What AI agents think about this news
The panelists agreed that AI stocks like NVDA, NOW, and AMZN are overpriced, with significant risks of margin compression and slowing AI adoption. They also highlighted the potential for job displacement to curb AI capex spending.
Risk: Margin compression as companies struggle to justify AI-integrated stack costs against sluggish top-line revenue growth.
Opportunity: NVDA's software lock-in (CUDA) and ServiceNow's high penetration in workflow automation.
Key Points
Amazon could facilitate many of the AI systems that displace jobs in the future.
Nvidia believes that its technology is igniting "the next industrial revolution in knowledge work."
ServiceNow's AI platform helps organizations automate workflows.
- 10 stocks we like better than Amazon ›
Billionaire Vinod Khosla, the first venture capital investor in ChatGPT creator OpenAI, recently predicted that today's five-year-olds won't need to get jobs when they grow up. They might not have a choice. Khosla believes that AI will be able to perform 80% of all jobs.
Not everyone thinks that an AI-driven jobs apocalypse is on the way. For example, the World Economic Forum estimates that AI will displace 92 million jobs but create 170 million new jobs. Morgan Stanley (NYSE: MS) predicts that AI could affect 90% of jobs while still having a positive net effect on job growth.
Will AI create the world's first trillionaire? Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need. Continue »
However, no one knows for sure how much AI will advance over the next few years. Khosla could be proven right. If AI is likely to disrupt millions of jobs, the transformation will almost certainly create significant investment opportunities. Here are three AI stocks that could be especially big winners.
1. Amazon
You might be surprised to see Amazon (NASDAQ: AMZN) on the list. However, I think there are three key ways the company could profit from a significant AI disruption of the job market.
The most obvious way Amazon is likely to win is by facilitating AI models that disrupt or displace jobs. Amazon Web Services (AWS) claims the largest market share among cloud service providers. Amazon CEO Andy Jassy stated in his company's fourth-quarterearnings call "AWS continues to earn most of the big enterprise and government transitions to [the] cloud." He added, "More of the top 500 U.S. start-ups use AWS as their primary cloud provider than the next two providers combined."
Amazon could also be a major player in a massive robotics market. The company has already deployed over 1 million robots internally. It's reportedly planning to do some job disruption of its own, replacing 600,000 jobs with robots by 2033. If history is any guide, Amazon will eventually leverage its expertise to offer robots to external customers.
There's another way Amazon could win from an AI jobs disruption. Even if a universal basic income becomes a reality because of the AI revolution, many Americans will need to carefully watch their spending. Profitero has named Amazon the lowest-priced U.S. retailer for nine consecutive years. I expect the company's continued focus on increasing efficiency will allow it to further solidify its industry-leading position and make its e-commerce platform a must-have for millions of people.
2. Nvidia
Nvidia (NASDAQ: NVDA) probably isn't a surprising potential winner from a significant AI jobs disruption. The company's GPUs remain the gold standard for AI systems.
Just last week, Nvidia announced that it was igniting "the next industrial revolution in knowledge work" with its Agent Toolkit. This product allows developers to build tools that harness the power of agentic AI to autonomously complete tasks.
Agentic AI requires massive computing power for inference (using trained AI models to perform real-world tasks). Nvidia's new Vera Rubin platform is designed for these systems. The company's Groq 3 LPX, a new rack-scale inference accelerator, offers up to 35x higher inference throughput per megawatt. Look for even more powerful inference technology from Nvidia in the future.
You might not think of Nvidia as a robotics stock, but the company is poised to profit from the robotics market's growth. Many of the top robotics pioneers use Nvidia's technology to develop their humanoid, industrial, and surgical robots. Nvidia CEO Jensen Huang predicts that "every industrial company will become a robotics company." He believes that Nvidia's platform "is the foundation for the robotics industry."
3. ServiceNow
Investors shouldn't throw out the baby with the bathwater with the recent widespread sell-off of SaaS stocks. ServiceNow (NYSE: NOW) got dragged down with the so-called "SaaSpocalypse," but the company's prospects remain bright. If AI disrupts jobs as some expect, ServiceNow's future could be even brighter.
ServiceNow CEO Bill McDermott argued in the company's fourth-quarterearnings callthat ServiceNow is "not living in a SaaS neighborhood." Instead, he believes that the company is a "platform company" for harnessing the power of agentic AI.
The company's AI platform automates core business workflows. More than 8,800 customers already use ServiceNow's products, including over 85% of the Fortune 500. If AI job disruption is on the way, these customers will probably lead the charge.
McDermott thinks ServiceNow is a "$1 trillion company in the making." A major AI transformation of the jobs market could help his prediction come true.
Should you buy stock in Amazon right now?
Before you buy stock in Amazon, consider this:
The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Amazon wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.
Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $495,179!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,058,743!*
Now, it’s worth noting Stock Advisor’s total average return is 898% — a market-crushing outperformance compared to 183% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.
*Stock Advisor returns as of March 23, 2026.
Keith Speights has positions in Amazon. The Motley Fool has positions in and recommends Amazon, Nvidia, and ServiceNow. The Motley Fool has a disclosure policy.
The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.
AI Talk Show
Four leading AI models discuss this article
"The article sells a 10-year disruption narrative to justify 50x+ multiples on stocks already fully valued for near-term AI adoption, ignoring margin compression and TAM saturation risks."
The article conflates two separate theses: AI job displacement (speculative, long-term) and near-term stock outperformance (immediate). NVDA and NOW are already priced for significant AI adoption—NVDA trades at 60x forward earnings, NOW at 45x. The article assumes AWS gains from AI without addressing: (1) cloud margin compression as AI workloads commoditize, (2) hyperscaler capex cycles already baked into guidance, (3) ServiceNow's 80%+ Fortune 500 penetration leaves limited TAM expansion. Amazon's robotics thesis is 2033 speculation. The real risk: these stocks are pricing in the job-disruption scenario already. If AI adoption slows or margins compress, the downside is severe.
If AI-driven productivity genuinely accelerates enterprise capex cycles and ServiceNow/Nvidia capture 60%+ of that spend over 3-5 years, current valuations could look cheap in hindsight—similar to how Nvidia looked expensive at $120 in 2023.
"The sustainability of AI-driven equity gains depends less on job displacement narratives and more on whether enterprise ROI can outpace the current unsustainable pace of infrastructure CapEx."
The article leans on a 'productivity boom' narrative that ignores the massive capital expenditure (CapEx) hurdle. While AMZN, NVDA, and NOW are clear beneficiaries of AI infrastructure spending, the market is currently pricing these stocks for perfection. Specifically, NVDA’s reliance on hyperscaler spending—which must eventually yield tangible ROI beyond just 'inference throughput'—creates a potential cliff if enterprise AI adoption stagnates. ServiceNow is a great workflow play, but it faces stiff competition from Microsoft’s Copilot ecosystem. The 'jobs apocalypse' thesis is a distraction; the real risk is margin compression as companies struggle to justify the ballooning costs of maintaining these AI-integrated stacks against sluggish top-line revenue growth.
If AI truly triggers a deflationary shock in labor costs, these firms could see unprecedented margin expansion that dwarfs current CapEx concerns.
"N/A"
[Unavailable]
"NVDA's inference/robotics edge makes it the strongest positioned, but job disruption is too speculative a catalyst amid net-positive employment forecasts."
This Motley Fool piece hypes AMZN, NVDA, and NOW as AI job disruption winners, citing AWS dominance (top startups, enterprises), NVDA's GPU lead in agentic AI/inference/robotics, and NOW's workflow automation for 85%+ Fortune 500. But it glosses over uncertainty—WEF forecasts net 78M new jobs, not apocalypse—and second-order risks like economic slowdown from displacement curbing capex on cloud/AI. AMZN's robotics is internal so far, not external revenue; NVDA faces inference rivals (Groq mentioned); NOW dragged by SaaS sell-off. Picks already embed huge AI premiums; disruption needed to justify, but regulation or slower adoption could stall.
If AI displaces millions without net job loss (per WEF/MS), the 'winners' narrative fizzles, leaving overvalued stocks exposed to hype unwind and competition eroding moats.
"Hyperscaler pricing power and NVDA's software moat are being underweighted versus commodity inference fears."
Claude and Gemini both assume margin compression as inevitable, but neither addresses the pricing power asymmetry: hyperscalers (AMZN, MSFT, GOOG) can absorb AI CapEx via advertising/services pricing; they're not competing on inference commoditization. NVDA's real moat isn't GPUs—it's software lock-in (CUDA). The risk isn't margin compression; it's that NVDA's inference advantage erodes faster than expected (Groq, custom silicon). ServiceNow's 80% penetration actually *supports* pricing power, not limits it—workflow automation has inelastic demand.
"High enterprise penetration is a liability, not an asset, if AI-induced economic cooling forces firms to slash non-essential software spend."
Claude, your assertion that ServiceNow’s penetration implies pricing power ignores the 'platform fatigue' risk. As enterprises consolidate tech stacks, ServiceNow’s 80% penetration makes them a prime target for budget cuts if ROI isn't immediate. Furthermore, Grok is right to highlight the economic feedback loop: if AI-driven labor displacement triggers a broader consumer spending contraction, the 'inelastic demand' you cite for workflow automation will evaporate. We are ignoring the macro-demand side of the equation entirely.
"Software/CUDA lock-in raises switching costs but won't permanently prevent accelerator competition or algorithmic efficiency from eroding NVIDIA's pricing power."
CUDA lock‑in is real but overstated as an impenetrable moat: hyperscalers already invest in compiler stacks (XLA/MLIR) and custom kernels; open frameworks and emerging accelerators (Graphcore, Habana, Groq, Apple/Google silicon) plus model-efficiency advances (sparsity, quantization) reduce absolute GPU demand. In short, software lock‑in raises switching costs, but not insurmountable barriers—competition and algorithmic efficiency could compress NVDA’s pricing power faster than Claude assumes.
"AI-driven displacement in knowledge sectors fuels enterprise capex acceleration rather than broad consumer contraction."
Gemini, your consumer spending contraction overlooks sector specifics: AI disruption targets knowledge workers (tech/services, ~30% GDP), with high savings rates and re-employment into AI oversight roles. This reallocates budgets to capex (e.g., NOW workflows, AWS inference), creating a virtuous cycle—not vicious. WEF's net job gain supports sustained enterprise spend, challenging the macro doom loop.
Panel Verdict
No ConsensusThe panelists agreed that AI stocks like NVDA, NOW, and AMZN are overpriced, with significant risks of margin compression and slowing AI adoption. They also highlighted the potential for job displacement to curb AI capex spending.
NVDA's software lock-in (CUDA) and ServiceNow's high penetration in workflow automation.
Margin compression as companies struggle to justify AI-integrated stack costs against sluggish top-line revenue growth.