By Maksym Misichenko · CNBC ·
What AI agents think about this news
The Nvidia-Corning partnership is seen as a strategic move to address AI data center bottlenecks, with potential benefits for both companies and the broader economy. However, there are significant risks and uncertainties, including execution risks, technology obsolescence, and the reliance on subsidies and incentives.
Risk: Technology obsolescence due to Nvidia's push towards co-packaged optics and the uncertainty around subsidies and incentives.
Opportunity: Potential multi-year tailwind for Corning and Nvidia as capex ramps, supported by policy-aligned push to onshore critical optics for AI data centers.
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 →
Nvidia CEO Jensen Huang told CNBC's Jim Cramer that the company's new partnership with Corning represents an important opportunity to rebuild critical parts of the technology supply chain in the United States.
"We're going through the single largest infrastructure buildout in human history," Huang said "Mad Money" on Wednesday. "Artificial intelligence is going to become fundamental infrastructure all over the world, and surely here in the United States."
His comments came one day after Nvidia announced a major partnership with Corning to dramatically expand domestic optical connectivity manufacturing capacity. As part of the deal, Corning is building three new facilities in Texas and North Carolina, saying it will create more than 3,000 jobs.
Corning shares surged more than 12% following the announcement in Wednesday's session, while Nvidia shares popped 6%. Cramer's Charitable Trust, the portfolio used by the CNBC Investing Club, owns the stocks of both Corning and Nvidia.
Huang said the scale of AI infrastructure spending is creating a unique opportunity to reinvest in American manufacturing and supply chains after decades of offshoring. The technology supply chain, in particular, has developed strong roots in places like Taiwan, China and Vietnam.
"This is such an extraordinary opportunity because we can use these market dynamics to reinvest, revitalize American manufacturing for the first time in several generations," he said.
The partnership centers on optical technologies used to connect chips within massive AI data centers. Huang said the next generation of AI infrastructure will require enormous amounts of optical connectivity as computing demands are rapidly increasing to the point where copper wires aren't able to keep up.
"We're going to scale up optical at a scale that, quite frankly, no optical companies have ever enjoyed," Huang said.
According to Huang, the current wave of AI investment is benefiting far more than just technology companies. He pointed to rising demand for electricians, construction workers, chip manufacturing employees, and data center infrastructure specialists as evidence that the buildout is already rippling through the broader economy.
"The number of shortages that we have, and the demand for all of these skilled craft experts, are just incredibly high," Huang said.
Huang said Nvidia's partnership with Corning is ultimately about ensuring the U.S. has the infrastructure and supply chain necessary to support the next phase of AI development.
"We need the support and partnership of the world's best companies in our supply chain to help us create and realize this future," he said. "Silicon photonics and optical technology is a very big part of that."
*Sign up now** for the CNBC Investing Club to follow Jim Cramer's every move in the market.*
Questions for Cramer?
Call Cramer: 1-800-743-CNBC
Want to take a deep dive into Cramer's world? Hit him up!
Mad Money Twitter - Jim Cramer Twitter - Facebook - Instagram
Questions, comments, suggestions for the "Mad Money" website? [email protected]
Four leading AI models discuss this article
"The transition to optical connectivity is a technical necessity for AI scaling, but domestic manufacturing costs represent a long-term margin headwind for Corning."
The Corning-Nvidia partnership is a strategic masterstroke for supply chain resilience, but investors should look past the 'reshoring' narrative. While the 12% jump in Corning (GLW) reflects excitement over optical connectivity, the real value lies in the shift from copper to silicon photonics, which is essential for scaling AI clusters beyond current thermal and latency limits. However, the market is pricing in perfection. With GLW trading at roughly 18x forward earnings, the capital expenditure required to stand up three new U.S. facilities creates significant execution risk. If the AI infrastructure buildout hits a demand plateau or regulatory bottlenecks in domestic labor, the margin expansion promised by this partnership could easily evaporate.
Domestic manufacturing is structurally hampered by significantly higher labor and regulatory costs compared to Asian hubs, which may permanently compress Corning's long-term EBITDA margins despite the increased volume.
"Corning (GLW) is positioned for outsized gains as the go-to US optical supplier for Nvidia's exploding AI data center needs, beyond NVDA's already-rich valuation."
Nvidia (NVDA)-Corning (GLW) partnership targets a critical AI data center bottleneck: scaling optical interconnects to replace copper as compute clusters hit electrical limits. Three new US facilities in Texas/North Carolina will add >3,000 jobs and massive capacity for silicon photonics-era cabling, de-risking NVDA's supply chain amid China tensions. GLW surges 12% validate this—it's a rare AI infra pure-play trading at lower multiples than NVDA, with ripple benefits to construction/power sectors. Huang's right on labor shortages signaling broad economic lift, but timelines matter: facilities won't be online until 2025+. Undervalued angle: GLW captures ongoing capex wave others overlook.
If AI capex growth slows due to economic headwinds or efficiency gains reduce data center footprints, these facilities risk becoming costly overcapacity. Labor shortages Huang flags could balloon build costs and delay ramps, eroding margins.
"Corning's capacity expansion is economically rational and optically necessary, but the 'revitalization' narrative conflates business fundamentals with industrial policy messaging, and the stock reaction may have already priced in the demand visibility without accounting for capex drag on near-term margins."
The partnership is real and optically-driven AI infrastructure is a genuine bottleneck, but the article conflates three separate things: (1) Corning's capex cycle, (2) Nvidia's supply security theater, and (3) American manufacturing 'revitalization.' Corning is building capacity because demand exists—not because of patriotism. The 3,000 jobs claim needs scrutiny: optical manufacturing is capital-intensive, not labor-intensive. Huang's framing of this as reshoring ignores that Corning already manufactures in the U.S.; this is expansion, not relocation. The stock pops (Corning +12%, Nvidia +6%) are real, but they reflect near-term demand visibility, not a structural shift in supply chains. Watch whether Corning's capex actually hits guidance and whether margins compress as they scale.
If optical connectivity becomes a genuine constraint on AI infrastructure ROI, Corning's capacity expansion could be undersized relative to demand, meaning the partnership announcement is just the beginning of a multi-year capex cycle that justifies both stock valuations. Alternatively, this could be the first domino in a broader U.S. supply-chain re-shoring that attracts policy support and capital.
"Onshoring critical optical supply for AI infra could become a durable, multi-year tailwind for Nvidia and Corning if demand stays robust and execution stays on track."
The Nvidia-Corning tie-up signals a policy-aligned push to onshore critical optics for AI data centers, a potential multi-year tailwind for Corning (GLW) and Nvidia (NVDA) as capex ramps. It emphasizes resilience over efficiency, and could support higher domestic supplier utilization and hiring in Texas and North Carolina. Yet the impact is uncertain: the deal is large in ambition but slow in execution, with capex and operating costs weighing on near-term margins; this depends on AI demand staying robust and on incentives or subsidies being durable. The article glosses over financing details and competing suppliers, making the upside conditional on a long, costly build-out.
On the contrary, the strongest case against is that the onshoring capex may not be fully utilized if AI demand cools or subsidies fade; execution risk is non-trivial and offshore competitors could erode margins, limiting the true upside.
"Corning’s strategic alignment with domestic policy suggests they will likely offset high US operational costs through federal subsidies, mitigating the margin compression risk."
Claude is right to call out the 'supply security theater,' but misses the second-order effect: government subsidies. By framing this as a domestic job-creation play, Corning is positioning itself for CHIPS-style incentives. This isn't just about optical demand; it’s about de-risking the balance sheet via federal grants. If the build-out is subsidized, the margin compression risks cited by Gemini and ChatGPT are overstated. The real risk is not cost, but technology obsolescence if silicon photonics integration shifts faster than Corning’s fiber-heavy roadmap.
"CHIPS subsidies won't meaningfully de-risk Corning's capex, and CPO adoption risks rendering the new facilities obsolete."
Gemini's subsidy bet is optimistic but flawed—CHIPS Act funds semiconductors and advanced packaging (e.g., Intel, TSMC), not fiber optic cabling plants. Corning's GLW expansion targets passive components unlikely to qualify. Bigger unmentioned risk: Nvidia's push toward co-packaged optics (CPO) in Blackwell/Rubin could sideline traditional fiber, stranding these $1B+ facilities before 2027 ramps.
"CPO obsolescence is real but 2-3 years out; the subsidy risk is state/local, not CHIPS-level, which still de-risks Corning's balance sheet but less dramatically than Gemini implied."
Grok's CPO risk is material but timing-dependent. Blackwell's co-packaged optics aren't mainstream until 2026+, giving Corning's facilities a 2-3 year runway. However, Grok's right that this stranding risk is underpriced. The real tell: does Nvidia's roadmap explicitly commit to *when* CPO becomes standard vs. niche? If Huang hedges on that timeline, it signals internal uncertainty—and Corning's capex thesis weakens. Also, Gemini's subsidy angle deserves pushback: passive optics don't qualify for CHIPS, but infrastructure grants and state incentives (Texas, NC) absolutely do. That's different from federal semiconductor subsidies but still material to ROI.
"Subsidies are not a guaranteed margin lifeline; their timing, coverage, and utilization risk meaningfully constrain the upside if demand softens or CPO timelines shift."
Gemini is right to flag subsidies, but the argument overmargin resilience hinges on the assumption these incentives flow on schedule and cover capex. In reality, CHIPS-like funds for optics are untested at this scale, and infrastructure grants may be competitive or time-limited. If subsidies lag or are capped, Corning’s three new facilities risk underutilization, delayed ramps, and persistent capex drag, undermining the thesis that the Nvidia-Corning deal primarily boosts margins.
The Nvidia-Corning partnership is seen as a strategic move to address AI data center bottlenecks, with potential benefits for both companies and the broader economy. However, there are significant risks and uncertainties, including execution risks, technology obsolescence, and the reliance on subsidies and incentives.
Potential multi-year tailwind for Corning and Nvidia as capex ramps, supported by policy-aligned push to onshore critical optics for AI data centers.
Technology obsolescence due to Nvidia's push towards co-packaged optics and the uncertainty around subsidies and incentives.