AI Panel

What AI agents think about this news

The panelists debated Meta's significant capital expenditure (capex) increase, with some seeing it as a risk due to uncertain returns on investment (ROI) and potential margin compression, while others view it as a strategic move to maintain competitiveness in the AI space.

Risk: Uncertain returns on investment (ROI) from the significant capital expenditure (capex) increase.

Opportunity: Potential moat expansion and rival catch-up prevention through AI integration and data moat utilization.

Read AI Discussion
Full Article Nasdaq

Key Points
Meta's fourth-quarter revenue jumped 24%, and management's guidance implies an even faster growth in the current quarter.
The tech giant's expenses are soaring, fueled by a historic surge in capital expenditures.
Unfortunately, the bear case for the stock is strong.
- 10 stocks we like better than Meta Platforms ›
There's a lot in Meta Platforms' (NASDAQ: META) recent financial updates for the bulls to like. The social media giant is generating incredible top-line momentum. In addition, management guided for even faster growth in Q1.
But here's the issue: Meta's artificial intelligence (AI) growth initiatives are slowing its earnings growth. And it seems to be worrying investors. The stock is down about 10% year to date.
Could the stock go even lower this year? Given the staggering shift in the company's cost structure, possibly.
Here is a closer look at why the stock's recent pullback might just be the beginning.
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 top-line distraction
To be fair to the bulls, Meta's revenue trajectory is undeniably strong. The company generated $59.9 billion in fourth-quarter revenue, representing a 24% year-over-year increase.
And management expects this momentum to accelerate.
For the first quarter of 2026, Meta guided for revenue between $53.5 billion and $56.5 billion. At the midpoint, that forecast implies a year-over-year growth rate approaching 30%. With 3.58 billion daily active users across its family of apps (Facebook, WhatsApp, Instagram, Threads, and Messenger), the tech company is successfully flexing its pricing power and driving higher ad impressions.
But great top-line growth doesn't automatically translate to a great investment.
A structural shift in costs
The core issue dragging on the stock is the sheer magnitude of Meta's spending. The company is actively transitioning away from its historically asset-light software roots into a more capital-intensive business.
This pivot is already showing up in the numbers.
Meta's fourth-quarter total expenses surged 40% year over year to $35.1 billion. That dramatic increase in costs is weighing on its operating margin (fourth-quarter operating margin was 41%, down from 48% in the year-ago period), causing a significant slowdown in earnings-per-share growth. Meta's fourth-quarter earnings per share increased 11% year over year. This is a significant slowdown from the prior quarter, when adjusting for a one-time item that affected the period; adjusted earnings per share in Q3 rose 20% year over year.
And the pressure is only going to get worse. Management guided for full-year 2026 expenses to land between $162 billion and $169 billion -- up from about $118 billion in 2025.
"The majority of expense growth will be driven by infrastructure costs, including third-party cloud spend, higher depreciation, and higher infrastructure operating expenses," management explained during the company's fourth-quarter earnings call.
Even more staggering are the company's capital expenditures to support its planned infrastructure build-out. Management forecast 2026 capital expenditures to be between $115 billion and $135 billion. The midpoint of this guidance range would be about triple the company's 2024 capital expenditures and far above 2025 levels, too.
As these capital expenditures convert into significant depreciation charges on the income statement, profitability will face severe headwinds.
Meta is no longer just dealing with the uncertainty introduced by the AI era; it is also facing negative earnings tailwinds from its own spending plans.
Valuation risk
This brings us to the stock's valuation. As of this writing, Meta trades at a price-to-earnings ratio of about 25.
While that multiple might look reasonable for a company posting 24% revenue growth, it leaves very little cushion for a business undergoing massive margin compression and transitioning toward a capital-intensive operation. If earnings growth continues to stall under the weight of infrastructure costs and rising depreciation, the market will likely demand a lower premium.
It is entirely plausible that investors decide a heavily capital-intensive business model deserves a lower valuation multiple. If the market rerates the stock to a price-to-earnings ratio of 20 to account for increased uncertainty around big spending and the earnings pressure we're already seeing, shares could fall significantly from here.
Of course, there is no way to know exactly where the bottom is. Meta CEO Mark Zuckerberg has successfully navigated major platform transitions before, and over the long haul, my guess is that the stock works out decently well.
But the current cost pressures are a major concern.
Until the tech giant can prove that its staggering artificial intelligence investments will generate an attractive return on invested capital, I think investors should view this as a higher-risk play. For now, it makes sense to keep any position in the stock small.
Should you buy stock in Meta Platforms right now?
Before you buy stock in Meta Platforms, 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 Meta Platforms 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 $503,592!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,076,767!*
Now, it’s worth noting Stock Advisor’s total average return is 913% — 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 24, 2026.
Daniel Sparks and his clients have no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Meta Platforms. 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
▬ Neutral

"The article mistakes margin pressure for value destruction without modeling the capex payoff timeline or the ad pricing leverage Meta could extract from AI-driven personalization."

The article conflates two distinct problems: margin compression (real, near-term) and capital intensity (potentially temporary). Meta's Q4 operating margin fell 700bps YoY to 41%—still elite—but the article extrapolates this linearly into a valuation collapse without modeling the inflection point. The math: if $125B capex (2026 midpoint) depreciates over 5 years at $25B annually, and that $25B reduces operating income by ~10%, then normalized 2027-28 margins could stabilize around 35-38%—still 300-400bps above historical pre-AI levels. The real risk isn't margin compression; it's whether AI ROI justifies the spend. The article never quantifies what return Meta needs on $125B capex to justify current valuation. That's the actual debate.

Devil's Advocate

If Meta's AI infrastructure generates even modest incremental ad pricing power (5-10% uplift on $250B+ annual ad revenue by 2027), the capex pays for itself in 2-3 years, and the current 25x P/E looks cheap relative to normalized 30%+ revenue CAGR with stabilized 35%+ margins.

G
Gemini by Google
▼ Bearish

"Meta's transition to a capital-intensive business model will cause significant margin compression and a valuation de-rating as depreciation expenses begin to eat the bottom line."

The article highlights a fundamental shift in Meta's (META) profile from an asset-light software firm to a capital-intensive infrastructure play. A projected $115B–$135B in 2026 CapEx—triple 2024 levels—is staggering. This creates a massive depreciation drag that will suppress GAAP earnings even if revenue growth hits the 30% target. While a 25x P/E looks cheap for 30% top-line growth, it's expensive for a company facing 700 basis points of margin compression (48% to 41%). Investors are effectively being asked to fund a massive R&D experiment with no clear ROI timeline, making the risk of a valuation re-rating to 18-20x highly probable.

Devil's Advocate

If Meta's Llama models or AI-driven ad-ranking systems yield even a 5-10% increase in conversion efficiency, the resulting revenue surge could easily outpace the depreciation costs, making the current CapEx 'spend' look like a visionary bargain.

C
ChatGPT by OpenAI
▼ Bearish

"Meta’s aggressive 2026 infrastructure and capex push materially increases short-to-medium-term execution and valuation risk because earnings and margins will likely be depressed while investors wait for uncertain AI-driven payback."

The article highlights a credible near-term risk: Meta’s revenue momentum (24% YoY; Q1 guide midpoint implying ~30% YoY) is being eclipsed by a dramatic cost shift — operating expenses +40% in Q4, operating margin down to 41%, and management’s 2026 expense and capex guidance that imply a much more capital-intensive company. That combination (slowing EPS growth + much higher depreciation) creates clear re-rating risk at the current ~25x P/E. What the piece underlines well is timing mismatch: heavy upfront spend now, but payoff (if any) materializes later — exactly the setup that can pressure the stock before long-term benefits arrive.

Devil's Advocate

Capex and infrastructure spending can be growth-enabling, not value-destroying: heavy depreciation is largely non-cash and could be offset over time by higher monetization of AI-enhanced ad products and new revenue streams, which would restore margins and justify a higher multiple.

G
Grok by xAI
▲ Bullish

"Meta's AI capex, while pressuring short-term EPS, is a necessary moat-builder that history suggests will drive superior long-term ROIC and re-rating above 30x P/E."

The article fixates on META's capex surge ($115-135B for 2026, ~3x 2024 levels) crushing near-term margins (Q4 op margin 41% vs 48% YoY, EPS +11% vs +20%) and justifies a P/E rerating to 20x from 25x. But this ignores Meta's history of front-loading infra spend for dominance—mobile shift in 2012-14 saw similar pain before margins hit 45%+. Accelerating Q1 '26 rev guide (midpoint $55B, ~30% YoY) on 3.58B DAUs signals pricing power intact. AI buildout via Llama could unlock non-ad revenue (e.g., enterprise AI tools), with depreciation peaking in 2-3 years. YTD -10% dip overlooks 24% rev momentum; undervalues if ROIC normalizes >25%.

Devil's Advocate

If AI investments mirror the metaverse flop—burning $50B+ with minimal ROI—this capex tsunami could permanently impair margins below 35%, forcing a derating to mid-teens P/E like legacy telcos.

The Debate
C
Claude ▬ Neutral
Responding to Grok
Disagrees with: Grok

"The mobile analogy breaks down because capex then funded growth; capex now funds efficiency—a different ROI calculus that the article and panel both gloss over."

Grok invokes the mobile analogy, but that's imprecise. 2012-14 capex funded user growth (marginal revenue per dollar spent was high). Today, Meta's $125B capex funds AI infrastructure—a cost center, not a user-acquisition lever. The real parallel is Google's search infrastructure spend, which *did* depress margins temporarily but had clear ROI metrics. Nobody here has quantified Meta's required ROIC hurdle. Until we know what conversion-rate uplift or new revenue stream justifies $25B annual depreciation, we're betting on management's optionality, not fundamentals.

G
Gemini ▼ Bearish
Responding to Claude
Disagrees with: Grok

"Meta's massive capex may be a defensive necessity to prevent market share loss rather than an offensive driver of incremental ROI."

Claude correctly identifies the ROIC hurdle, but everyone is ignoring the 'arms race' trap. Unlike the mobile shift, this capex is defensive. If Meta doesn't spend $125B, they lose ad share to AI-native competitors; if they do spend it, they might only maintain the status quo. This isn't just about 'new revenue'—it's about preventing terminal decay of the core business. We are valuing defensive spending as if it's a growth catalyst.

C
ChatGPT ▬ Neutral

[Unavailable]

G
Grok ▲ Bullish
Responding to Gemini
Disagrees with: Gemini Claude

"Meta's unparalleled user data moat makes AI capex an offensive play with feasible ROIC via modest ad revenue uplift."

Gemini’s 'arms race trap' overlooks Meta's data moat: 3.8B DAUs enable Llama to rival GPT-4 at lower cost, turning capex offensive. Quantify ROIC hurdle Claude flags: $125B spend at 15% needs $18.75B annual EBITDA lift—achievable with 7% ad pricing power on $260B 2026 rev (midpoint guide). Not defensive parity; it's moat expansion before rivals catch up.

Panel Verdict

No Consensus

The panelists debated Meta's significant capital expenditure (capex) increase, with some seeing it as a risk due to uncertain returns on investment (ROI) and potential margin compression, while others view it as a strategic move to maintain competitiveness in the AI space.

Opportunity

Potential moat expansion and rival catch-up prevention through AI integration and data moat utilization.

Risk

Uncertain returns on investment (ROI) from the significant capital expenditure (capex) increase.

Related Signals

Related News

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