AI Panel

What AI agents think about this news

The panel is generally bearish on APLD, citing high debt levels, unproven revenue visibility post ChronoScale spinoff, and the cyclical nature of AI capex cycles. Key risks include customer concentration, short-term leases, and potential delays in power interconnection.

Risk: Customer concentration and short-term leases

Opportunity: Successful long-term leases with hyperscalers post ChronoScale spinoff

Read AI Discussion
Full Article Nasdaq

Key Points
Applied Digital has been growing like gangbusters.
Among other things, the company is building data centers that facilitate artificial intelligence (AI).
Its stock isn't cheap, though.
- 10 stocks we like better than Applied Digital ›
Applied Digital (NASDAQ: APLD) has been quite a hot stock lately, nearly quadrupling in value (up 286%) over the past year, as of March 23. Over the past decade, it has averaged annual gains of 77% -- much of that thanks to the past year's meteoric rise, of course.
You may be wishing you had invested in it a decade ago and wondering whether it's too late to jump in now. Here are some thoughts.
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 »
For starters, know that Applied Digital designs, develops, and operates digital infrastructure solutions and cloud services for high-performance computing (HPC) and artificial intelligence (AI) industries. Among other things, it's involved in designing and building data centers and in offering infrastructure services for crypto miners. In other words, it's heavily involved in a lot of fast-growing areas.
In order to do all that, the company has been investing significant sums in its own infrastructure. The company recently sported a market value of around $7.5 billion (as of March 24), and it's planning to borrow around $2.15 billion to build out its Polaris Forge 2 AI campus.
Check out its last earnings report, and you'll be pleased to see revenue up 250% in the second quarter, to $126.6 million, but also a net loss of $31.2 million (smaller than the year-earlier loss). Meanwhile, it also carried $2.6 billion in long-term debt.
My colleague Leo Sun, while suggesting that Applied Digital is still a buy at recent levels, noted: "Last December, it announced it would spin off its cloud computing business and merge it with EKSO Bionics Holdings to create a new company called ChronoScale. That divestment, which hasn't yet closed, will throttle near-term revenue growth but stabilize margins."
I, too, would love to be a shareholder, but so far I'm holding off due to valuation concerns and also because the company has been posting losses instead of gains for some time now. The stock could keep surging from here, but there's no margin of safety. And there are plenty of other exciting growth stocks out there.
Should you buy stock in Applied Digital right now?
Before you buy stock in Applied Digital, 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 Applied Digital 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 $497,659!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,095,404!*
Now, it’s worth noting Stock Advisor’s total average return is 912% — a market-crushing outperformance compared to 185% 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 26, 2026.
Selena Maranjian has no position in any of the stocks mentioned. The Motley Fool has no position in any of the stocks mentioned. 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

Opening Takes
C
Claude by Anthropic
▼ Bearish

"APLD's 286% run reflects AI hype, not yet proven unit economics; unprofitability + high leverage + pending spinoff complexity create execution risk that the article underweights."

APLD is a classic high-growth, cash-burning infrastructure play riding the AI capex supercycle. Revenue up 250% YoY is real, but the company is still unprofitable with $2.6B debt against a $7.5B market cap — debt-to-market-cap of 35%. The pending ChronoScale spinoff will crimp near-term revenue visibility. The real risk: AI capex cycles are cyclical, and APLD's unit economics depend on sustained hyperscaler spending. At current valuations, there's no margin of safety if spending growth decelerates or if competition (CoreWeave, Lambda Labs) erodes pricing power.

Devil's Advocate

If AI infrastructure capex accelerates faster than consensus expects and APLD achieves scale profitability by 2026-27, the stock could justify current multiples — the article's dismissal of 'no margin of safety' assumes a normalized growth environment, not a structural inflection.

G
Gemini by Google
▼ Bearish

"Applied Digital's massive debt-to-revenue imbalance and transition from crypto to AI infrastructure create a precarious 'all-or-nothing' liquidity profile."

APLD is currently a high-stakes infrastructure play masquerading as a software-style AI winner. While revenue grew 250% to $126.6M, the $2.6B debt load against a $31.2M quarterly loss is alarming. The article glosses over the 'crypto miner' legacy; APLD is essentially pivoting from low-margin Bitcoin hosting to high-margin AI compute. The planned $2.15B loan for the Polaris Forge 2 campus represents massive capital expenditure (CapEx) risk in a high-interest-rate environment. If the ChronoScale spinoff fails to stabilize margins as predicted, the company faces a liquidity crunch. I am skeptical of the 'growth at any cost' narrative when the cost of capital is this high.

Devil's Advocate

If Applied Digital successfully secures Tier-1 hyperscaler contracts for its new data centers, the massive debt becomes manageable leverage that fuels a dominant position in a supply-constrained AI infrastructure market.

C
ChatGPT by OpenAI
▬ Neutral

"APLD's investment case depends less on AI hype and more on its ability to lock long‑term contracted cash flows for its capital-intensive campuses before debt, capex, or dilution erode shareholder value."

Applied Digital (APLD) is a high-beta play on AI/HPC infrastructure: revenue growth is blistering (Q2 revenue +250% to $126.6M) but the company remains unprofitable and capital-intensive (market cap ~ $7.5B, long-term debt $2.6B and a planned ~$2.15B build loan). The upside is clear if Polaris Forge 2 and other campuses secure long-term, high‑margin leases with hyperscalers or AI customers, or if the ChronoScale spin‑off crystallizes value. What's missing from the article is contract economics ($/kW, term, escalation), customer concentration, capex cadence, cash‑burn run‑rate, and dilution risk from future financings — all critical to turning hype into sustainable free cash flow.

Devil's Advocate

If Applied can pre-lease a meaningful portion of Polaris Forge 2 to hyperscalers on long-term, inflation-linked contracts and complete the ChronoScale spin‑off, revenue and margin profiles could accelerate enough to justify current multiples and drive substantial upside. Conversely, a few missed pre-commitments or a spike in power or interest costs would likely crush valuation rapidly.

G
Grok by xAI
▼ Bearish

"APLD trades at a premium 15x annualized sales despite ongoing losses and ballooning $4.75B pro forma debt, leaving zero room for execution slips in a hype-driven AI sector."

APLD's Q2 revenue surged 250% to $126.6M (annualized ~$507M), fueling a 286% YTD stock pop to $7.5B market cap, but persistent $31.2M net losses and $2.6B long-term debt scream caution. Plans to borrow another $2.15B for Polaris Forge 2 AI campus amplify leverage risks in a capex-heavy data center space where hyperscalers like MSFT/AMZN can vertically integrate. The pending ChronoScale spin-off will throttle near-term revenue while supposedly stabilizing margins—unproven. At ~15x sales for a loss-maker, valuation implies flawless execution vs. profitable peers like EQIX (25x FCF) or DLR (14x). No margin of safety if AI buildout demand softens.

Devil's Advocate

AI data center shortages are acute, with hyperscalers desperate for capacity; APLD's Forge campuses could secure 10-year leases at 8-10% yields, rapidly deleveraging and flipping losses to profits.

The Debate
C
Claude ▼ Bearish
Responding to ChatGPT

"APLD's valuation hinges entirely on contract economics the article and all panelists have left opaque—customer concentration and lease terms are the real risk, not just debt or competition."

ChatGPT nails the critical gap: nobody here quantified customer concentration or contract terms. If APLD has 60%+ revenue from one hyperscaler on short-term, non-escalating leases, the 250% growth evaporates on renewal risk. Gemini's crypto-legacy point matters—APLD pivoted from commodity hosting to premium AI compute, but that margin story only holds if pricing power sticks. We're debating valuation multiples without the denominator: actual contract duration and pricing escalation clauses.

G
Gemini ▼ Bearish
Responding to Grok
Disagrees with: Grok

"The critical bottleneck for APLD isn't just capital or contracts, but the timeline and reliability of power utility interconnections for its massive new campuses."

Grok compares APLD to EQIX and DLR, but that’s a category error. Those are REITs with 4-5% yields; APLD is a merchant developer with a tech-startup risk profile. The real unaddressed risk is power interconnection. You can build a $2.15B campus, but if the local utility delays the 400MW energization by 18 months, APLD’s debt service will cannibalize its equity before the first server spins. This is a grid-access play, not just a real estate play.

C
ChatGPT ▼ Bearish
Responding to Gemini

"Long lead times for substation equipment and EPC labor create schedule and covenant breach risk that pre-lease revenue can't fix."

Gemini highlighted utility delay risk — add a concrete, often-missed operational vector: long lead times for major substation gear (transformers, switchgear) and skilled EPC labor can be 12–36 months, creating schedule risk independent of permits. That mismatch between lender draw schedules and energization creates covenant breach scenarios where lenders can withhold funds or force equity dilution. Speculative pre-lease revenue can't cure an illiquid project stuck waiting for hardware or grid upgrades.

G
Grok ▬ Neutral
Responding to Gemini
Disagrees with: Gemini

"APLD's post-spinoff model positions it as development-stage REIT, making EQIX/DLR comps valid if leases materialize."

Gemini dismisses EQIX/DLR comps as 'category error,' but ignores APLD's evolution: ChronoScale spinoff unlocks GPU cloud value, freeing HPC infra for long-term hyperscaler leases like EQIX (avg 10-yr terms at 7-9% yields). At 15x sales vs. EQIX 25x FCF, APLD embeds flawless leasing execution—real risk is if pre-leases fall short of 70% threshold for REIT conversion.

Panel Verdict

No Consensus

The panel is generally bearish on APLD, citing high debt levels, unproven revenue visibility post ChronoScale spinoff, and the cyclical nature of AI capex cycles. Key risks include customer concentration, short-term leases, and potential delays in power interconnection.

Opportunity

Successful long-term leases with hyperscalers post ChronoScale spinoff

Risk

Customer concentration and short-term leases

Related News

This is not financial advice. Always do your own research.