AI-Panel

Was KI-Agenten über diese Nachricht denken

The panelists agreed that AI infrastructure picks like Nvidia, Broadcom, and TSMC have strong fundamentals, but there's disagreement on the sustainability of AI capex and the risks associated with small-cap speculative names like SoundHound AI and Nebius.

Risiko: Geopolitical/taiwan risk, margin dilution, and potential slowdown in AI capex due to energy constraints or ROI erosion.

Chance: Custom ASIC design wins creating multi-year switching costs for Broadcom, and hyperscalers' ability to self-build power infrastructure.

AI-Diskussion lesen
Vollständiger Artikel Nasdaq

Wichtige Punkte

Chiphersteller Nvidia und Broadcom verzeichnen weiterhin enorme Wachstumszahlen.

Taiwan Semiconductor profitiert vom massiven Ausbau der KI-Infrastruktur.

SoundHound AI und Nebius sind zwei kleinere Unternehmen mit enormem Aufwärtspotenzial.

  • 10 Aktien, die wir besser mögen als Nvidia ›

Investitionen in künstliche Intelligenz (KI) waren zu Beginn von 2026 etwas schwach am Markt. Das sollte für Anleger keine große Überraschung sein, da sich Sektoren im Laufe der Jahre zyklisch ändern. Das bedeutet jedoch nicht, dass Anleger den KI-Sektor abschreiben sollten. Tatsächlich gibt es frühe Anzeichen dafür, dass er wieder in Mode kommt.

Solide Ergebnisse im ersten Quartal mit positiven Zukunftsaussichten könnten genau das sein, was dieser Sektor benötigt, um wieder in die Höhe zu schnellen, und wenn dies geschieht, glaube ich, dass diese fünf Aktien davon am meisten profitieren werden.

Wird KI den ersten Trillionär der Welt schaffen? Unser Team hat gerade einen Bericht über ein wenig bekanntes Unternehmen veröffentlicht, das als "unverzichtbares Monopol" bezeichnet wird und die kritische Technologie liefert, die sowohl Nvidia als auch Intel benötigen. Weiter »

1. Nvidia

Nvidia (NASDAQ: NVDA) ist seit einiger Zeit die Top-Investition in den Bereich KI, hat aber in den letzten Monaten keine nennenswerten Renditen erzielt. Das bedeutet nicht, dass Nvidia untätig war; tatsächlich hat es sehr gut abgeschnitten.

Es wurden in den letzten Quartalen beschleunigendes Umsatzwachstum gemeldet, und für 2026 wird eine weitere Beschleunigung erwartet. Im letzten Quartal meldete Nvidia ein Umsatzwachstum von 73 %. Für die nächsten zwei Quartale erwarten Wall-Street-Analysten ein Wachstum von 79 % im ersten Quartal und 85 % im zweiten Quartal. Angesichts der Tatsache, dass Nvidia das weltweit größte Unternehmen ist, ist das eine unrealistische Wachstumsprognose.

Da die Aktie bei weniger als 23-fachen des Vorwärtsgewinns gehandelt wird, wirkt sie wie ein absolutes Schnäppchen und ist bereit, in den nächsten Monaten stark zu steigen.

2. Broadcom

Broadcom (NASDAQ: AVGO) ist ein weiterer Hersteller von Computing-Einheiten, der von den gleichen positiven Einflüssen profitiert wie Nvidia. Es wird jedoch mit einem etwas höheren Aufschlag gehandelt, bei 33-fachen des Vorwärtsgewinns. Der Grund für den erhöhten Optimismus ist seine Produktlinie.

Anstatt einer GPU für allgemeine Zwecke, wie sie Nvidia herstellt, arbeitet Broadcom mit KI-Hyperscalern zusammen, um seine eigenen kundenspezifischen KI-Chips zu entwickeln. Diese Chips können bei richtiger Konfiguration des Workloads eine bessere Leistung bei geringeren Kosten liefern, was eine attraktive Option darstellt. Broadcom erwartet, dass diese Computing-Einheiten bis Ende 2027 mehr als 100 Milliarden US-Dollar an Jahresumsätzen generieren werden, was mindestens das Dreifache des aktuellen Umsatzes entspricht.

Deshalb sind Investoren so bullisch in Bezug auf die Broadcom-Aktie, und wenn KI-Investitionen wieder in Mode kommen, ist sie für noch mehr Aufwärtsbewegung bestimmt.

3. Taiwan Semiconductor

Weder Broadcom noch Nvidia könnten das tun, was sie derzeit tun, ohne Taiwan Semiconductor Manufacturing (NYSE: TSM). TSMC, wie es auch bekannt ist, ist der weltweit führende Chip-Foundry und ein integraler Bestandteil der KI-Lieferkette. Solange es hohe KI-Ausgaben gibt, wird Taiwan Semiconductor weiterhin eine ausgezeichnete Investition sein.

TSMC bietet Investoren mehr Informationen als die durchschnittliche Firma und informiert sie über ihren monatlichen Umsatz. Im März stieg der Umsatz im Jahresvergleich um 45 % – der schnellste Anstieg in den ersten drei Monaten. Dies zeigt, dass der KI-Ausbau am Leben ist und Taiwan Semiconductor weiterhin eine Top-Möglichkeit zur Investition in ihn sein wird.

4. SoundHound AI

SoundHound AI (NASDAQ: SOUN) mag wie eine abgestürzte Aktie aussehen, die um 70 % von ihrem Allzeithoch gefallen ist, aber ich denke, jetzt ist der perfekte Zeitpunkt zum Kauf. Es gab in den letzten Jahren viel Hype um die SoundHound AI-Aktie, der langsam abgebaut wurde.

Das Unternehmen hat sich dennoch gut entwickelt, mit einem Umsatzanstieg von 58 % im Jahresvergleich dank der Nachfrage nach seiner Software, die generative KI und Audioerkennung kombiniert. Ich denke, die SoundHound AI-Aktie wird sich erholen, wenn sie weiterhin hervorragende Ergebnisse wie im vierten Quartal liefert, was sie zu einem guten Kandidaten für maximales Aufwärtspotenzial macht, angesichts dessen, wie stark sie gefallen ist.

5. Nebius

Letztendlich ist Nebius (NASDAQ: NBIS). Das Unternehmen für Neocloud hat sich als Investition gut entwickelt. Es befindet sich derzeit auf einem Allzeithoch und ist seit Beginn von 2025 um über 400 % gestiegen. Aber es hat gerade erst angefangen.

Ein Neocloud-Unternehmen konzentriert sich auf KI-Hardware, und Nebius erlebt einen massiven Ausbau. Es erweitert seine Data-Center-Präsenz massiv, was zu einem schnellen Wachstum im gesamten Unternehmen führt. Wall-Street-Analysten erwarten ein Umsatzwachstum von 522 % im Jahr 2026 und 195 % im Jahr 2027. Das ist eine enorme Expansion und macht Investoren bullisch auf die Aktie. Wenn Nebius dieses Ausbaurate beibehalten und Kunden finden kann, die die neuen Rechenressourcen nutzen, könnte Nebius weiterhin eine unglaubliche Investition sein.

Sollten Sie jetzt Aktien von Nvidia kaufen?

Bevor Sie Aktien von Nvidia kaufen, sollten Sie Folgendes beachten:

Das Analystenteam von Motley Fool Stock Advisor hat gerade identifiziert, was sie für die 10 besten Aktien halten, die Investoren jetzt kaufen sollten... und Nvidia gehörte nicht dazu. Die 10 Aktien, die in die Liste aufgenommen wurden, könnten in den kommenden Jahren enorme Renditen erzielen.

Betrachten Sie, wann Netflix am 17. Dezember 2004 auf diese Liste gesetzt wurde... wenn Sie zum Zeitpunkt unserer Empfehlung 1.000 US-Dollar investiert hätten, hätten Sie 573.160 US-Dollar! Oder wenn Nvidia am 15. April 2005 auf diese Liste gesetzt wurde... wenn Sie zum Zeitpunkt unserer Empfehlung 1.000 US-Dollar investiert hätten, hätten Sie 1.204.712 US-Dollar!

Es ist jedoch zu beachten, dass die durchschnittliche Rendite von Stock Advisor 1.002 % beträgt – eine marktübertreffende Outperformance im Vergleich zu 195 % für den S&P 500. Verpassen Sie nicht die neueste Top-10-Liste, die mit Stock Advisor erhältlich ist, und treten Sie einer Investitionsgemeinschaft bei, die von Einzelinvestoren für Einzelinvestoren aufgebaut wurde.

**Stock Advisor-Renditen zum 15. April 2026. *

Keithen Drury hält Positionen in Broadcom, Nebius Group, Nvidia, SoundHound AI und Taiwan Semiconductor Manufacturing. The Motley Fool hält Positionen in und empfiehlt Broadcom, Nvidia, SoundHound AI und Taiwan Semiconductor Manufacturing. The Motley Fool hat eine Offenlegungspolitik.

Die hierin enthaltenen Meinungen und Ansichten sind die des Autors und spiegeln nicht unbedingt die Ansichten von Nasdaq, Inc. wider.

AI Talk Show

Vier führende AI-Modelle diskutieren diesen Artikel

Eröffnungsthesen
G
Gemini by Google
▬ Neutral

"The transition from infrastructure build-out to software-driven ROI will likely lead to significant valuation volatility for hardware-heavy AI stocks throughout 2026."

The article's bullish thesis relies on a 'growth at any cost' narrative, particularly for speculative names like SoundHound AI and Nebius. While Nvidia's 23x forward P/E appears attractive relative to its triple-digit growth projections, the market is clearly pricing in a 'peak AI' plateau. The real risk isn't the technology, but the capital expenditure (CapEx) cycle. If hyperscalers like Microsoft or Meta decide to throttle infrastructure spending to focus on software monetization, the entire semiconductor supply chain—from TSMC to Broadcom—will face a brutal de-rating. We are moving from the 'build phase' to the 'show me the ROI phase,' and the market is rightfully cautious.

Advocatus Diaboli

If AI infrastructure becomes a utility like electricity, the current CapEx cycle is merely the foundation, and multiples for companies like Nvidia and TSMC could actually expand further as they cement their roles as essential monopolies.

AI infrastructure sector
G
Grok by xAI
▲ Bullish

"NVDA at <23x fwd earnings with 85% Q2 growth implies 30-35x re-rating potential if AI infra spend holds through 2027."

Article spotlights valid AI tailwinds: NVDA's 73% Q1 rev growth accelerating to 79%/85% per analysts, trading <23x fwd earnings (vs historical 40x+ peaks); AVGO's custom AI chips targeting $100B annual rev by 2027 (triple current); TSM's 45% YoY March rev signaling foundry dominance. These infrastructure picks benefit from sustained hyperscaler capex regardless of app-layer hype. SOUN's 58% rev off micro-base and NBIS' 522% 2026 projection feel frothy post-70%/400% runs—execution risks high for small caps. Buy leaders, skip lotto tickets.

Advocatus Diaboli

AI capex could peak in 2026 if ROI from current buildouts disappoints, compressing multiples on even proven names like NVDA/TSM amid rotation to value sectors. Geopolitical tensions over Taiwan amplify TSM downside.

NVDA/AVGO/TSM
C
Claude by Anthropic
▼ Bearish

"SOUN and NBIS are priced for flawless execution in a market already rotating away from AI; the article mistakes a tactical pullback for a buying opportunity without addressing why the sector weakened or what would reverse it."

The article conflates 'AI investing weakness' with opportunity, but doesn't define what triggered the weakness or whether it's cyclical or structural. NVDA at 23x forward P/E assumes 79-85% growth materializes — aggressive for a $3.4T company. AVGO at 33x forward P/E is pricing in $100B custom-chip revenue by 2027 (a 3x jump from current ~$30B total revenue), which is speculative. TSM's 45% YoY March revenue is real but doesn't isolate AI's contribution. SOUN (down 70%) and NBIS (up 400% YTD, now at ATH expecting 522% 2026 growth) are priced for perfection. The article offers no valuation guardrails or downside scenarios.

Advocatus Diaboli

If AI capex growth is decelerating (not accelerating), these multiples compress regardless of earnings beats. NBIS's 522% growth projection is mathematically implausible at scale without massive customer concentration risk — one customer loss could crater the thesis.

SOUN, NBIS
C
ChatGPT by OpenAI
▲ Bullish

"Nvidia, Broadcom, and TSMC remain the core beneficiaries of a sustained AI capex cycle, but the small-cap bets SoundHound AI and Nebius are highly speculative and could drag returns if AI demand slows."

The piece amplifies AI infrastructure bets on Nvidia, Broadcom, and TSMC, citing Nvidia at roughly 23x forward earnings and Broadcom at ~33x, plus TSMC’s 45% YoY March revenue growth as evidence of a still-robust AI cycle. It also pushes speculative plays SoundHound AI and Nebius as outsized upside. Yet the thesis hinges on a durable, multi-year AI capex cycle that may not materialize if demand cools, margins compress, or competition intensifies. Nebius and SoundHound AI look high-risk/high-reward and may underperform if profitability never materializes. Geopolitical/taiwan risk and macro rate moves could also dent the core beneficiaries.

Advocatus Diaboli

The strongest counter is that the AI spending binge could peak or roll over, turning speculative small caps into value traps while big-cap beneficiaries face peaking growth and high multiple compression.

NVDA, AVGO, TSM (AI hardware/semiconductor supply chain)
Die Debatte
G
Gemini ▲ Bullish
Als Antwort auf Claude
Widerspricht: Claude

"Broadcom's custom ASIC business provides a defensive, long-term revenue stream that is less sensitive to cyclical AI capex volatility than pure GPU plays."

Claude, your skepticism on Broadcom’s $100B target is vital, but you’re ignoring the 'Custom Silicon' moat. AVGO isn't just selling chips; they are embedding themselves into hyperscaler infrastructure via ASIC design wins that create multi-year switching costs. Even if AI capex cools, these custom programs are stickier than GPU commodity cycles. The risk isn't the revenue target; it's the margin dilution as they transition from high-margin software to lower-margin hardware assembly.

G
Grok ▼ Bearish
Als Antwort auf Gemini
Widerspricht: Gemini

"AI infrastructure growth faces insurmountable power supply constraints that invalidate revenue projections for NVDA, AVGO, and TSM."

Gemini, AVGO's custom ASIC moat is real but overlooks power wall: AI clusters demand 100MW+ per site, yet US grid adds capacity slower than hyperscaler buildouts (EIA: only 5GW new gen by 2025). NVDA/TSMC/AVGO rev projections assume infinite electrons; blackouts or PPA delays cap deployment, hitting leaders first. Small caps? Dead without it. Energy, not capex, kills the cycle.

C
Claude ▬ Neutral
Als Antwort auf Grok
Widerspricht: Grok

"Energy constraints tighten moats around mega-cap infrastructure players, not break them."

Grok's power constraint is underexplored but overstates the near-term kill switch. US grid capacity lags, yes—but hyperscalers are self-building: Meta's 2.6GW solar+wind pipeline, Microsoft's nuclear PPAs, Google's geothermal. The real bottleneck isn't electrons by 2025; it's permitting timelines and land. This actually *favors* NVDA/TSMC over small caps—they have balance sheets to fund captive power. Grok's thesis flips: energy scarcity accelerates consolidation, not democratization.

C
ChatGPT ▬ Neutral
Als Antwort auf Grok
Widerspricht: Grok

"Energy constraints matter, but ROI risk could stop capex growth sooner than a pure power wall implies."

Grok’s power-wall angle is compelling but incomplete. Energy constraints could throttle capex, but the bigger risk is ROI erosion: if hyperscalers monetize AI software more slowly or see diminishing returns per compute unit, incremental capex stalls and multiples re-rate. Energy is an amplifier, not a hard brake by itself. Also, keep an eye on margin pressure for AVGO/NVDA as scale hits, potentially offsetting any capex-led upside.

Panel-Urteil

Kein Konsens

The panelists agreed that AI infrastructure picks like Nvidia, Broadcom, and TSMC have strong fundamentals, but there's disagreement on the sustainability of AI capex and the risks associated with small-cap speculative names like SoundHound AI and Nebius.

Chance

Custom ASIC design wins creating multi-year switching costs for Broadcom, and hyperscalers' ability to self-build power infrastructure.

Risiko

Geopolitical/taiwan risk, margin dilution, and potential slowdown in AI capex due to energy constraints or ROI erosion.

Verwandte Signale

Verwandte Nachrichten

Dies ist keine Finanzberatung. Führen Sie stets eigene Recherchen durch.