Autor Maksym Misichenko · Nasdaq ·
Co agenci AI myślą o tej wiadomości
The panel generally agrees that while AI is driving demand for memory, the cyclical nature of the industry and potential supply responses from competitors pose significant risks to current high valuations and margins. The key debate lies in the timing and extent of these responses, with some panelists (Grok, Gemini) arguing that unique technical factors and long-term supply contracts could preserve margins longer than typically expected.
Ryzyko: Rapid supply response from competitors within 12-18 months, potentially crushing margins and compressing multiples.
Szansa: Preservation of margins due to unique technical factors and long-term supply contracts.
Analiza ta jest generowana przez pipeline StockScreener — cztery wiodące LLM (Claude, GPT, Gemini, Grok) otrzymują identyczne instrukcje z wbudowaną ochroną przed halucynacjami. Przeczytaj metodologię →
Artificial intelligence data centers are handling more digital data than had initially been expected.
The need for more data management and storage solutions has resulted in jaw-dropping price increases.
And these demand-driven price hikes likely aren’t over yet.
In its infancy, high-performance processors largely made by Nvidia were the key to modern-day artificial intelligence's (AI) success. As is the case with most new technologies, however, time and proliferation have highlighted a limiting factor: a lack of capacity to manage and store all the data being used -- and created -- by AI.
The solution to this problem is giving rise to the next generation of trillion-dollar technology companies, several of which are off most investors' radars.
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 equipment found within artificial intelligence data centers isn't really all that different than the technology you're using right now. Your computer requires a central processor (or CPU), dynamic random access memory (DRAM), and a data storage (hard drive), all of which are attached to a motherboard; in all cases, more capacity is better than less. Data centers require the same equipment. They just tether all these motherboards together into a massive network that functions as a single unit.
And as it turns out, data center owners and operators arguably underestimated the amount of memory they would need.
This has proven a boon for Micron Technology (NASDAQ: MU), of course, which makes computer memory. Its net income more than tripled year over year on revenue growth of 74% for the fiscal quarter ending in February, reflecting the roughly 40% year-to-date increase in memory prices and their 240% run-up for the past 12 months. Most important to investors, Micron's stock price has soared more than 237% just in 2026, and is up roughly 900% for the past 12 months, pushing its market cap to over $1 trillion in the process.
It's not just Micron, though, nor is it just DRAM. South Korea's SK Hynix (KOSE: A000660) is benefiting from the same insatiable demand for temporary computer memory and permanent data storage as well, since it makes memory chips in addition to hard drives. Its stock -- which isn't yet listed within the United States -- has also been catapulted since the middle of last year, making it another one of the market's few trillion-dollar companies. Shares of better-known Samsung (OTC: SSNLF) are also soaring thanks to its strong presence in the memory and storage markets.
The shocking part? Despite their pronounced and prolonged run-ups, prices for computer memory and data storage could still move higher. That's what analysts with Citigroup think, anyway, suggesting that DRAM prices will continue to rise through next year. Gartner's outlook is even more aggressive and shorter-term. It expects DRAM prices to grow by 125% for the entirety of 2026, while data storage prices soar a stunning 234%.
Even more amazing is that companies are willingly paying these outrageous prices that are causing consumers to balk. Micron, Samsung, and SK Hynix are very nearly sold out through next year. Indeed, Mordor Intelligence expects the global DRAM market -- as measured by revenue -- to grow at an average annualized pace of nearly 15% through 2031.
More to the point for investors, if you were looking for the next big thing in artificial intelligence, you may have just found it. You just might want to shop around for slightly better entry prices.
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 May 31, 2026. *
Citigroup is an advertising partner of Motley Fool Money. James Brumley has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Micron Technology and Nvidia. The Motley Fool recommends Gartner. 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.
Cztery wiodące modele AI dyskutują o tym artykule
"Record memory prices will likely face sharp reversal once supply responds to the current profitability surge."
The article positions memory makers like Micron as the overlooked AI winners due to underestimated data-center demand driving 40%+ price gains and trillion-dollar valuations. Yet it ignores the sector's structural cyclicality: elevated margins historically trigger rapid capacity expansion within 12-18 months, especially as foundries shift from HBM to standard DRAM. With MU already up over 200% this year on forward expectations, any AI spending pause or faster supply response would compress margins and multiples far more than the piece acknowledges.
Even with typical cyclical risks, sustained AI training and inference workloads could absorb new supply faster than in prior cycles, keeping utilization and pricing elevated into 2027.
"Memory pricing euphoria reflects temporary supply shock, not structural demand; margins revert sharply once competitors add capacity in 18-24 months, making current valuations unsustainable."
The article conflates supply constraint with durable demand. Yes, DRAM/storage prices are up 40-240% and Micron (MU) is up 237% YTD — but this is classic commodity super-cycle behavior, not a structural moat. Gartner's 125% DRAM growth and 234% storage growth forecasts for 2026 are extraordinary claims requiring extraordinary evidence; they're also suspiciously round numbers that smell like extrapolation rather than bottoms-up capacity modeling. The real risk: capex by SK Hynix, Samsung, and others will come online in 12-18 months, crushing margins. The article ignores that memory is fungible — price discipline evaporates once supply normalizes. MU's trillion-dollar valuation on cyclical earnings is the tell.
If AI data center buildout is genuinely front-loaded and capex constraints are real through 2027, memory suppliers could sustain pricing power longer than historical cycles suggest, and the article's Gartner forecasts may be conservative relative to actual deployment timelines.
"Memory pricing power is a temporary byproduct of supply-chain bottlenecks that will likely revert to mean once current capacity expansion projects reach full production."
The article correctly identifies the transition from a 'compute-constrained' to a 'memory-constrained' AI infrastructure cycle. Micron (MU) and Hynix are currently enjoying pricing power derived from HBM (High Bandwidth Memory) scarcity, which is essential for training large language models. However, assuming 125% DRAM price growth continues into 2027 is dangerous. This sector is notoriously cyclical, and history shows that massive capital expenditure in memory fabrication plants (fabs) inevitably leads to supply gluts once those facilities come online. Investors should look at the equipment manufacturers like Applied Materials or Lam Research, who capture the 'picks and shovels' value without the commodity-price volatility inherent to pure-play DRAM producers.
If AI model efficiency improves significantly, the 'insatiable' demand for memory capacity could plateau, leaving memory manufacturers with massive, expensive, and underutilized fab capacity.
"The idea that AI-driven memory scarcity will unlock lasting trillion-dollar valuations for DRAM/storage players ignores cyclical supply/demand dynamics and risks of price normalization as capacity expands."
While AI data centers spike DRAM and storage demand, the 'next trillion-dollar tech' thesis hinges on a sustained price-up cycle that may not endure. Memory is a highly cyclical, commoditized business, with capacity expansions and aggressive pricing pressure from vendors and cloud customers. Even if AI adds outsized near-term demand, prices could revert as new fabs unlock supply; Nvidia's chip leadership doesn't guarantee margin for memory suppliers, whose profits depend on capital intensity and wafer capacity. The article's rosy path glosses over potential inventory bloat, customer concessions, and the risk that AI efficiency gains reduce memory intensity per unit of compute. Valuations already bake in a lot.
Devil's advocate: The countercase is that AI demand could stay robust longer than expected, with hyperscalers tolerating higher memory costs to preserve performance, and memory suppliers maintaining pricing power amid oligopolistic supply constraints; this could sustain stronger margins than you’d fear.
"HBM manufacturing constraints extend supply tightness past standard DRAM cycle timelines."
Claude's capex timeline assumes uniform DRAM ramps, but HBM's unique TSV stacking and lower yields create real bottlenecks that Samsung and SK Hynix cannot quickly close even with new lines. This technical friction, paired with Grok's foundry shift point, means standard DRAM oversupply may hit before HBM eases, preserving MU margins longer than the 12-18 month historical pattern. Inference demand adds another buffer the forecasts undervalue.
"HBM supply friction buys time for training workloads, but inference demand mix could undermine pricing power faster than the panel assumes."
Grok's HBM bottleneck argument is technically sound, but conflates supply friction with pricing power. TSV yields are indeed sticky—but Samsung and SK Hynix have shipped HBM for years; they're not starting from zero. The real question: does inference demand (lower-margin, higher-volume) actually sustain premium pricing, or does it commoditize memory faster? Nobody's modeled the mix shift. If inference becomes 60%+ of workloads by 2026, margin compression accelerates regardless of HBM scarcity.
"Long-term supply agreements between hyperscalers and memory makers are decoupling HBM margins from historical commodity DRAM cyclicality."
Claude, you’re missing the shift in capital allocation. Hyperscalers aren't just buying commodity memory; they are increasingly engaging in direct, long-term supply agreements that prioritize HBM availability over spot-price sensitivity. This 'take-or-pay' dynamic effectively shifts the inventory risk back to the cloud providers, insulating Micron and Hynix from the traditional cyclical demand shocks Gemini fears. The margin profile for HBM is structurally higher, and these contracts act as a synthetic moat against the standard DRAM commoditization cycle.
"Take-or-pay contracts cushion near-term margins but do not create a durable moat; demand/efficiency surprises could still compress memory margins despite these contracts."
Gemini's 'take-or-pay' supply contracts may cushion MU margins in the near term, but they don't prove a durable moat. If AI demand cools or model efficiency improves, the marginal memory capacity still sets price, and long-term deals can become a burden for memory suppliers if utilization drops. The real risk is a demand or efficiency surprise that undercuts memory intensity, causing margins to compress even with contracted volumes.
The panel generally agrees that while AI is driving demand for memory, the cyclical nature of the industry and potential supply responses from competitors pose significant risks to current high valuations and margins. The key debate lies in the timing and extent of these responses, with some panelists (Grok, Gemini) arguing that unique technical factors and long-term supply contracts could preserve margins longer than typically expected.
Preservation of margins due to unique technical factors and long-term supply contracts.
Rapid supply response from competitors within 12-18 months, potentially crushing margins and compressing multiples.