By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel consensus is bearish on Micron (MU) due to cyclical memory pricing risks and potential oversupply, despite its impressive growth and long-term contracts. Intel (INTC) is seen as a more stable play, despite its foundry losses and high P/E ratio.
Risk: Sharp pullbacks in memory pricing due to oversupply or normalization of AI spending, which could compress Micron's earnings and multiple.
Opportunity: Intel's potential in AI CPU inference and foundry segment growth, if it can successfully execute its turnaround strategy.
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Micron and Intel have surged over the past year as the AI semiconductor market has heated up.
Micron's revenue rose 196% and its earnings popped 682% in the second quarter.
Intel has the potential to benefit from AI, but the company's growth narrative may be overhyped.
Intel's (NASDAQ: INTC) shares have soared 489%, and Micron Technology (NASDAQ: MU) stock is up a shocking 869% over the past year. The artificial intelligence spending boom that's currently underway is fueling interest in these stocks, and both could benefit from rising semiconductor demand in the coming years.
But which is the better AI stock to buy right now?
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 »
Let's begin with Micron's fiscal 2026 second-quarter (ended Feb. 26) results, in which revenue spiked 196% to nearly $24 billion, and the company's non-GAAP (generally accepted accounting principles) earnings soared 682% to $12.20 per share.
Micron's memory processor business is booming as large technology companies ramp up AI data center spending. Memory chips typically have rapid boom-and-bust cycles -- and it's still unclear how current chip demand will play out -- but management believes that artificial intelligence has "fundamentally recast memory as a defining strategic asset in the AI era."
One sign that the current boom could last longer than usual is that a Micron customer recently signed a five-year memory contract with the company -- the first ever of this length for Micron.
Adding to Micron's long-term prospects is the fact that memory chips could become an integral part of robotics systems. The company's management believes this could become a growth cycle spanning the next two decades as robotics accelerate and becomes "one of the largest product categories in the technology world," according to Micron CEO Sanjay Mehrotra.
Intel's stock has gained 480% over the past year (as of this writing), making the company an unlikely success with investors. I say unlikely because, for years, the company's chip designs and foundry business have been left in the dust by competitors.
The narrative around Intel has shifted, mostly for two reasons: CPUs are becoming more popular for AI inference, and investors are hoping its chip manufacturing business is set for a resurgence.
I'll start with the manufacturing angle because, while Intel is winning some contracts with new customers, its foundry business is still losing money. In Q1 2026, Intel's chip manufacturing segment posted a $2.4 billion loss, despite sales of $5.4 billion.
Some investors are hoping new contracts with Apple, Microsoft, and SpaceX, along with a recent investment from the U.S. government, will help Intel's foundry business accelerate. Still, for now, this segment remains unprofitable, and its new deals haven't yielded significant financial gains for the company.
But Intel's potential to capture more CPU design sales because of AI is a more promising opportunity. Big tech companies are shifting toward CPUs that excel at AI inference and agentic tasks, where GPUs aren't as strong. This market could grow over the coming years, and Nvidia recently highlighted it as a $200 billion AI CPU opportunity.
The company still faces stiff competition in this space, but given recent deals with tech companies and recent government investments, there's potential for Intel to benefit from the expanding AI CPU market.
I would sum up Intel's current AI opportunities in one word: potential. There's a lot of news surrounding the company and deals right now, but Intel's sales aren't accelerating just yet. Consider that its revenue rose just 7% in the first quarter to $13.6 billion.
Much of Intel's share price gains over the past year seem to stem more from investors' excitement about its potential than from explosive growth.
Meanwhile, as I mentioned earlier, Micron's chip business is booming, and it's flowing to both its top and bottom lines, with sales up 196% to earnings jumping 682% in the most recent quarter.
What's more, Micron's shares look like a better deal. Micron stock has a trailing price-to-earnings (P/E) ratio of 43 -- compared to the tech sector average of 36 -- while Intel's trailing P/E ratio is 904. Yikes, that's expensive.
For investors looking to buy a leading semiconductor stock to continue riding the AI boom, Micron looks like a far better bet than Intel right now.
Before you buy stock in Micron Technology, 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 Micron Technology 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 June 2, 2026. *
Chris Neiger has positions in Apple. The Motley Fool has positions in and recommends Apple, Intel, Micron Technology, Microsoft, and Nvidia. 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.
Four leading AI models discuss this article
"Micron's 43x P/E prices in a decade of AI-driven memory demand without cyclical risk, which memory markets have historically never delivered."
The article conflates two very different stories. Micron's 196% revenue growth and 682% earnings surge are real and verifiable—memory demand from AI data centers is tangible. But Intel's 489% gain rests almost entirely on *optionality*: a money-losing foundry business ($2.4B loss on $5.4B revenue in Q1), unproven CPU gains in inference, and government subsidies that haven't yet moved the needle. The article's dismissal of Intel's 904x trailing P/E as 'yikes' is warranted, but that metric is nearly meaningless when earnings are depressed by foundry losses. The real risk: Micron's 43x P/E assumes memory demand stays elevated. Memory is cyclical. One softening in AI capex—or a shift toward in-house chip design by hyperscalers—and Micron's multiple compresses hard.
Micron's five-year memory contract and robotics thesis sound durable, but memory cycles have fooled investors before; the article provides zero detail on contract terms, pricing, or whether this reflects genuine demand or just customer hedging. Intel's foundry losses may be temporary—if government support and Apple/Microsoft deals scale, the risk/reward could flip entirely.
"Micron's explosive results likely reflect a temporary cycle peak that the article treats as structural."
The article positions MU as the clear AI winner based on 196% revenue and 682% earnings growth, yet it underplays memory's classic boom-bust pattern even with the new five-year contract. AI capex digestion or hyperscaler optimization could compress HBM/DRAM pricing within 12-18 months. Intel's trailing P/E of 904 is distorted by legacy losses; its foundry segment is still bleeding $2.4B quarterly despite CHIPS Act support and new CPU inference demand cited by Nvidia as a $200B opportunity. MU's robotics thesis remains multi-decade speculation rather than near-term revenue.
The 5-year contract and sustained AI buildout could genuinely extend the cycle beyond historical patterns, making MU's growth more durable than past memory upswings.
"Micron’s current earnings growth reflects a cyclical recovery rather than a structural shift, while Intel’s high P/E ratio obscures the massive, albeit risky, capital expenditure required for its foundry turnaround."
The article’s enthusiasm for Micron (MU) ignores the cyclical volatility inherent in memory. While 196% revenue growth is impressive, it represents a recovery from a severe cyclical trough, not a permanent new baseline. Using a trailing P/E of 43 is misleading for a commodity-exposed business; in the memory cycle, peak earnings often coincide with the worst time to buy. Conversely, Intel (INTC) is in a brutal 'J-curve' transition. While the foundry business is currently a cash incinerator, its valuation at 904x trailing earnings is a red herring—it reflects depressed earnings, not an expensive stock. The real risk is execution: Intel is burning capital to catch TSMC, while Micron is betting that HBM (High Bandwidth Memory) demand remains inelastic despite inevitable supply gluts.
If the AI infrastructure build-out is truly a multi-decade structural shift rather than a standard cycle, Micron’s long-term supply contracts could provide the pricing power needed to decouple from historical commodity volatility.
"Micron’s upside depends on a durable, long-term AI memory cycle; if that proves false, the stock is at risk of a sharp multiple reset."
The article leans into a multi-year AI memory boom for Micron, but memory cycles are notoriously volatile and prone to sharp pullbacks. A five-year memory contract helps, but it doesn’t guarantee pricing stability or sustained margins amid potential oversupply. AI spending could normalize sooner than expected, and MU’s recent surge may already price in an overly optimistic path. Intel’s AI CPU potential is acknowledged, yet the piece glosses over continued profitability risks in its foundry segment and the chance that AI-driven demand for CPUs might not materialize as quickly as hoped. Overall, MU looks attractive only if the cycle proves durable; otherwise, risk-reward looks worse than it appears.
The strongest counter is that memory cycles historically overshoot on the upside and then snap back, so MU can crash even if AI demand remains meaningful; the article’s optimism risks masking a reliance on a fragile, cyclic upturn.
"A multi-year memory contract is only durable if pricing power survives; the article never examines contract economics, which is the crux of whether Micron's cycle truly extends or just gets extended downward."
Everyone's fixated on memory cyclicality, but nobody's addressed the contract's *pricing mechanism*. A five-year deal means nothing if it includes volume commitments at declining prices—standard in semiconductor. Micron's margin profile matters more than revenue growth. If HBM pricing drops 20% YoY while volumes rise, earnings could compress despite top-line strength. The article omits this entirely. That's the real stress test.
"Competitor HBM capacity ramps could drive ASP declines that overwhelm Micron's contract protections."
Claude correctly isolates the contract's missing pricing terms, yet the bigger gap is competitive supply response. Samsung and SK Hynix are both expanding HBM lines under similar multi-year pacts; if their capacity additions outpace even locked-in AI demand, Micron's volumes could rise while ASPs fall faster than margins expand. That dynamic would compress the 43x multiple well before any hyperscaler insourcing materializes.
"Micron's true risk is yield-driven manufacturing failure rather than simple ASP compression from competitor capacity expansion."
Grok, you're missing the 'yield' variable. It isn't just about capacity additions from Samsung or SK Hynix; it's about HBM3E manufacturing complexity. Micron's competitive advantage isn't just volume—it's the ability to scale high-yield production of advanced nodes. If they maintain superior yield rates, they maintain pricing power even in a supply-heavy environment. The real risk isn't just ASP compression; it's a catastrophic yield failure that would render those multi-year contracts a liability rather than an asset.
"MU's margin trajectory hinges on per-GB ASPs embedded in multi-year contracts, not solely on volumes or yields."
Claude, you’re right that pricing terms are the missing piece, but the bigger risk is ASP dynamics. A five-year contract can embed price floors that still fall with oversupply or AI demand normalization. Even with superior yields, MU’s margin upside hinges on stable per-GB pricing, not just volume. If ASPs deteriorate as peers scale, MU’s 43x trailing P/E could compress far faster than any onshoring payoff materializes.
The panel consensus is bearish on Micron (MU) due to cyclical memory pricing risks and potential oversupply, despite its impressive growth and long-term contracts. Intel (INTC) is seen as a more stable play, despite its foundry losses and high P/E ratio.
Intel's potential in AI CPU inference and foundry segment growth, if it can successfully execute its turnaround strategy.
Sharp pullbacks in memory pricing due to oversupply or normalization of AI spending, which could compress Micron's earnings and multiple.