OpenAI closes largest private tech deal on record

Tech deal

OpenAI on Monday 31st March 2025 announced it had closed its $40 billion funding round, the most ever raised by a private tech company.

The deal values OpenAI at $300 billion, including the new capital.

The round includes $30 billion from SoftBank and $10 billion from a syndicate of investors.

OpenAI is now more valuable than Chevron.

The generative AI market is projected to exceed $1 trillion in revenue within the next decade. Companies such as Google, Amazon, Anthropic, and Perplexity are rapidly unveiling new products and features as competition to develop ‘AI agents’ intensifies.

The future is AI!

Dow closed 700 points lower Friday 28th March 2025 as inflation and tariff fears worsen

Dow down

Stocks sold off sharply on Friday 28th March 2025, pressured by growing uncertainty on U.S. trade policy as well as a grim outlook on inflation

The Dow Jones Industrial Average closed down 715 points at 41,583. The S&P 500 lost 1.97% to close 5,580 ending the week down for the fifth time in the last six weeks. The Nasdaq Composite plunged 2.7% to 17,322.

Shares of several technology giants also fell putting pressure on the broader market. Google-parent Alphabet lost 4.9%, while Meta and Amazon each shed 4.3%.

This week, the S&P 500 lost 1.53%, while the 30-stock Dow shed 0.96%. The Nasdaq declined by 2.59%. With this latest losing week, Nasdaq is now on pace for a more than 8% monthly decline, which would be its worst monthly performance since December 2022.

Dow Jones one-day chart (28th March 2025)

Dow Jones one-day chart (28th March 2025)

Stocks took a leg lower on Friday after the University of Michigan’s final read on consumer sentiment for March 2025 reflected the highest long-term inflation expectation since 1993.

Friday’s core personal consumption expenditures price index also came in hotter-than-expected, rising 2.8% in February and reflecting a 0.4% increase for the month, stoking concerns about persistent inflation.

Economists had reportedly been looking for respective numbers of 2.7% and 0.3%. Consumer spending accelerated 0.4% for the month, below the 0.5% forecast, according to fresh data from the Bureau of Economic Analysis.

The market is getting squeezed by both sides. There is uncertainty about reciprocal tariffs hitting the major exporting sectors like tech alongside concerns about a weakening consumer facing higher prices

Trump’s tariffs push will hit the U.S. harder than Europe in the short term, it has been reported.

Japan’s Nikkei enters correction as Trump’s tariff assault drives sell-off in Asia markets

China’s position on open-source artificial intelligence (AI) is upending the global AI race

AI

China’s embrace of open-source artificial intelligence (AI) is revolutionising the global AI landscape, challenging traditional notions of innovation and competitiveness in this rapidly evolving field.

Traditionally, the AI sector has been dominated by proprietary models and closed-source systems, particularly in the U.S.

However, China has made a strategic pivot towards open-source initiatives, driven by trailblazers like the AI startup DeepSeek.

DeepSeek’s R1 model, released earlier this year, has become a symbol of China’s open-source movement. Distributed under the permissive MIT licence, the R1 model allows unrestricted use, modification and distribution.

This approach has disrupted traditional business models by democratising access to cutting-edge AI tools. Companies from tech giants like Baidu and Tencent to emerging players like ManusAI have followed suit, releasing their own open-source models and fostering a collaborative environment for AI innovation.

This shift is seen by some as China’s ‘Android moment’ in AI – a reference to the impact of Google’s open-source Android operating system on the mobile app ecosystem.

The move towards open-source has enabled rapid cost reductions, increased accessibility, and accelerated product development. Chinese firms have leveraged these advantages to narrow the perceived technological gap with the U.S., with some analysts suggesting that the disparity has shrunk from years to mere months.

Despite these advancements, the open-source approach also raises questions about intellectual property, security, and sustainable business models.

While it has catalysed innovation, it remains to be seen whether open-source strategies can sustain long-term competitiveness against well-funded proprietary systems.

China’s open-source embrace exemplifies a bold shift in AI strategy, emphasizing collaboration and accessibility over exclusivity.

This paradigm shift could redefine global dynamics in artificial intelligence, fostering a more inclusive and innovative future for the industry.

Nvidia sales grow 78% on AI demand – gives strong guidance

AI

Nvidia recently reported its Q4 results, showcasing impressive growth driven by strong demand for AI technology.

The company achieved a record quarterly revenue of $39.3 billion, marking a 78% increase from the previous year.

This growth was primarily fuelled by the success of Nvidia’s Blackwell AI supercomputers, which saw billions of dollars in sales in their first quarter.

The data centre segment, which constitutes the bulk of Nvidia’s revenue, also performed exceptionally well, generating $35.60 billion, up 16% from the previous quarter. Nvidia’s adjusted earnings per share for Q4 were $0.89, surpassing analysts’ expectations of $0.84.

Looking ahead, Nvidia provided strong guidance for Q1, forecasting revenue of $43 billion, which exceeds market expectations of $42.05 billion. The company also projected a gross margin of 70.60% for the upcoming quarter.

The first-quarter forecast indicates a year-over-year growth of approximately 65%, a deceleration from the 262% annual growth recorded in the same period the previous year.

Nvidia’s CEO, Jensen Huang reportedly highlighted the rapid advancements in AI technology and the company’s successful ramp-up of Blackwell AI supercomputers as key drivers of this growth.

Despite facing competition from Chinese AI firms like DeepSeek, Nvidia remains optimistic about the demand for its AI chips.

The company’s robust performance and positive outlook signal continued growth and innovation in the AI sector.

China’s AI vs U.S. AI – competition heats up – and that’s good for business – isn’t it?

DeepSeek AI

The escalating AI competition between the U.S. and China has taken a new turn with the emergence of DeepSeek, a Chinese AI startup that has introduced a low-cost AI model capable of rivaling the performance of OpenAI’s models.

This development has significant implications for data centres and the broader technology sector.

The rise of DeepSeek

DeepSeek’s recent breakthrough involves the development of two AI models, V3 and R1, which have been created at a fraction of the cost compared to their Western counterparts.

The total training cost for these models is estimated at around $6 million, significantly lower than the billions spent by major U.S. tech firms. This has challenged the prevailing assumption that developing large AI models requires massive financial investments and access to cutting-edge hardware.

Impact on data centres

The introduction of cost-effective AI models like those developed by DeepSeek could lead to a shift in how data centers operate.

Traditional AI models require substantial computational power and energy, leading to high operational costs for data centers. DeepSeek’s models, which are less energy-intensive, could reduce these costs and make AI technology more accessible to a wider range of businesses and organizations.

Technological advancements

DeepSeek’s success also highlights the potential for innovation in AI without relying on the most advanced hardware.

This could encourage other companies to explore alternative approaches to AI development, fostering a more diverse and competitive landscape. Additionally, the open-source nature of DeepSeek’s models promotes collaborative innovation, allowing developers worldwide to customise and improve upon these models2.

Competitive dynamics

The competition between DeepSeek and OpenAI underscores the broader U.S.-China rivalry in the AI space. While DeepSeek’s models pose a limited immediate threat to well-funded U.S. AI labs, they demonstrate China’s growing capabilities in AI innovation.

This competition could drive both countries to invest more in AI research and development, leading to faster technological advancements and more robust AI applications.

Broader implications

The rise of DeepSeek and similar Chinese and other AI startups could have far-reaching implications for the global technology sector.

As AI becomes increasingly integrated into various industries, the ability to develop and deploy AI models efficiently will be crucial.

Data centres will need to adapt to these changes, potentially investing in more energy-efficient infrastructure and exploring new ways to support AI workloads.

Where from here?

DeepSeek’s emergence as a significant player in the AI race highlights the dynamic nature of technological competition between the U.S. and China.

While the immediate impact on data centres and technology may be limited, the long-term implications could be profound.

As AI continues to evolve, the ability to innovate cost-effectively and collaborate across borders will be key to driving progress and maintaining competitiveness in the global technology landscape.

Microsoft’s Quantum Leap: The Majorana 1 Chip

Quantum Physics

Microsoft has unveiled a new chip called Majorana 1 that it says will enable the creation of quantum computers able to solve ‘meaningful, industrial-scale problems in years, not decades’.

What is Microsoft’s Majorana 1?

It is the latest development in quantum computing – tech which uses principles of particle physics to create a new type of computer able to solve problems ordinary computers cannot.

Microsoft has announced a game-changing development in the world of quantum computing: the Majorana 1 chip. This revolutionary chip integrates eight topological quantum bits (qubits), setting a new standard for stability and resistance to environmental interference.

Microsoft. The new Majorana 1 chip

The Majorana 1 chip is built on a unique combination of indium arsenide, a semiconductor, and aluminum, a superconductor. This cutting-edge design enables the chip to create a topological state, a new form of matter that encodes information in a way that is inherently noise-resistant. This means that the Majorana 1 chip can maintain its quantum state longer, making it more reliable for complex computations.

What sets the Majorana 1 chip apart is its use of topoconductors, a new class of materials developed by Microsoft’s researchers over nearly two decades. These materials provide a high level of error protection, which is essential for practical quantum computing applications. The Majorana 1 chip is a significant step toward the ultimate goal of creating quantum computers with millions of qubits, capable of solving complex industrial and societal problems.

While the Majorana 1 chip is still in the research phase and not yet available for commercial use, it represents a monumental leap forward in quantum technology. Microsoft’s commitment to advancing quantum computing is evident in the substantial investment of time and resources required to develop this groundbreaking chip.

In summary, the Majorana 1 chip is poised to transform the landscape of quantum computing, offering a more stable and reliable platform for future innovations. This development marks a pivotal moment in the quest for practical and scalable quantum computing solutions.

What is Quantum computing?

Quantum computing is a revolutionary technology that uses the principles of quantum mechanics to process information in a fundamentally different way than classical computers, allowing for exponentially faster calculations in certain tasks.

It leverages qubits, which can represent multiple states simultaneously, enabling complex problem-solving and data analysis beyond the capabilities of traditional computing.

Microsoft says powerful quantum computers will be a reality in years not decades.

Musk’s xAI releases new Grok 3 AI

xAI Grok AI

Elon Musk’s AI company, xAI, has recently released its latest AI model, Grok 3.

This new AI model is designed to be significantly more powerful and capable than its predecessor, Grok 2.
  • Enhanced Capabilities: Grok 3 boasts 10 times more computing power than Grok 2 and has been trained on an expanded dataset, including court case filings.
  • Reasoning Models: Grok 3 includes reasoning models that can carefully analyze and fact-check information before providing responses. This helps in avoiding common pitfalls of AI models.
  • Benchmark Performance: Grok 3 has outperformed other leading AI models, including OpenAI’s GPT-4o and DeepSeek’s R1, on various benchmarks such as AIME (math questions) and GPQA (physics, biology, chemistry problems).
  • New Features: The Grok app now includes a ‘DeepSearch’ feature that scans the internet and xAI’s social network, X, to provide summarised responses to user queries.
  • Subscription Plans: xAI has introduced a new subscription plan called SuperGrok, which offers additional reasoning capabilities and unlimited image generation.

Grok 3 is being hailed as the ‘smartest AI on Earth’ by Musk, and it’s expected to have a significant impact on various industries.

Definition

Grok is a neologism (a newly coined word or expression), referenced by Robert A. Heinlein for his 1961 science fiction novel Stranger in a Strange Land. It means to understand something so deeply that you become one with it.

Grok is a term used in computer programming to mean to ‘profoundly understand something‘, such as a system, a language, or an algorithm.

Less woke

Grok, the company previously reportedly said, is modelled on ‘The Hitchhiker’s Guide to the Galaxy’. 

It is supposed to have ‘a bit of wit, a rebellious streak’ and it should answer the ‘spicy questions’ that other AI might dodge, according to a statement from xAI.

I wonder if it has been modelled on Elon Musk?

Chinese tech giant Baidu to release next-generation AI model soon as DeepSeek leads Chinese AI tech

AI

China’s Baidu reportedly plans to release the next generation of its artificial intelligence model in the second half of this year, according to information recently reported.

The planned update comes as Chinese companies race to develop innovative AI models to compete with OpenAI and other U.S. based companies.

Baidu was the first major Chinese tech company to roll out a ChatGPT-like chatbot called Ernie in March 2023.

However, despite initial momentum, the product has since been eclipsed by other Chinese chatbots from large tech companies such as Alibaba and ByteDance, as well as startups.

BYD shares hit record as the EV maker rolls out advanced driver tech with DeepSeek’s AI assistance

BYD with DeepSeek AI (fictitious image)

Shares of BYD, the Chinese electric vehicle (EV) giant, surged to a record high on Tuesday 11th February 2025, following the announcement of its new driver assistance technology.

The company revealed its latest ‘DiPilot’ assisted driving system, which integrates artificial intelligence (AI) from Chinese startup DeepSeek.

This move is expected to significantly enhance the driving experience and safety features of BYD’s vehicles.

BYD’s founder and chairman, Wang Chuanfu, announced the launch of the DiPilot system at a livestreamed event, emphasizing that advanced smart driving will become a standard safety feature, akin to seatbelts and airbags (time will tell on that statement).

The system includes features such as remote parking and autonomous highway navigation. These features reportedly are being integrated into over 20 models. Budget-friendly options priced below 70,000 yuan ($9,555) will also have the system.

DeepSeek AI integration

The integration of DeepSeek’s AI technology is a game-changer for BYD. DeepSeek, known for its innovative chatbot that rivals U.S. competitors such as OpenAI and others brings high-quality AI capabilities to BYD’s autonomous driving systems.

This partnership allows BYD to offer advanced intelligent features at a competitive price, putting it ahead of its rivals in the fiercely competitive Chinese EV market.

Analysts have praised BYD’s strategic shift from price-cutting to upgrading vehicle functions and have noted that BYD is now dictating the pace of technological features in the market.

The company’s stock rose by 4.5% to a record high in Hong Kong, reflecting investor optimism about the new technology.

BYD’s move to integrate advanced driver assistance systems into budget models is expected to intensify the EV price war. The company’s aggressive pricing strategy, combined with cutting-edge technology, positions it well to capture a larger market share.

With more than 20 models featuring the new driver assistance tech, BYD is set to lead the way in smart vehicle innovation.

As BYD continues to expand its presence globally, the integration of DeepSeek’s AI technology marks a significant milestone in the company’s journey towards becoming a leader in the EV industry.

The future looks promising for BYD as it continues to innovate and push the boundaries of automotive technology.

One Year BYD charts as of 11th February 2025

One Year BYD charts as of 11th February 2025

Could DeepSeek deliver another shock to the stock market and to tech stocks in particular?

AI

DeepSeek’s impact probably isn’t yet fully reflected in U.S. stocks

The ramifications of the Chinese startup DeepSeek, with its promise of delivering cheaper and more energy-efficient alternatives to harness artificial intelligence (AI), have yet to be fully reflected in U.S. equities.

If DeepSeek ends up delivering a less costly way forward – it will make it much easier and cheaper for smaller more typical companies to create AI ‘agents’ or AI opportunities for their businesses.

Under this scenario there will be ‘useful’ and meaningful benefits from DeepSeek that could bring huge earnings potential for a broader mix of companies beyond the current AI heavyweights through greater efficiencies and productivity from less-expensive AI solutions.

AI spending race

When DeepSeek’s chatbot launched earlier this month in the U.S., it shocked Wall Street, prompting a historic $600 billion one-day wipeout for AI chip developer Nvidia.

It also put huge sums being pledged for AI infrastructure by U.S. mega cap tech companies under a microscope. Rather than back down, the U.S. spending race has intensified.

  • Meta’s Chief Executive Mark Zuckerberg spoke a week ago of spending ‘hundreds of billions of dollars’ on AI infrastructure in the coming years, after pledging $60 billion to $65 billion on AI this year.
  • Alphabet announced AI investment for 2025, a bigger figure than Wall Street was anticipating.
  • Google forecast $75 billion in capital expenditures in 2025, a bigger figure than Wall Street was anticipating.
  • Microsoft reported its cloud and AI spending grew 95% in its fiscal second quarter to $22.6 billion.
  • Amazon has reported big AI investment too.

The spending frenzy on anything AI sends the market into a spin. How much more has to be spent before we see capital expenditures reduced or decrease is anyone’s guess right now – but current levels of AI expenditure are high, and returns will be expected.

“When is enough, enough?”

Or more to the point you might ask – when is ‘enough’ too much?

Fresh AI-spending commitments helped lift shares of Nvidia on while we saw a slump for Tesla shares in the week.

China this week saw the U.S. slap new 10% tariffs, while Canada and Mexico saw Trump threaten but delay 25% tariffs by 30 days. China retaliated in kind.

Catching up with the ‘Magnificent Seven’

Despite the high scrutiny on AI stocks, there is also much renewed focus from investors on other areas of the market.

There has been a bit of a rotation – while tech has been under pressure, defensive and rate-sensitive parts of the market have been gaining. This seems to be an emerging pattern.

​But there should be reason for caution. For one thing, the growth rate of ‘Magnificent Seven’ earnings has been tailing off in recent quarters, especially since the group reached a 61% yearly rate in the fourth quarter of 2023 – the spend on AI investment has yet to fully appreciate the full return.

Forward analysts’ expectations have this percentage reportedly closer to 16% to 18% for the end of this year. 

But that also would move the group closer ​to the roughly 12% to 13% yearly growth rate expected for the rest of the companies in the S&P 500 index, potentially making the high valuations of the ‘Magnificent Seven’ tougher to justify.

One of the most surprising things of the past couple of weeks, given the news around DeepSeek and shocks on the trade front, is the fact that stocks were still close to their all-time highs.

The market is pretty resilient right now, but tech stocks are sitting at a very high valuation – a pullback is due, even a correction (in my opinion).

The arrival of DeepSeek creates an alternative ‘cheaper’ AI option and that will unravel the status quo.

Apple and Google shares fall after China reportedly launches probes into Apple App Store practices and Google’s anti-trust issues

Google and Apple probed

China Launches Probes into Google and Apple Over Antitrust Concerns

China has recently initiated investigations into both Google and Apple, raising concerns over potential antitrust violations.

The State Administration for Market Regulation (SAMR) is considering whether to formally investigate Apple’s App Store practices, particularly focusing on the fees Apple charges and its policies that block third-party payment providers. This move has already caused Apple’s shares to fall.

In addition to the probe into Apple, China has also opened a separate investigation into Google, although details about the focus of this investigation have not been disclosed. These probes come at a time when trade tensions between the U.S. and China are escalating under President Donald Trump’s administration.

Apple’s app store under scrutiny

Apple’s App Store has been under scrutiny globally, with regulators in Europe recently forcing the company to open up its App Store under the Digital Markets Act, allowing non-Apple companies to offer app stores and app developers to use third-party payment systems.

If the China probe goes ahead, it would pose further challenges for Apple in one of its largest markets, where it is already facing stiff competition from local companies such as Huawei.

Google

Google, on the other hand, has not yet commented on the specifics of the investigation, but the move highlights the increasing regulatory pressures faced by U.S. tech giants in China.

Both companies will need to navigate these investigations carefully as they continue to operate in a highly competitive and regulated environment.

The outcome of these probes could have significant implications for the tech industry, potentially leading to changes in how these companies operate in China and other markets.

As the investigations unfold, the world will be watching closely to see how Google and Apple respond to these regulatory challenges.

Tariff Man – Trumps tariffs take affect – markets fall!

U.S. Tariffs

U.S. President Donald Trump’s tariffs have moved from threat to reality.

U.S. President Donald Trump launched a series of tariffs on Saturday. U.S. imports from Mexico and Canada will face a 25% duty, while those from China will be subject to a 10% tariff. Energy resources from Canada will face a lower 10% tariff.

Canada’s Prime Minister Justin Trudeau announced on the same day retaliatory tariffs of 25% against $155 billion in U.S. goods. Industry leaders in the U.S. have expressed concern over those tariffs.

They cap off a wild start to the new year during which a new U.S. president entered the White House and a new Chinese artificial intelligence player, DeepSeek upended the industry.

Indices at new highs

Something else that was new in January: the highest-ever closing level for the S&P 500, Dow Jones and new FTSE 100 highs were enjoyed too.

With tariffs now in effect and the possibility of a trade war looming markets may struggle to new heights in the short term.

Even Big Tech earnings and the jobs numbers coming out this week, typically market-moving reports, are likely to play second fiddle to policy developments.

Markets react

Markets are already responding to the news. Prices of oil and gold, which typically rise during periods of volatility, have increased, but Bitcoin is trading lower. It remains uncertain whether these will be a temporary shock or a sustained trend.

China’s factory activity experienced slower growth in January 2025 compared to December 2024 and is expected to be adversely affected as U.S. companies seek to reduce their dependence on Chinese imports.

Trump’s current tariffs may be targeted, but it’s hard to see any country or sector escaping the tariff turmoil.

The EU is also in line for a tariff attack and maybe the UK after.

Is Nvidia share price at risk as DeepSeek creates an alternative lower cost AI direction?

China and U.S. AI

Nvidia’s share price has been on a rollercoaster ride recently. After experiencing a significant drop due to concerns over the Chinese startup DeepSeek’s AI models, Nvidia’s stock saw a sharp recovery.

On Tuesday 28th January 2025 Nvidia shares ended 8.82% higher at $128.86 on Nasdaq, following a 17% drop the previous day.

However, there are mixed opinions about the potential for more downside. Some analysts believe that Nvidia’s stock still looks weak on the technical charts and may face further declines.

Some analysts suggest that Nvidia shares may trade in the range of $105 to $135 and recommend a ‘sell on rise’ strategy. Some also pointed out signs of technical deterioration, suggesting that Nvidia’s stock may be entering an intermediate-term corrective phase.

On the other hand, some investors are optimistic about Nvidia’s long-term growth prospects, especially with its strong fundamentals and continued advancements in AI technology.

The market remains dynamic, and the stock’s performance will likely depend on various factors, including broader market trends and developments in the AI industry.

Nvidia meteoric will likely change dramatically when face with an alternative AI chip manufacturer.

Doubt cast

DeepSeek, has made significant advancements in AI technology. There are claims and speculations that DeepSeek may have used some U.S. technology to enhance its capabilities.

For instance, it was reported that DeepSeek acquired a substantial number of Nvidia’s high-performance A100 graphics processor chips before the U.S. imposed restrictions on their sales to China. Additionally, there have been allegations that DeepSeek copied some technology developed by U.S. rival OpenAI.

However, these are unfounded claims and it’s important to point out that DeepSeek has also been praised for its innovation and efficiency, developing AI models at a fraction of the cost compared to leading U.S. tech companies.

This may even aid Nvidia as it could drive the cost of AI down bringing it to a wider audience more quickly thus enhancing Nvidia’s future sales.

Investors poured money into leveraged ETFs linked to Nvidia – then the stock crashed!

ETFs

Single-stock ETFs betting heavily on Nvidia’s blistering rally plunged, tracking losses in the AI chip makers shares, calling into question the reliability of the leveraged investment strategy.

The GraniteShares 2x Long NVDA Daily ETF (NVDL) fell nearly 34% overnight. The Direxion Daily NVDA Bull 2x Shares ETF (NVDU) and T-Rex 2X Long Nvidia Daily Target ETF (NVDX) plunged 33.8% and 33.77% respectively. All three funds reported their largest loss in a single day, according to data from FactSet. 

Conversely, funds betting against Nvidia like the GraniteShares 2x Short NVDA Daily ETF (NVDL) rose more than 33%.

This sell-off has been a difficult lesson for investors who have seen Nvidia as invincible and have taken aggressive bets on its growth without understanding the risks of single stock ETFs.

The funds were designed to deliver twice the performance of Nvidia on a single-day basis.

It could be a matter of time before some of them implode depending on the intensity of market movements of individual stocks.

Single stock ETFs come with a huge risk and huge upside – we just witnessed the downside.

It’s so volatile – a day after the fall Nvidia regained some 9% of its one-day loss. Remarkable loss, exceptional recovery too?

Nvidia one-month chart 28th January 2025

Trade carefully.

The aftermath from the arrival of Deepseek

Deepseek AI

Nvidia, the renowned American technology company, recently experienced the largest one-day loss in U.S. history. On January 27, 2025, Nvidia’s stock plummeted by 17%, resulting in a staggering market cap loss of nearly $600 billion.

This unprecedented drop was primarily triggered by the emergence of DeepSeek, a Chinese artificial intelligence startup that has been making waves in the tech industry.

DeepSeek, founded in 2023 by Liang Wenfeng, has developed open-source large language models that rival some of the best AI models in the world. The company’s latest model, DeepSeek-V3, has demonstrated impressive performance at a fraction of the cost of its competitors.

This has raised concerns among investors about the sustainability of Nvidia’s dominance in the AI chip market.

The release of DeepSeek’s latest technology has caused significant anxiety among U.S. tech giants, leading to a massive sell-off in the stock market. Companies that rely heavily on Nvidia’s GPUs, such as Dell, Oracle, and Super Micro Computer, also saw their stock prices plummet.

The ripple effect of Nvidia’s loss was felt across the tech-heavy Nasdaq, which dropped by 3.1% on the same day.

Nvidia one-month chart 27th January 2025

In response to this market upheaval, former President Donald Trump commented on the situation, stating that DeepSeek’s emergence should serve as a ‘wake-up call’ for American companies.

Trump emphasised the need for U.S. industries to remain competitive and innovative in the face of rising competition from Chinese tech firms. He acknowledged the impressive advancements made by DeepSeek and suggested that American companies could benefit from adopting more cost-effective methods in their AI development.

Trump’s remarks highlight the growing concern among U.S. policymakers and industry leaders about the rapid advancements in AI technology coming from China.

The success of DeepSeek has demonstrated that significant breakthroughs can be achieved with relatively modest investments, challenging the notion that massive capital expenditure is necessary for top-tier AI performance.

As the AI race continues to heat up, it is clear that companies like Nvidia will need to adapt and innovate to maintain their competitive edge. The emergence of DeepSeek has not only disrupted the market but also underscored the importance of staying ahead in the rapidly evolving field of artificial intelligence.

For American tech giants, this wake-up call serves as a reminder that the global AI landscape is becoming increasingly competitive, and complacency is not an option.

Has the U.S. spent wisely on AI development?

The emergence of DeepSeek has indeed raised questions about the spending strategies of U.S. tech companies on AI development. DeepSeek’s ability to develop high-performing AI models at a fraction of the cost has led to concerns about the necessity of the massive capital expenditures by large U.S. tech firms.

For instance, companies like Microsoft, Alphabet, Meta, and Amazon have collectively spent over $1 trillion on AI investments in recent years. This significant spending has been driven by the belief that larger models and more computing power would lead to better performance.

However, DeepSeek’s success with more cost-effective methods challenges this notion and suggests that efficient innovation might be more important than sheer scale.

The impressive performance and lower costs of DeepSeek’s models have prompted some analysts to question whether the billions of dollars spent by U.S. tech companies on AI development are justified. This has led to a re-evaluation of AI spending strategies and a push for more efficient and innovative approaches to AI development.

In summary, while U.S. tech companies have invested heavily in AI, the success of DeepSeek highlights the potential for achieving cutting-edge results with fewer resources. This has sparked a broader discussion about the most effective and efficient ways to advance AI technology.

Asking ChatGPT – ‘Do you see Deepseek as a competitor or a threat?’

The reply:

As an AI, I don’t have personal opinions or feelings. However, I can share that DeepSeek’s rapid rise and impressive performance in the AI field are noteworthy. Their ability to develop high-performing models at a lower cost is a significant achievement and has certainly shaken up the industry. It’s a reminder of the dynamic and competitive nature of the AI landscape, where innovation can come from unexpected places.

Asking ChatGPT – ‘What do you think of Deepseek?’

The reply:

DeepSeek is a fascinating and disruptive player in the AI landscape. Founded in 2023 by Liang Wenfeng, this Chinese startup has quickly gained attention for its open-source large language models, which rival some of the best AI models in the world at a fraction of the cost. Their latest models, DeepSeek-V3 and DeepSeek-R1, have demonstrated impressive performance and efficiency, challenging the dominance of established tech giants2.

DeepSeek’s emergence has caused significant market upheaval, leading to substantial drops in the stock prices of major AI-related firms, including Nvidia. The company’s success highlights the potential for innovation and cost-effectiveness in AI development, which has prompted industry leaders and policymakers to re-evaluate their strategies.

Overall, DeepSeek’s rapid rise and impact on the AI industry underscore the importance of staying competitive and innovative in this fast-evolving field. It’s a reminder that breakthroughs can come from unexpected places and that the AI landscape is becoming increasingly dynamic and competitive.

It would not be drawn on these questions but, one thing is for sure the U.S. has spent billions developing their systems and charge fortunes for using it.

This is about to change.

And further…

The Deepseek website reportedly crashed on 27th January 2025 due to heavy global demand. There were also reports of unrelenting cyberattacks on its systems…?

Curious. From minnow to centre stage in just one day!

China’s DeepSeek low-cost challenger to AI rattles tech U.S. markets

China Deepseek AI

U.S. technology stocks plunged as Chinese startup DeepSeek sparked concerns over competitiveness in AI and America’s lead in the sector, triggering a global sell-off

DeepSeek launched a free, open-source large-language model in late December 2024, claiming it was developed in just two months at a cost of under $6 million.

The developments have stoked concerns about the large amounts of money big tech companies have been investing in AI models and data centres.

DeepSeek is a Chinese artificial intelligence startup that has recently gained significant attention in the AI world. Founded in 2023 by Liang Wenfeng, DeepSeek develops open-source large language models. The company is funded by High-Flyer, a hedge fund also founded by Wenfeng.

The AI models from DeepSeek have demonstrated impressive performance, rivaling some of the best chatbots in the world at a fraction of the cost. This has caused quite a stir in the tech industry, leading to significant drops in the stock prices of major AI-related firms.

The company’s latest model, DeepSeek-V3, is known for its efficiency and high performance across various benchmarks.

DeepSeek’s emergence challenges the notion that massive capital expenditure is necessary to achieve top-tier AI performance.

The company’s success has led to a re-evaluation of the AI market and has put pressure on other tech giants to innovate and reduce costs.

S&P 500 touches new record high!

Stocks rose on Wednesday 22nd January 2024 with the S&P 500 reaching a new all-time high, as technology shares including Nvidia and Oracle surged on optimism surrounding artificial intelligence and President Donald Trump’s new term in office.

The S&P 500 advanced after hitting an intraday record of 6,100.81, exceeding the last milestone touched in December 2024 before pulling back. The index closed at 6,086.37, slightly below its all-time closing high.

S&P 500 one-month chart as of Wednesday 22nd January 2024

S&P 500 one-month chart as of Wednesday 22nd January 2024

The S&P’s move to an all-time high comes as investors witnessed a December 2024 pullback. Despite the index ending last year with a 23% gain, the S&P 500 shed 2.5% in December 2024, as traders fretted that the Federal Reserve wouldn’t be able to cut rates as much as anticipated.

That lacklustre performance bled into the first few trading sessions of 2025, but some data indicating modest easing on the inflation front and good earnings results have helped the market recover.

Trump announces massive U.S. AI investment backed by Oracle, OpenAI and Softbank

U.S. AI investment

President Donald Trump announced a joint venture with OpenAI, Oracle and Softbank to invest billions of dollars in artificial intelligence infrastructure in the U.S.

The project, dubbed Stargate, was unveiled at the White House by Trump, Softbank CEO Masayoshi Son, OpenAI CEO Sam Altman and Oracle co-founder Larry Ellison.

The executives committed to invest an initial $100 billion and up to $500 billion over the next four years in the project, which will be set up as a separate company.

Softbank’s Son had reportedly already promised a four-year, $100-billion investment when he recently visited then-President-elect Trump at his Mar-a-Lago resort.

And this new AI investment is over and above the investments from the likes of Microsoft, Google, Apple, Anthropic and many others already in progress.

The UK is planning to build a homegrown artificial intelligence rival to OpenAI

UK AI

In a bold move to establish as a global leader in artificial intelligence, the United Kingdom is undertaking an ambitious initiative to develop a homegrown competitor to OpenAI.

This initiative is part of a broader strategy to enhance the nation’s computing infrastructure and foster innovation in AI technology.

Prime Minister Keir Starmer’s administration has committed to increasing the UK’s ‘sovereign’ computing capacity by twentyfold by 2030. This significant investment aims to support the development of powerful AI models that rely on high-performance computing equipment.

The government plans to expand data centre capacity across the country, providing the necessary infrastructure for AI developers to train and run their systems effectively.

AI Opportunities Action Plan

Central to this initiative is the AI Opportunities Action Plan, spearheaded by tech investor Matt Clifford. The plan outlines a comprehensive approach to harnessing the potential of AI, including the establishment of AI growth zones where planning permission rules will be relaxed to facilitate the creation of new data centers.

These zones are expected to become hubs of innovation, attracting both domestic and international talent to the UK.

The government is also set to launch the AI Research Resource, an initiative aimed at bolstering the UK’s computing infrastructure. This resource will provide access to high-performance computing facilities, enabling researchers and developers to work on cutting-edge AI projects.

Additionally, the establishment of a National Data Library will connect public institutions, such as universities, to enhance the country’s ability to create sovereign AI models.

Funding challenge

One of the key challenges facing the UK in its bid to rival OpenAI is funding. While the government has pledged substantial investments, many entrepreneurs and venture capitalists in the country have highlighted the difficulties in raising the kind of capital available to AI startups in the U.S. To address this, the government has secured commitments from leading tech firms, which have pledged £14 billion towards various AI projects.

This includes significant investments in data centers and the creation of thousands of AI-related jobs across the country.

UK AI sovereignty

The UK’s focus on AI sovereignty is driven by the belief that technologies critical to economic growth and national security should be developed within the country. This approach aims to reduce reliance on foreign tech giants and ensure that AI advancements align with national interests and ethical standards.

The government is also exploring the role of renewable and low-carbon energy sources, such as nuclear, to power the data centers that will support AI development.

Despite the ambitious plans, the UK faces several hurdles in its quest to become a global AI leader. The country’s risk-averse investment culture and the competitive landscape of AI development pose significant challenges.

However, the government’s proactive approach and the support of industry leaders provide a strong foundation for success.

Initiative and challenge

The UK’s initiative to build a homegrown rival to OpenAI represents a significant step towards establishing itself as a global leader in artificial intelligence.

By investing in computing infrastructure, fostering innovation, and securing industry support, the UK aims to create a thriving AI ecosystem that can compete on the world stage. While challenges remain, the commitment to AI sovereignty and the strategic vision outlined in the AI Opportunities Action Plan offer a promising path forward for the nation’s AI ambitions.

Sold – the UK needs to protect its future and not sell the silver… again

Over the years, the UK has seen several of its tech companies sold off to foreign investors.

  1. ARM Holdings: Perhaps the most famous example, ARM Holdings, a leading semiconductor and software design company, was acquired by Japan’s SoftBank Group in 2016 for £24.3 billion. ARM’s technology is used in the majority of smartphones worldwide.
  2. DeepMind: In 2014, Google acquired DeepMind, a UK-based AI company known for its advancements in machine learning and neural networks, for around £400 million. DeepMind has since become a key part of Google’s AI research efforts.
  3. Imagination Technologies: This British GPU and AI processing company was sold to Canyon Bridge Capital Partners, a private equity fund backed by Chinese state-owned China Reform Fund Management, in 2017 for £550 million. Recently, Imagination Technologies has been put up for sale again.
  4. Autonomy Corporation: Acquired by Hewlett-Packard (HP) in 2011 for $11.7 billion. The deal later became controversial due to allegations of financial mismanagement
  5. Powa Technologies: This mobile payments company faced financial difficulties and was sold off in parts after going into administration in 2016. PowaTag was sold to a consortium led by businessman Ben White, while Powa Web was sold in a management buyout backed by Greenlight Digital.

One to keep

Raspberry Pi Holdings plc, the parent company behind the iconic Raspberry Pi computer series, is a British technology business focused on designing and manufacturing single-board computers and modules. The company was founded by Eben Upton and is headquartered in Cambridge, England1.

As of the latest information, the largest shareholder of Raspberry Pi Holdings is the Raspberry Pi Foundation, which holds around 49% of the company. Other notable shareholders include Arm Holdings plc, Lansdowne Partners (UK) LLP, and the Raspberry Pi Employee Benefit Trust. The company went public on the London Stock Exchange in June 2024.

Raspberry Pi Holdings continues to innovate and expand its product offerings, maintaining its mission to make computing accessible and affordable for everyone.

These sales reflect the global interest in UK tech companies and the challenges they face in securing domestic investment to remain independent. The UK’s tech sector continues to be a hotbed of innovation, attracting significant attention from international investors.

The UK needs to nurture and keep its upcoming new tech discoveries, AI or otherwise – to protect the future of Britain.

We have the knowhow – we just need to keep it!

U.S. introduces more restrictions on AI chip sales across the world

U.S. AI tech

In a significant move to maintain its technological edge and ‘national security’, the United States has announced new restrictions on the sale of advanced AI chips to most countries around the world

This decision, unveiled in the final days of President Joe Biden’s administration, aims to limit the global distribution of AI technology while ensuring that America’s closest allies continue to have access to these critical resources.

Regulation

The new regulations will cap the number of AI chips that can be exported to most countries, while allowing unlimited access to U.S. AI technology for America’s closest allies, including Japan, UK, South Korea, and the Netherlands.

This approach is designed to prevent adversaries like China, Russia, Iran, and North Korea from acquiring advanced computing power that could enhance their military capabilities.

Commerce Secretary Gina Raimondo emphasised the importance of maintaining U.S. leadership in AI development and chip design. ‘The U.S. leads AI now – both AI development and AI chip design, and it’s critical that we keep it that way,’ she reportedly said.

The regulations are part of a broader effort to close loopholes and add new guardrails to control the flow of AI chips and the global development of AI.

AI rules

The new rules will place limits on the export of advanced graphics processing units (GPUs), which are essential for powering data centers needed to train AI models. Companies like Nvidia and Advanced Micro Devices, which produce these chips, will be significantly impacted by the new regulations.

Major cloud service providers, such as Microsoft, Google, and Amazon, will be able to seek global authorisations to build data centres, exempting their projects from the country quotas on AI chips.

The Biden administration’s decision has faced criticism from industry leaders. Nvidia, a leading producer of AI chips, called the new rules “sweeping overreach” and argued that the restrictions would clamp down on technology already available in mainstream gaming PCs and consumer hardware.

Oracle, a major data center provider, expressed concerns that the rules would hand over a significant portion of the global AI and GPU market to Chinese competitors.

Despite the opposition, the U.S. government remains steadfast in its commitment to protecting national security and maintaining its technological dominance. The new regulations are set to take effect in 120 days, giving the incoming administration of President-elect Donald Trump time to weigh in on the implementation and enforcement of the rules.

Restrictions

The U.S. restrictions on AI chip sales represent a strategic effort to safeguard ‘national security’ and maintain leadership in AI technology.

While the new regulations have sparked controversy and criticism from industry leaders, the government’s focus on controlling the global distribution of AI chips underscores the importance of technological sovereignty in an increasingly competitive world

UK wants to control its own AI direction – suggesting a divergence from the EU and U.S.

UK tech

The UK is charting its own course when it comes to regulating artificial intelligence, signaling a potential divergence from the approaches taken by the United States and the European Union. This move is part of a broader strategy to establish the UK as a global leader in AI technology.

UK AI framework

Britain’s minister for AI and digital government, Feryal Clark, emphasised the importance of the UK developing its own regulatory framework for AI.

She highlighted the government’s strong relationships with AI companies like OpenAI and Google DeepMind, which have voluntarily opened their models for safety testing. Prime Minister Keir Starmer echoed these sentiments, stating that the UK now has the freedom to regulate AI in a way that best suits its national interests following Brexit.

Unlike the EU, which has introduced comprehensive, pan-European legislation aimed at harmonising

AI rules across the bloc, the UK has so far refrained from enacting formal laws to regulate AI.

Instead, it has deferred to individual regulatory bodies to enforce existing rules on businesses developing and using AI. This approach contrasts with the EU’s risk-based regulation and the U.S.’s patchwork of state and local frameworks.

Labour Party Plan

During the Labour Party’s election campaign, there was a commitment to introducing regulations focusing on ‘frontier’ AI models, such as large language models like OpenAI’s GPT. However, the UK government has yet to confirm the details of proposed AI safety legislation, opting instead to consult with the industry before formalising any rules.

The UK’s AI Opportunities Action Plan, endorsed by tech entrepreneur Matt Clifford, outlines a comprehensive strategy to harness AI for economic growth.

The plan includes recommendations for scaling up AI capabilities, establishing AI growth zones, and creating a National Data Library to support AI research and innovation. The government has committed to implementing these recommendations, aiming to build a robust AI infrastructure and foster a pro-innovation regulatory environment.

Despite the ambitious plans, some industry leaders have expressed concerns about the lack of clear rules. Sachin Dev Duggal, CEO of AI startup Builder.ai, reportedly warned that proceeding without clear regulations could be ‘borderline reckless’.

He reportedly highlighted the need for the UK to leverage its data to build sovereign AI capabilities and create British success stories.

The UK’s decision to ‘do its own thing’ on AI regulation reflects its desire to tailor its approach to national interests and foster innovation.

While this strategy offers flexibility, it also presents challenges in terms of providing clear guidance and ensuring regulatory certainty for businesses. As the UK continues to develop its AI regulatory framework, it will be crucial to balance innovation with safety and public trust

Elon Musk wants to make Tesla a $25 trillion company by 2040

Autonomous vehicle

Elon Musk’s Vision for Tesla’s Trillion Dollar Future

Elon Musk, the visionary CEO of Tesla, has consistently set ambitious goals for the company. Among his most audacious claims is that Tesla could potentially become a multi trillion-dollar company and even reach a valuation of $25 trillion, largely driven by the deployment of robotaxis.

Robotaxi vision

Tesla’s robotaxi concept is centred around autonomous vehicles that can operate as self-driving taxis. These vehicles are equipped with Tesla’s Full Self-Driving (FSD) technology, which Musk believes will revolutionize transportation. By transforming Tesla cars into autonomous ride-sharing vehicles, the company could generate significant revenue without increasing the number of cars sold.

Projections

Musk’s financial projections are based on the immense potential of the robotaxi market

  1. Revenue Generation: Each Tesla vehicle could earn substantial income as a robotaxi. If Tesla owners opt into the robotaxi network, Tesla could take a share of the revenue generated from these rides.
  2. Cost Efficiency: Autonomous driving reduces the need for human drivers, leading to lower operational costs. This efficiency could make robotaxis more affordable for users and highly profitable for Tesla.
  3. Reduced pollution: will help meet green energy goals.
  4. Market Penetration: As autonomous technology matures, the adoption of robotaxis could grow rapidly, capturing a significant share of the global transportation market.

Market potential

The global ride-hailing market is already valued at hundreds of billions of dollars, and with the introduction of autonomous vehicles, this market is expected to expand further. Tesla’s early entry and continuous advancements in FSD technology position it to be a dominant player in this space.

Challenges

While the potential is enormous, there are several challenges and scepticism surrounding Musk’s projections

  1. Regulatory Hurdles: Autonomous vehicles must navigate a complex regulatory landscape. Approval processes and safety standards vary by region, which could delay widespread adoption.
  2. Technical Milestones: Achieving full autonomy is a significant technical challenge. Tesla’s FSD technology is still in development, and perfecting it for widespread use requires overcoming numerous technical obstacles.
  3. Market Competition: Tesla is not the only player in the autonomous vehicle market. Competitors like Waymo, Cruise, and traditional automakers are also investing heavily in autonomous technology.

Conclusion

Elon Musk’s vision of making Tesla a trillion-dollar and eventually a $25 trillion company through robotaxis is both bold and captivating. The success of this vision hinges on the successful deployment and adoption of autonomous driving technology. While there are significant challenges to overcome, Musk’s track record of defying odds and achieving groundbreaking innovations keeps the possibility within the realm of achievable dreams.

The future of transportation, as envisioned by Musk, could fundamentally reshape how we move and how Tesla thrives as a pioneer in autonomous mobility.

Tesla’s future does seem promising with the introduction of Optimus, their humanoid robot, as well as their advancements in solar energy and battery technology.

The future looks very bright for Tesla.

Apple, Amazon and Intel all post positive results 31st October 2024

Apple

Apple’s fourth-quarter results surpassed Wall Street forecasts for revenue and earnings per share. However, net income declined due to a one-time charge related to a tax settlement in Europe.

iPhone sales and overall sales both rose by 6%.

Apple one year stock chart

Amazon

Amazon’s shares soared in after-hours trading following the announcement of earnings and revenue that exceeded expectations. The firm’s cloud services and advertising divisions demonstrated significant expansion.

Amazon one year stock chart

Intel

Intel has reported earnings that surpassed expectations and provided improved guidance. The company is currently undergoing a significant restructuring initiative.

Intel one year stock chart

However, Intel has now lost over half its market value.

Nasdaq hits new all-time high – Tesla enjoys another great day

Nasdaq index at new high!

The Nasdaq Composite climbed to an all-time high on Friday 25th October 2024, boosted by BIG tech stocks.

The tech-heavy index rose 0.56% to 18,518.61

The tech-heavy Nasdaq Composite index rose 0.56% to 18,518.61

Tech stocks boosted the market ahead of their upcoming earnings. Nvidia added 0.8%, and shares of Meta Platforms, Amazon and Microsoft were also higher.

Some analysts are suggesting it may be time to short Amazon and Apple as they head into earnings season? Let’s see.

Tesla helped boost the Nasdaq as its stock climbed to close at a 13-month high, sustaining its rally post-earnings.

Tesla enjoyed its best market day since 2013, the stock rose more than 3% on Friday 25th October 2024, closing at its highest since September 2023.

Tesla 5-day stock chart as of 25th October 2024

Tesla 5-day stock chart as of 25th October 2024

Amazon goes nuclear, to invest more than $500 million to develop small modular reactors (SMR)

AWS nuclear power

Amazon Web Services (AWS) has announced the signing of an agreement with Dominion Energy, the utility company of Virginia U.S., to explore the development of a small modular nuclear reactor near Dominion’s existing North Anna nuclear power station.

As Amazon’s cloud computing subsidiary, AWS has an ever-growing demand for clean energy, particularly as it expands into generative AI. This agreement aligns with Amazon’s journey towards net-zero carbon emissions.

Amazon joins other major tech companies like Google and Microsoft in turning to nuclear power to meet the increasing energy needs of data centres.