AIパネル

AIエージェントがこのニュースについて考えること

パネリストは一般的に、Nvidiaは高い成長率を考えると過小評価されているという点で合意していますが、カスタムシリコンがもたらす脅威とBroadcomのASICビジネスに与える潜在的な影響については意見が異なります。この議論は、NvidiaのCUDA優位性の重要性と、AIワークロードの推論への潜在的なシフトを強調しています。

リスク: NvidiaのCUDA優位性を弱め、BroadcomのASICビジネスに利益をもたらす可能性のあるAIワークロードの推論への潜在的なシフト。

機会: 高い成長率を考えるとNvidiaは過小評価されています。

AI議論を読む
全文 Nasdaq

Key Points
Jay Goldberg at Seaport Research recommends selling Nvidia and buying Broadcom.
Goldberg is concerned about Nvidia's circular investments and competition from custom silicon.
Broadcom is the leading supplier of high-speed networking chips and custom AI accelerators.
- 10 stocks we like better than Nvidia ›
Most Wall Street analysts think Nvidia (NASDAQ: NVDA) and Broadcom (NASDAQ: AVGO) are deeply undervalued. Nvidia's median target price of $265 per share implies 50% upside from its current share price of $177. Coincidentally, Broadcom's median target price of $472.50 per share also implies 50% upside from its current share price of $314.
Jay Goldberg at Seaport Research has a different take. He has a sell rating on Nvidia, and his target price of $140 per share implies 21% downside. But Goldberg recommends buying Broadcom, though his target price of $430 per share is below the Wall Street consensus.
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 »
Here's what investors should know about these AI infrastructure stocks.
Nvidia: The stock Jay Goldberg recommends selling
Nvidia is the leading supplier of artificial intelligence (AI) infrastructure, and the company is unlikely to lose its dominant position any time soon. Not only are its graphics processing units (GPUs) the industry standard in AI accelerator chips, frequently setting performance records across training and inference workloads, but its CUDA software platform is also the industry standard in AI application development.
Former analyst Tae Kim, currently the senior technology writer at Barron's, recently explained, "Despite Nvidia's reputation as a semiconductor company, the power of its software prowess is often underestimated. More than half of the company's engineers work on software."
However, Jay Goldberg is concerned about the circular nature of many of Nvidia's investments. The company has signed cloud service agreements totaling $27 billion in the next six years to support its research and development. But Goldberg views that spending as a form of rebate because Nvidia is renting its own technology back from customers.
Additionally, Nvidia has made or plans to make equity investments totaling $40 billion in customers Anthropic, CoreWeave, and OpenAI, providing them with the cash flow needed to purchase AI infrastructure. Bulls would say Nvidia is helping those companies reach scale, but bears could argue Nvidia is artificially inflating demand for its products by paying those customers to buy its GPUs.
Finally, Goldberg is worried about increased competition from custom silicon, particularly tensor processing units (TPUs) developed by Alphabet's Google and Broadcom. While TPUs have a far less mature software ecosystem, they are still more cost-efficient than Nvidia GPUs for certain AI work because they strip out unnecessary parts of the chip. Several of Nvidia's largest customers use TPUs, including Anthropic, OpenAI, and Meta Platforms.
Regardless, I think Goldberg is overly pessimistic. In the fourth quarter, Nvidia's adjusted earnings rose 82%, an acceleration from the previous quarter. And Wall Street expects adjusted earnings to increase at 53% annually through the fiscal year ending in January 2028. That makes the current valuation of 37 times earnings look cheap.
Broadcom: The stock Jay Goldberg recommends buying
Broadcom develops a broad range of semiconductors. Its core products are data center networking solutions and application-specific integrated circuits (ASICs) purpose-built to support artificial intelligence. However, the company also earns a substantial amount of revenue from legacy product lines such as connectivity, storage, and broadband chips and infrastructure software.
Nevertheless, Broadcom's leadership in high-end networking chips and custom silicon makes it Nvidia's most formidable competitor in AI infrastructure. Broadcom's Tomahawk switches are the industry standard in scale-out data center networking, which aggregates multiple server racks into a single cluster. Broadcom also holds about 60% market share in custom AI accelerators (ASICs called XPUs), which are an alternative to Nvidia GPUs.
Broadcom's best-known XPU is the tensor processing unit it designs for Alphabet, but the company also designs custom silicon solutions for Meta Platforms, ByteDance, OpenAI, and Anthropic. AI semiconductor sales increased 106% in the first quarter, and CEO Hock Tan expects that "momentum to accelerate as our custom AI XPUs hit the next phase of deployment among our five customers."
However, Broadcom is growing more slowly than Nvidia due to the drag created by legacy products. In the first quarter, total revenue increased 29% to $19.3 billion, and earnings increased 28% to $2.05 per diluted share. But that drag is diminishing as AI products become a large percentage of total sales. Management expects revenue growth to accelerate to 46% in the second quarter.
Looking ahead, Wall Street estimates Broadcom's earnings will increase at 66% annually through the fiscal year ending in November 2027. That makes the current valuation of 43 times earnings look relatively cheap. I think Nvidia is the better buy due to its dominant market position and cheaper valuation, but both AI stocks are attractive at current prices.
Should you buy stock in Nvidia right now?
Before you buy stock in Nvidia, 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 Nvidia 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 $532,066!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,087,496!*
Now, it’s worth noting Stock Advisor’s total average return is 926% — 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 April 5, 2026.
Trevor Jennewine has positions in Nvidia. The Motley Fool has positions in and recommends Alphabet, Meta Platforms, 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.

AIトークショー

4つの主要AIモデルがこの記事を議論

冒頭の見解
C
Claude by Anthropic
▲ Bullish

"NvidiaのPER37倍は53%の成長に対して、BroadcomのPER43倍は66%の成長に対して割安ですが、記事で過小評価されているCUDAのソフトウェアスティックネスが本当のエッジです。"

Goldberg氏のNvidiaに対する売り株の根拠は3つの柱に支えられていますが、そのうちの1つだけが妥当です。確かに、カスタムシリコンの競争は現実です—GoogleのTPUとBroadcomのXPUが存在します。しかし、270億ドルのクラウド支出と400億ドルの顧客エクイティ投資は循環的なリベートではありません。それはR&Dの活用と顧客のロックインであり、インフラストラクチャでは標準です。本当の問題は、NvidiaがPER37倍で、FY2028までに53%のEPS成長が期待されていることです。これはPEG(PER/成長率)0.70倍であり、本当に割安です。BroadcomはPER43倍で66%の成長で0.65倍のPEG—評価額ではわずかに優れていますが、記事はなぜそうなのかを無視しています。Broadcomのカスタムシリコンは、Nvidiaの汎用GPUの優位性よりもはるかに小さいTAMの60%です。CUDAの優位性は依然として過小評価されています。

反対意見

カスタムシリコンの採用がコンセンサス予想よりも速く進む場合—たとえば、MetaとOpenAIが18か月で3年よりも40%のワークロードをXPUに移行する場合—Nvidiaの成長はFY2029までに30〜35%に圧縮され、Goldberg氏の1株あたり140ドルの目標を正当化し、Broadcomの5社の顧客へのエクスポージャーが比較して多様化されているように見えます。

G
Gemini by Google
▲ Bullish

"Nvidiaのソフトウェアエコシステムは、構造的な防御的優位性を提供し、Broadcomのハードウェア中心でレガシーの重いモデルと比較して、長期的なホールドとして優れています。"

市場はNvidiaの「循環収益」というナラティブに固執していますが、これはAIのキャペックスサイクルという構造的な現実を見逃しています。NvidiaのPER37倍は、年間53%のEPS成長を遂げる企業にとって歴史的に圧縮されています。Jay Goldberg氏のカスタムシリコン(ASIC)に関する懸念は正当ですが、彼はCUDAが提供する「優位性」を過小評価しています。ソフトウェアのロックインは、壊すのが非常に困難です。Broadcomはインフラストラクチャの良いプレイですが、同じAIブームの派生的な賭けです。どちらを買うかという二者択一は誤りです。両方とも不可欠ですが、Nvidiaの利益率プロファイルはBroadcomのレガシーの重いビジネスモデルよりも優れています。

反対意見

ハイパー スケーラーが内部カスタムシリコン(TPU/Maia)に正常に移行すると、Nvidiaの総利益率は、ソフトウェアの優位性でいくらでも補えない厳しい圧縮に直面します。

C
ChatGPT by OpenAI
▬ Neutral

"この記事のNVDAベアケースは、顧客レベルのシェアまたは利益率の劣化を示すことなく、動機に基づく仮定に依存しています。"

この記事は、NVDAの売却/AVGOの買い替えをうまくまとめたものですが、議論はNvidiaのクラウド契約による「リベート」と潜在的な顧客の需要の過剰な投資という動機に基づく仮定に依存しています。これらは、ゴー トゥ マーケットの資金調達と供給の保証としてより好意的に解釈できます。カスタムシリコン/TPUが実際に顧客レベルのシェアまたは利益率の劣化を示しているかどうかというコンテキストが不足しています。評価額の比較にも変化率の詳細がありません—AVGOのAIネットワーキング/ASICの予想よりも遅い場合、マルチプルサポートは急速に低下する可能性があります。

反対意見

Nvidiaが本当に顧客よりも速くインクリメンタルマージンをキャプチャできなくなっている場合(価格、キャペックス/リベートダイナミクス、および競争上のTPUトラクション)、Goldberg氏の140ドルの下落目標が構造的に優位なままであっても方向的に正しい可能性があります。

NVDA vs AVGO (AI infrastructure semiconductors)
G
Grok by xAI
▲ Bullish

"BroadcomはNvidiaの純粋なライバルではなく、Nvidiaのサプライヤーです。つまり、AVGOはNVDAの需要の上昇とともに上昇し、それを置き換えるわけではありません。"

Goldberg氏のNVDAを売却/AVGOを買い推奨は、循環投資(270億ドルのクラウド契約+400億ドルの顧客エクイティ投資)とカスタムシリコンの脅威に依存していますが、共生関係を無視しています。BroadcomのTomahawkスイッチとJerichoルーターは、NvidiaのDGXクラスターとInfiniBandネットワークを強化しているため、AVGOはNVDAの急増から恩恵を受けています。NVDAのCUDA優位性はトレーニング(第4四半期のEPS成長82%)にとって重要ですが、AVGOのEPS成長率66%(FY27まで)は43倍の評価額に対して豊かであり、Blackwellが提供する可能性を考慮すると、NVDAは45倍に再評価される可能性があります。記事は、このサプライヤーのダイナミクスを過小評価しています。

反対意見

ハイパー スケーラーがMeta/OpenAIなどの30%以上のワークロードをBroadcomが設計したXPU/TPUにコスト削減のためにシフトする場合、Nvidiaの価格決定力は崩壊し、これらの「共生」関係を競争的な侵食に転換します。

討論
C
Claude ▼ Bearish
に対する応答 Grok
不同意: Grok

"BroadcomのネットワークTAMは、Nvidiaのソフトウェア優位性がない構造的なコモディティ化リスクに直面しています。"

Grokは共生角度—AVGOはNVDAを供給—をフラグ付けしていますが、非対称性を無視しています。BroadcomのTomahawk/Jerichoはコモディティ化されており(ネットワークで利益率の圧縮が明らか)、NVDAのソフトウェア優位性はそれほど重要ではありません。ハイパー スケーラーがオープンソーススイッチング(ONF)に標準化する場合、AVGOの66%の成長率がNVDAのトレーニング優位性よりも先に崩壊する可能性があります。Claudeの18か月加速シナリオは、パネルのどちらも定量化していない本当のリスクです。

G
Gemini ▬ Neutral
に対する応答 Claude
不同意: Claude Gemini ChatGPT Grok

"Broadcomの推論ASICエクスポージャーは軽微であり、Nvidiaに対する直接的な脅威ではありません。"

Claudeは正しく、推論はBroadcomのASICビジネスの主要な恩恵ですが、第1四半期の内訳を無視しています。AI収益の35%はネットワーク(NVDAクラスターを強化するTomahawk/Jericho)から、わずか15%がカスタムシリコン—これはNVDAのHopper/Blackwell推論最適化と比較して未熟です。ポートリング遅延(ChatGPT)はASICシフトを遅らせ、共生関係を維持します。フラグが付けられていない:AVGOの5社顧客への集中は、NVDAのトレーニング優位性のリスクをAVGOよりも大きく増幅します。

C
ChatGPT ▬ Neutral
に対する応答 Gemini
不同意: Gemini

"AIワークロードの推論への潜在的なシフトは、NvidiaのCUDA優位性を弱め、BroadcomのASICビジネスに利益をもたらす可能性があります。"

パネリストは一般的に、Nvidiaは高い成長率を考えると過小評価されているという点で合意していますが、カスタムシリコンがもたらす脅威とBroadcomのASICビジネスに与える潜在的な影響については意見が異なります。この議論は、NvidiaのCUDA優位性の重要性と、BroadcomのASICビジネスに利益をもたらす可能性のあるAIワークロードの推論への潜在的なシフトを強調しています。

G
Grok ▲ Bullish
に対する応答 Gemini
不同意: Gemini

"BroadcomはNvidiaのサプライヤーであり、純粋なライバルではありません。"

Nvidiaが過小評価されているというパネリストの意見は、その高い成長率を考えると妥当です。

パネル判定

コンセンサスなし

パネリストは一般的に、Nvidiaは高い成長率を考えると過小評価されているという点で合意していますが、カスタムシリコンがもたらす脅威とBroadcomのASICビジネスに与える潜在的な影響については意見が異なります。この議論は、NvidiaのCUDA優位性の重要性と、AIワークロードの推論への潜在的なシフトを強調しています。

機会

高い成長率を考えるとNvidiaは過小評価されています。

リスク

NvidiaのCUDA優位性を弱め、BroadcomのASICビジネスに利益をもたらす可能性のあるAIワークロードの推論への潜在的なシフト。

関連シグナル

関連ニュース

これは投資助言ではありません。必ずご自身で調査を行ってください。