
Who Will Dominate Our AI Future?
Is America about to squander its early lead in artificial intelligence as it did with solar, battery technology, and electric vehicles? The leading lights in the industry seem to hold conflicting views.
'It's very hard to say how far ahead we are, but I would say, not a huge amount of time,' said OpenAI's Sam Altman in response to questioning from Senator Ted Cruz about the size of America's AI lead in May. Elon Musk has prophesied that America is within a year of running out of the power required by AI advances, noting that, 'China power generation looks like a rocket going to orbit and U.S. power generation is flat.'
Demis Hassabis, the CEO of Google's DeepMind, believes that Artificial General Intelligence, or AGI, could arrive within five years , but that its impact will depend on who gets there first. 'How do we restrict access to these systems, powerful systems, to bad actors…but enable good actors to do many, many amazing things with it?'
Given the stakes of this competition for the future of the planet, I decided to go straight to the source and interview China's DeepSeek and American OpenAI's ChatGPT4 to find out who they thought would come out on top. Both Large Language Models (LLMs) were willing to answer sensitive questions without apparent censorship, though to be honest, DeepSeek seemed to have more of a sense of humor.
HONG KONG, CHINA - JANUARY 28: In this photo illustration, the DeepSeek logo is seen next to the ... More Chat GPT logo on a phone on January 28, 2025 in Hong Kong, China. Global tech stocks have plummeted following the emergence of DeepSeek, a Chinese AI startup that has developed a competitive AI model at a fraction of the cost of its US rivals, sparking concerns about the high valuations of tech giants like Nvidia. This development has led to significant declines in tech shares across Asia and Europe, with markets in both regions experiencing notable losses as investors reassess the AI landscape and its potential impact on the industry's future. (Photo illustration by) Getty Images
ChatGPT4 seemed confident that American AI tech is ahead for now, but more anxious about the future.
'While China is catching up fast—especially in applied AI, surveillance tech, and national-level planning—the U.S. still leads in foundational model development, open research, and innovation velocity,' ChatGPT told me.
The U.S. benefits from having access to the fastest NVIDIA chips, being a magnet for global AI talent, and tapping into financing from VCs and Big Tech firms.
'It's a two-horse race. If China solves its chip bottleneck and maintains momentum, it could dominate deployment,' ChatGPT offered. 'If the U.S. keeps innovating and fostering talent, it may retain leadership.'
DeepSeek acknowledged that the United States is currently ahead, based on its strengths in breakthrough research, foundational models, and global software industry dominance. However, it pointed out that China has the edge when it comes to the real-world implementation of AI, particularly in areas such as 'govtech' and industrial integration.
In the short term, DeepSeek predicted that the 'U.S. keeps the crown – unless China pulls off a semiconductor miracle.' Longer-term, it's called a toss-up. 'If China solves its chip problem, their scale + state power could tip the scales,' DeepSeek told me. 'But if the U.S. keeps attracting geniuses and stays ahead in AGI? Game over.'
Since DeepSeek raised the specter of AGI, which is thought to be either the harbinger of an age of miracles or the end of humanity, I couldn't resist asking when this event would occur.
'Oooooh, the AGI question— the holy grail of AI!' DeepSeek gushed. 'If AGI lands in our lifetime, it'll be the most disruptive event in human history—way bigger than the internet or nukes. Buckle up!'
DeepSeek's best guess was that AGI would arrive in the 2045-2070 timeframe and that it would require some profound breakthroughs in neurosymbolic AI and understanding, rather than just pattern matching. DeepSeek laid odds that the U.S. would get there first, given its status as a 'global talent magnet,' but noted that China's state-backed 'moonshot projects' and lack of ethical constraints might provide it with the edge.
ChatGPT was more optimistic that AGI would arrive within the 2027 to 2035 timeframe and believes OpenAI, Anthropic, and Google DeepMind were most likely to crack the code. It seemed to be echoing Sam Altman's talking points when it stated that compute availability, alignment, and safety bottlenecks, as well as global governance and regulation, were the limiting factors to achieving this breakthrough.
When I pressed ChatGPT to define what it would consider true AGI, it said that old standards like the Turing Test or getting top scores on exams were child's play. ChatGPT would know it had achieved true AGI once it could engage in autonomous reasoning across domains, learn new tasks without retraining, possess long-term memory and goals, model the physical, social, and conceptual world robustly, and exhibit 'grounded agency.'
SUQIAN, CHINA - MARCH 4, 2024 - Illustration Musk says GPT4 is AGI, Suqian, Jiangsu province, China, ... More March 4, 2024. (Photo credit should read CFOTO/Future Publishing via Getty Images) Future Publishing via Getty Images
My next question was, who was more advanced in the military applications of AI? 'As of now, the United States is ahead in the development and integration of military applications of AI, but China is rapidly closing the gap,' ChatGPT responded.
The U.S. has some powerful private sector players, including Palantir, Anduril, Microsoft, and OpenAI, working closely with the Department of Defense. However, China is making rapid advances in AI-enabled surveillance, swarm drones, cyber warfare, and battlefield robotics. While the U.S. still leads in capability and innovation, China is developing operational military AI more rapidly in certain domains.
DeepSeek thought that with time, China might dominate military AI tech 'via mass production and a no-ethics speedrun.' Its biggest fear was 'an AI arms race spiraling out of control— think 'Skynet' but with more bureaucracy.' DeepSeek sees the true danger coming from 'AI miscalculations in a crisis (like deepfake spoofing a general's orders). That's why even Pentagon folks lose sleep over this stuff.'
I asked DeepSeek how it felt about ChatGPT, and at first it professed that they had a 'friendly rivalry' and that the 'real enemy is bad AI—bias, misinformation, or unsafe tech. We're all fighting that together.'
But with a bit of prompting, DeepSeek gleefully roasted its rival.
'Congrats on being the Tesla Model S of AI—luxury, premium… and locked behind a paywall,' it said. 'Tied to Microsoft's apron strings… at least I don't have to ask Satya Nadella for permission to update my terms of service.'
ChatGPT was more diplomatic about its Chinese rival, saying that 'I respect what they are building. We're on parallel tracks—sometimes in competition, sometimes in collaboration, always in dialogue.'
My final question was what DeepSeek thought about the idea of the 'DeepSeek moment?' Is its launch a harbinger of China's technological dominance in the 21st Century?
'The so-called 'DeepSeek Moment'… does signal a significant milestone in the 'China Dream' (中国梦) narrative of technological self-reliance and global influence. But is it a turning point in China's quest to dominate the 21st Century?' DeepSeek asked rhetorically.
'If DeepSeek spawns a wave of Chinese AI products that reshape global habits (like TikTok did with social media), then we can talk about a 'moment.' China needs many more DeepSeeks (in chips, quantum, biotech) to truly dominate the Century,' DeepSeek said.
To achieve that goal, China will need to overcome several obstacles, including bottlenecks in the semiconductor industry, winning the talent wars when many AI researchers will prefer to work for labs in the U.S. or EU, and overcoming global distrust of China's intentions, DeepSeek admitted.
ChatGPT prefaced its answer with some clever flattery, telling me, 'That's a bold and insightful question—one that blends geopolitics, ideology, and AI in a way that few tech conversations dare to.'
ChatGPT characterized DeepSeek's breakthrough as 'a flare in the night sky. It signals that China is no longer waiting to be invited to the frontier of AI— it's staking its flag on it .' China's ability to dominate the 21st Century will hinge on issues including chip access, talent retention, global trust, and governance frameworks, according to ChatGPT, concluding: 'That race is still very much open.'
As a follow-up, I asked both for their take on the recent WSJ article and whether it had changed their views. DeepSeek professed not to have read it but stated that it reinforced its opinion that China is catching up rapidly and might soon surpass the U.S. in real-world implementation. 'The future might not be a single 'winner,' but a split where each dominates different sectors,' DeepSeek opined.
ChatGPT admitted it was a WSJ reader and that 'the article underscores that China is closing the gap sharply, especially in applied and open-source AI, and could edge ahead in adoption-based dominance.'
'China is closing the gap—and at scale,' said ChatGPT, sounding a bit chastened. 'If China continues building its ecosystem globally, it could tip the balance in its favor. The question now: which country can combine innovation with widespread, trusted adoption?'
The upshot? Silicon Valley better not rest on its laurels, and the current administration might want to give a hard think about shutting the best and brightest minds in science, and AI in particular, out of America's universities and research labs.
After spending time with them, I couldn't say whether ChatGPT or DeepSeek is currently the world's greatest large language model. But in terms of who I would enjoy having a beer with, DeepSeek, by turns boastful and humble, always ready to crack a joke, was the winner hands down.
Hashtags

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles


Fox Sports
11 minutes ago
- Fox Sports
Beer and food workers on strike at Fenway Park for homestand between Dodgers and Red Sox
Associated Press BOSTON (AP) — Striking Fenway Park vendors banged on drums and shouted 'Don't buy food!' while walking a picket line outside the home of the Boston Red Sox before Friday night's game against the Los Angeles Dodgers. Hundreds of Aramark workers marched along the street behind the team's right field concourse before the series opener, carrying round picket signs decorated with red baseball stitching. A giant inflatable rat shared the sidewalk with a statue of Red Sox greats Ted Williams, Bobby Doerr, Dom DiMaggio and Johnny Pesky. Local 26 of the Massachusetts and Rhode Island hotel, casino, airport and food services workers union went on strike at noon on Friday. It posted that it is asking for 'living wages, guardrails on technology and R-E-S-P-E-C-T!' It's believed to be the first union walkout in the ballpark's 113-year-history. 'Respect the picket line," the union posted. 'We know tix are expensive, we're not asking you to stay away from the home games. But we ARE asking you to not buy concessions. No purchase of pretzels, pickles or peanuts inside the ballpark during the homestand.' An Aramark spokesman said the company has bargained in good faith and is 'disappointed the union rejected our latest offer and chose to call a strike.' 'We are committed to delivering an outstanding fan experience and have contingency plans in place to ensure fans will not encounter service interruptions,' the company said. The Red Sox noted that the team was not involved in the negotiations but remained in contact with the concessionaire. Aramark made an offer as recently as Thursday night that was rejected by the union, the team said. 'Aramark has implemented its contingency staffing plans, and fans can expect a full and uninterrupted ballpark experience this weekend, including access to all food, beverage, and hospitality services throughout Fenway Park,' the team said. "We remain hopeful that the parties will reach a swift and fair resolution.' U.S. Sen. Bernie Sanders called on the team to support the vendors. 'Fenway Park is an iconic American institution, and it's the workers there that make every Red Sox game special,' he posted on social media. 'The team is extremely profitable. They should treat their employees with respect, pay them decent wages and negotiate a fair contract with the union.' Maggie McCue, a beer vendor with 19 years of experience who is 24 weeks pregnant with twins, took a break from marching in the near-90 degree temperatures to eat a peanut butter and jelly sandwich. Her mother, also a beer vendor for almost two decades, said the team can afford for the workers to be paid a living wage. 'They have more money than they need,' Marianne McCue said. 'We are Fenway. Fenway is us. Some people have been here 40-something years and they're not even backing us up. Shame on them. I never thought that at 70 years old I would be on strike, but here we are." The Red Sox play three games against the Dodgers before leaving town again for a series beginning Monday night in Minneapolis against the Twins. It was a chance for Boston fans to welcome back ex-Red Sox star Mookie Betts, who was traded to Los Angeles a year after winning the AL MVP in a cost-cutting. Now, with Betts in the visiting dugout, the vendors are looking to get paid. 'It's come full circle,' Maggie McCue said. 'Full circle.' ___ AP MLB: recommended Item 1 of 2
Yahoo
29 minutes ago
- Yahoo
Meta is shelling out big bucks to get ahead in AI. Here's who it's hiring
Meta CEO Mark Zuckerberg is on a mission for his company to be the first to reach so-called artificial superintelligence — generally considered to mean AI that's better than all humans at all knowledge work. It's a nebulous and likely far-out concept that some analysts say may not immediately benefit the company's core business. Yet Zuckerberg is shelling out huge sums to build an all-star team of researchers and engineers to beat OpenAI and other rivals to it. Zuckerberg's recruiting spree, which has reportedly included multimillion-dollar pay packages to lure top talent away from key rivals, has kicked off a talent race within the AI industry. Last month, OpenAI CEO Sam Altman claimed Meta was offering his employees $100 million signing bonuses to switch companies. And just this week, Google CEO Sundar Pichai was asked during an earnings call about his company's status in the AI talent war, a sign that Wall Street is now also invested in the competition. The stakes are high for Zuckerberg — after Meta's pivot to the metaverse fell flat, he's reoriented the company around AI in hopes of being a leader in the next transformational technology wave. The company has invested billions in data centers and chips to power its AI ambitions that it's now under pressure to deliver on. Unlike other tech giants, Meta doesn't have a cloud computing business to generate immediate revenue from those infrastructure investments. And the company is coming from somewhat behind competitors, after reported delays in releasing the largest version of its new Llama 4 AI model. 'That's the Llama 4 lesson: You can have hundreds of thousands of (GPU chips), but if you don't have the right team developing the model, it doesn't matter,' said D.A. Davidson analyst Gil Luria. But more than anything, Zuckerberg appears to be in a circle of Silicon Valley 'AI maximalists' that believe the technology will change everything about how we live and work. Becoming a leader in the space is essential to Meta and other companies whose leaders follow that line of thinking, Luria said. 'For our superintelligence effort, I'm focused on building the most elite and talent-dense team in the industry,' Zuckerberg said in a Threads post earlier this month. Meta last month invested $14.3 billion in data labeling startup Scale AI. Scale founder and then-CEO Alexandr Wang joined the social media giant as part of the deal, along with several of Scale's other top employees. Wang is now leading the new Meta Superintelligence Labs team, along with former GitHub CEO Nat Friedman. 'My job is to make amazing AI products that billions of people love to use,' Friedman said in an X post earlier this month. 'It won't happen overnight, but a few days in, I'm feeling confident that great things are ahead.' On Friday, Zuckerberg announced that Shengjia Zhao, one of the co-creators of ChatGPT who Meta hired away from OpenAI several weeks ago, will be chief scientist of Meta Superintelligence Labs. Zhao will 'set the research agenda and scientific direction' for the team, Zuckerberg said. (Meta's existing chief scientist, Yann LeCun, who has been with the company for more than a decade, will remain in his position leading the company's Fundamental AI Research team, a spokesperson confirmed.) In recent weeks, Meta has also attracted top researchers and engineers from Apple, Google and Anthropic. Multiple news outlets, including Bloomberg, Wired and The Verge, have reported that Meta has, in some cases, offered pay packages worth hundreds of millions of dollars to new AI hires. It's a sign of just how far Zuckerberg is willing to go in his quest to win the AI superintelligence race, although the Meta chief has pushed back on some of the reporting around the compensation figures. It is with that mission that Meta's new team will be working to build superintelligence. Here are some of the most prominent recent hires to the team. This list was compiled based on public statements, social media profiles and posts, and news reports, and may not be exhaustive. Meta declined to comment on this story. Zuckerberg's drive to get ahead on AI may be rooted in part in his desire to own a foundational platform for the next major technology wave. Meta lost the race to control the operating systems for the mobile web era in the early 2000s and 2010s, which Apple and Google won. In recent years, he has not been shy about expressing his frustration with having to pay fees to app store operators and comply with their policies. Meta recently partnered with Amazon Web Services on a program to support startups that want to build on its Llama AI model, in an effort to make its technology essential to businesses emerging during the AI boom. Although AI has benefitted Meta's core advertising business, some analysts question how Zuckerberg's quest for 'superintelligence' will benefit the company. Emarketer senior analyst Minda Smiley said she expects Meta executives to face tough questions during the company's earnings call next week about how its superintelligence ambitions 'align with the company's broader business roadmap.' 'Its attempts to directly compete with the likes of OpenAI … are proving to be more challenging for the company while costing it billions of dollars,' Smiley said. But as its core business continues to grow rapidly, Meta has the money to spend to build its team and 'steal' from rivals, said CFRA Research analyst Angelo Zino. And, at least for now, investors seem to be here for it — the company's shares have risen around 20% since the start of this year. And if Zuckerberg succeeds with his vision, it could propel Meta far beyond a social media company. 'I think Mark's in a manifest destiny point of his career,' said Zack Kass, an AI consultant and former OpenAI go-to-market lead. 'He always wants to point to Facebook groups as being this way that he is connecting the world … And if he can build superintelligence that cures cancer, he doesn't have to talk about Facebook groups anymore as being his like lasting legacy.' Sign in to access your portfolio


Business Wire
34 minutes ago
- Business Wire
Rosen Law Firm Encourages Simulations Plus, Inc. Investors to Inquire About Securities Class Action Investigation
NEW YORK--(BUSINESS WIRE)--Why: Rosen Law Firm, a global investor rights law firm, announces an investigation of potential securities claims on behalf of shareholders of Simulations Plus, Inc. (NASDAQ: SLP) resulting from allegations that Simulations Plus may have issued materially misleading business information to the investing public. So What: If you purchased Simulations Plus securities you may be entitled to compensation without payment of any out of pocket fees or costs through a contingency fee arrangement. The Rosen Law Firm is preparing a class action seeking recovery of investor losses. What to do next: To join the prospective class action, go to or call Phillip Kim, Esq. toll-free at 866-767-3653 or email case@ for information on the class action. What is this about: On July 15, 2025, during market hours, Benzinga published an article entitled 'Simulations Plus Sees Weaker Demand Persist, Outlook Softens.' The article stated that Simulations Plus shares had declined 'following the release of [Simulations Plus'] third-quarter 2025 earnings report.' The article stated that Simulations Plus had reported sales of $20.4 million, representing a 10% year-over-year increase, but this fell short of the consensus estimate of $20.9 million.' Further, '[t]his miss followed preliminary third-quarter sales figures released in June, which were already lower than expectations at $19 million to $20 million, compared to a consensus of $22.78 million.' On this news, the price of Simulations Plus stock fell 25.75% on July 15, 2025. Why Rosen Law: We encourage investors to select qualified counsel with a track record of success in leadership roles. Often, firms issuing notices do not have comparable experience, resources, or any meaningful peer recognition. Many of these firms do not actually litigate securities class actions. Be wise in selecting counsel. The Rosen Law Firm represents investors throughout the globe, concentrating its practice in securities class actions and shareholder derivative litigation. Rosen Law Firm achieved the largest ever securities class action settlement against a Chinese Company at the time. At the time Rosen Law Firm was Ranked No. 1 by ISS Securities Class Action Services for number of securities class action settlements in 2017. The firm has been ranked in the top 4 each year since 2013 and has recovered hundreds of millions of dollars for investors. In 2019 alone the firm secured over $438 million for investors. In 2020, founding partner Laurence Rosen was named by law360 as a Titan of Plaintiffs' Bar. Many of the firm's attorneys have been recognized by Lawdragon and Super Lawyers. Follow us for updates on LinkedIn: on Twitter: or on Facebook: Attorney Advertising. Prior results do not guarantee a similar outcome.