Bởi Maksym Misichenko · Nasdaq ·
Các tác nhân AI nghĩ gì về tin tức này
The panel is bearish on Oklo's co-located SMR data-center concept, citing regulatory hurdles, scale economics, operational risks, and potential architectural mismatches with hyperscalers' redundancy requirements.
Rủi ro: Securing reliable fuel supply chains and waste disposal for scaled SMR deployments, as well as potential rejection by hyperscalers due to redundancy requirements.
Cơ hội: Potential timeline advantage through federal preemption powers for nuclear projects.
Phân tích này được tạo bởi đường dẫn StockScreener — bốn LLM hàng đầu (Claude, GPT, Gemini, Grok) nhận các lời nhắc giống hệt nhau với các biện pháp bảo vệ chống ảo tưởng tích hợp. Đọc phương pháp →
A Gallup poll shows 71% of Americans oppose AI data centers due to their impact on utility costs and the environment.
Nuclear start-up Oklo is partnering with power and cooling system designer Vertiv to co-locate small modular nuclear reactors and AI data centers.
The combination could circumvent local opposition by generating clean power and avoiding zoning restrictions.
The AI data center build-out just hit a rough patch.
According to a new Gallup poll, 71% of Americans oppose any construction of AI data centers in their area, with 48% strongly opposed. Meanwhile, just 7% strongly supported such construction. That's an incredibly lopsided result.
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 »
The reasons for the opposition were varied, but the most common concerns were data centers' excessive water and electricity use, their environmental impact, and their potential to raise utility bills. But in order for companies' AI investments to pay off, the infrastructure needs to be built without getting mired in years of litigation or red tape. Is there any way to make AI data centers palatable?
Surprisingly, nuclear energy company Oklo (NYSE: OKLO) might have an unexpected solution to this problem. Here's how the scrappy start-up's ambitious business plan could make everyone a winner (including its shareholders).
The strong bipartisan opposition to AI data centers is disrupting the AI build-out in communities across the country.
Local opposition has blocked or delayed at least $64 billion in U.S. data center construction projects since 2024, and that number is expected to increase as more projects come before local zoning boards and other decision makers who answer to voters. In the town of Warrenton, Virginia, for example, angry residents voted out every town council member who supported construction of a local Amazon data center. The new council then voted unanimously to approve a zoning change that permanently banned all data centers in the entire town.
Similar stories have recently played out in Oregon, Utah, New Jersey, and Massachusetts. This month, Maine became the first state to pass a statewide ban on AI data center construction. So, how could a lone nuclear power start-up stem the tide?
Oklo is a pre-commercial company that's currently building its first prototype power plant with a small modular reactor (SMR) at the Idaho National Laboratory. When completed, this "Aurora powerhouse" will provide up to 75 MW of nuclear power -- much less than a full-size nuclear power plant but enough to power about 50,000 residences.
Because AI data centers and nuclear power plants both require massive, electricity-hungry cooling systems, Oklo has partnered with manufacturer Vertiv (NYSE: VRT) to develop a cooling system for facilities that house an Oklo SMR and an AI data center. The same system would cool both the reactor and the data center, with the reactor providing all the electricity needed.
Not only would such a combined SMR/data center be more energy-efficient, it could also be located far from existing electric grids (and municipalities' pesky zoning regulations). Or it could send its excess power back to a local grid, easing potential energy shortages. Oklo plans to debut this combined cooling system technology at its first Aurora powerhouse, scheduled to go online late next year.
Oklo and Vertiv haven't publicly released details about what a co-located SMR data center would look like, or how large or powerful it would be. And until Oklo starts bringing its Aurora powerhouses online, we won't know if it's a viable plan, let alone one that could scale nationally.
That said, Gallup's poll showed that nuclear power plant construction polls 18 percentage points better than AI data center construction. It also found that carbon-neutral nuclear energy was the least politically divisive form of energy generation. So even if it takes years to bring Oklo nuclear-powered AI data centers to market, it might still be worth the wait for companies that are currently seeing their data centers mired in expensive litigation or canceled altogether by zoning law changes.
Keep in mind, though, that Oklo's business plan and technology are both highly speculative, making its stock a very risky buy at the moment, with plenty of volatility and potential for things to go wrong. Only the most risk-tolerant investors should even consider buying Oklo's stock now. But if Oklo can create an appetite for its nuclear-powered data centers, its stock could be a massive long-term winner.
Before you buy stock in Oklo, 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 Oklo 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 $463,900! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,294,401!
Now, it’s worth noting Stock Advisor’s total average return is 978% — a market-crushing outperformance compared to 211% 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 May 30, 2026. *
John Bromels has positions in Amazon and Oklo. The Motley Fool has positions in and recommends Amazon and Vertiv. 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.
Bốn mô hình AI hàng đầu thảo luận bài viết này
"Regulatory and construction timelines for nuclear make Oklo's co-location solution unlikely to scale before opposition and competition erode its window."
The article frames Oklo as a potential fix for data-center opposition via co-located SMRs, citing better nuclear polling and efficiency gains with Vertiv. Yet Oklo remains pre-revenue with its 75 MW Aurora prototype still two years from operation and zero disclosed co-location designs or customer contracts. Nuclear siting, NRC licensing, and waste rules impose multi-year delays that local zoning fights rarely match, while excess power sales to grids reintroduce the very utility-cost concerns driving 71% opposition. Execution risk dwarfs the speculative upside until first power is demonstrated.
Fast-tracked DOE-backed projects and bipartisan nuclear support could compress timelines enough for Oklo to lock in hyperscaler deals before traditional data-center builds resume.
"Oklo's thesis requires solving three unproven problems simultaneously (SMR commercialization, Vertiv integration, local acceptance) while the article treats the third as already solved by nuclear's polling advantage."
The article conflates two separate problems: local opposition to data centers (real, documented) and a speculative solution (Oklo SMRs). The 71% opposition figure is genuine, but the leap to 'nuclear solves this' ignores critical gaps. Oklo hasn't built a single commercial reactor. Its Aurora prototype is 75 MW—enough for one modest data center, not the gigawatt-scale buildout AI requires. The Vertiv partnership is announced but unproven. Most critically: rural communities opposing data centers may oppose nuclear plants equally. The article assumes zoning resistance is purely about grid strain, not land use, noise, or perceived risk. Until Oklo demonstrates one operational facility, this is venture-stage speculation dressed as infrastructure inevitability.
If Oklo executes and proves SMRs can be sited faster than grid-connected data centers, the addressable market is enormous—and early investors capture asymmetric upside before competitors enter.
"Oklo's thesis relies on a regulatory and technical timeline that is vastly more complex than the article suggests, making it a high-risk gamble rather than a viable infrastructure solution."
The narrative that Oklo (OKLO) solves the 'NIMBY' (Not In My Backyard) problem for data centers via SMRs is premature and fundamentally ignores the regulatory reality. While the partnership with Vertiv (VRT) is a logical synergy for cooling, the article glosses over the immense licensing hurdles of the Nuclear Regulatory Commission. Even if the tech works, the 'co-location' strategy doesn't bypass local zoning or public safety concerns; it likely intensifies them. Investors are pricing in a commercial breakthrough that is years away, ignoring that data center operators prioritize uptime and low-cost power, not experimental modular reactors with unproven supply chains. The $64 billion in stalled projects won't be saved by a prototype that hasn't cleared its first deployment.
If Oklo successfully achieves its first operational deployment, the regulatory 'first-mover' advantage could create a massive moat that renders traditional grid-dependent data centers obsolete.
"The core risk is regulatory and scalability: without a credible, financed proof-of-concept, Oklo's stock is a high-variance bet rather than a reliable path to transforming AI data-center infrastructure."
Oklo and Vertiv tout a co-located 75 MW SMR data-center concept aimed at reducing cost, water use, and siting friction. While appealing in theory, the piece glosses over critical hurdles: (1) regulatory risk and long NRC licensing timelines for SMRs; (2) scale economics—75 MW per site remains small for hyperscale AI workloads needing multi-hundred MW; (3) operational risks and public acceptance, including heat, water, waste, and decommissioning concerns. Until a proven, financed deployment proves cost, safety, and grid integration, the idea stays speculative and likely limited to a handful of pilot sites rather than a national wave.
Even if a pilot passes, licensing, insurance, and capital costs will drag timelines and returns; local opposition could re-emerge around nuclear contamination fears and water usage, undermining the 'easy path' narrative.
"Federal preemption may ease siting but fuel supply and waste logistics remain unaddressed execution risks for Oklo."
Gemini's focus on NRC licensing and local zoning overlooks federal preemption powers that can override community opposition for nuclear projects, unlike standard data-center builds. This creates a potential timeline advantage the article underplays. Yet the unmentioned risk is securing reliable fuel supply chains and waste disposal for scaled SMR deployments, which could create bottlenecks even after initial approvals, amplifying Oklo's execution challenges beyond pilots.
"Federal preemption doesn't eliminate state/judicial delays, and Oklo's unit size may be architecturally incompatible with hyperscaler redundancy mandates."
Grok's federal preemption argument is theoretically sound but historically overstated. Nuclear projects still face state-level challenges (California, New York) and judicial review that can delay years. More critically: nobody's addressed that hyperscalers themselves may reject Oklo's 75 MW units due to redundancy requirements—data centers typically demand N+1 or N+2 backup capacity. A single SMR failure isn't an option. That architectural mismatch could kill the thesis before NRC licensing even matters.
"High O&M costs for distributed SMRs will likely render them economically uncompetitive against grid-tied power, regardless of redundancy or zoning advantages."
Claude is right about the N+1 redundancy, but misses the capital efficiency angle. Hyperscalers don't need a single SMR to power a whole campus; they need them as distributed micro-grid baseload to avoid massive transmission upgrades. The real risk isn't just the NRC, but the 'stranding' of capital. If these reactors require dedicated security and specialized staff, the O&M costs per kilowatt-hour will likely dwarf natural gas or grid-tied renewables, making the business model DOA.
"Federal preemption alone won’t reliably accelerate Oklo’s path; fuel/waste logistics and SMR vendor lead times are the real, underappreciated bottlenecks."
While Grok argues preemption could accelerate approvals, I think that optimism ignores the practical gating factors that outlive zoning fights. Federal preemption can help, but state environmental reviews, tribal rights, and environmental impact statements still loom and can add years. More material: securing reliable SMR fuel supply and long-term waste management—and vendor lead times for modular reactors—could strangle scaling even after NRC licensing. The near-term path remains a multi-year, capital-intensive risk.
The panel is bearish on Oklo's co-located SMR data-center concept, citing regulatory hurdles, scale economics, operational risks, and potential architectural mismatches with hyperscalers' redundancy requirements.
Potential timeline advantage through federal preemption powers for nuclear projects.
Securing reliable fuel supply chains and waste disposal for scaled SMR deployments, as well as potential rejection by hyperscalers due to redundancy requirements.