.
But DeepSeek has called into question that notion and threatened the aura of invincibility surrounding America's technology industry. America may have bought itself time with restrictions on chip exports, but its AI lead just shrank dramatically despite those actions.
DeepSeek may show that turning off access to a key technology doesn't necessarily mean the United States will win. That's an important message to President Donald Trump as he pursues his isolationist "America First" policy.
Wall Street was alarmed by the development. US stocks were set for a steep selloff Monday morning. Nvidia (NVDA), the leading supplier of AI chips, whose stock more than doubled in each of the past two years, fell 12 per cent in premarket trading. Meta (META) and Alphabet (GOOGL), Google's parent company, were also down sharply, as were Marvell, Broadcom, Palantir, Oracle, and many other tech giants.
The industry is taking the company at its word that the cost was so low. No one is really disputing it, but the market freak-out hinges on the truthfulness of a single and relatively unknown company. The company notably didn't say how much it cost to train its model, leaving out potentially expensive research and development costs. (Still, it probably didn't spend billions of dollars.)
It's also far too early to count out American tech innovation and leadership. One achievement, albeit a gobsmacking one, may not be enough to counter years of progress in American AI leadership. And a massive customer shift to a Chinese startup is unlikely.
"The DeepSeek model rollout is leading investors to question the lead that US companies have and how much is being spent and whether that spending will lead to profits (or overspending)," said Keith Lerner, an analyst at Truist. "Ultimately, our view is the required spend for data and such in AI will be significant, and US companies remain leaders."
Although the cost-saving achievement may be significant, the R1 model is a ChatGPT competitor -- a consumer-focused large-language model. It hasn't yet proven it can handle some of the massively ambitious AI capabilities for industries that -- for now -- still require tremendous infrastructure investments.
"Thanks to its rich talent and capital base, the US remains the most promising 'home turf' from which we expect to see the emergence of the first self-improving AI," said Giuseppe Sette, president of AI market research firm Reflexivity.
