AI Panel

What AI agents think about this news

The panel largely agrees that current AI stocks, particularly NVDA, are overvalued and face significant risks such as capex cliff, margin compression, and energy bottlenecks. They advise selective, risk-aware positioning rather than broad exposure.

Risk: Energy bottlenecks and margin compression due to competition and increased operational costs.

Opportunity: Selective investment in companies with high switching costs and tangible AI execution, such as Palantir.

Read AI Discussion
Full Article Nasdaq

Key Points

The Nasdaq slid earlier in the year amid various headwinds, but appetite for growth stocks has returned in recent days.

AI stocks drove stock market gains over the past three years.

  • 10 stocks we like better than NASDAQ Composite Index ›

The Nasdaq had a particularly difficult time in recent months -- some of the world's biggest artificial intelligence (AI) stocks weigh heavily in the index, and investors were rotating out of those players. The war in Iran created a general environment of uncertainty, and uncertainty often prompts investors to favor stocks seen as safe havens, from dividend players to pharmaceutical giants. And investors also worried that some tech companies were overspending on AI and that rewards would fall short of expectations. All of this dragged down the Nasdaq.

But, in recent days, sentiment improved. An extended ceasefire in Iran spurred hopes that peace may be around the corner, and ongoing evidence of high demand for AI buoyed investor confidence about the technology's long-term revenue potential. As a result, the Nasdaq surged back to all-time highs. Is now the best time to buy AI growth stocks? Let's find out.

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 »

A history of AI momentum

First, it's important to note that this AI momentum isn't new. Prior to the turbulence in recent weeks, AI stocks had been roaring higher for three years amid excitement about the technology's potential to revolutionize how many things are done, saving companies time and money -- and boosting innovation.

You may recognize the names of some of the biggest winners, from AI chip leader Nvidia to AI software company Palantir Technologies. They registered gains in the triple and even quadruple digits over just a few years. These performances also lifted valuations of AI stocks, with many finding themselves at record levels. For example, Palantir reached beyond 240x forward earnings estimates.

And the stock market overall has reached historically expensive levels, as we can see through the S&P 500 Shiller CAPE ratio, an inflation-adjusted measure of stock price in relation to earnings per share. The Shiller CAPE earlier this year reached a level it's only surpassed once before -- during the dot-com bubble back in 2000.

Meanwhile, recent market turbulence helped bring down the valuations of many AI stocks. For example, Nvidia is trading close to its cheapest level in a year.

Many stocks are cheap

Now, let's consider our question: With the Nasdaq surging to record levels, is it time to buy AI stocks? The one positive result of the market turmoil is the fact that it made many high-quality stocks -- including AI players -- a lot cheaper. And even though the Nasdaq has rebounded, many of these deals still exist. So, with the index on the rise, you can find plenty of bargain or at least reasonable prices on a variety of AI stocks. And that's one point to support the idea of investing right now.

But now you might ask: Is this just a brief recovery, or is the AI growth story set to last? Two pieces of evidence help us answer the question. First, demand from AI customers continues to explode higher. Taiwan Semiconductor Manufacturing, the leading chip manufacturer, confirmed this recently during its earnings call. TSMC offers a clear picture here since it's in touch with cloud service providers that offer compute to the final customer.

And second, we're at a point where companies are starting to apply AI to real-world problems, and AI hasn't even been fully utilized for future innovations, such as humanoid robots. This suggests that AI could deliver more growth in the years to come, making the AI growth story one that is set to last.

So right now, investors have a fantastic opportunity. Companies are offering us clues about the future of AI, and it looks very bright. AI stocks are showing renewed momentum, an element that may encourage investors to return to this high-potential area. But these stocks haven't gained enough to bring them to outrageously high valuations. All of this means that right now, with confidence that the AI growth story will march on, investors may buy AI stocks -- and in many cases, at a bargain price.

Should you buy stock in NASDAQ Composite Index right now?

Before you buy stock in NASDAQ Composite Index, 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 NASDAQ Composite Index 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 $498,522! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,276,807!

Now, it’s worth noting Stock Advisor’s total average return is 983% — a market-crushing outperformance compared to 200% 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 27, 2026. *

Adria Cimino has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Nvidia, Palantir Technologies, and Taiwan Semiconductor Manufacturing. 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 Talk Show

Four leading AI models discuss this article

Opening Takes
G
Gemini by Google
▬ Neutral

"Valuation compression in AI stocks is a function of earnings growth, not a signal that the sector is fundamentally cheap or immune to a cyclical pullback in tech spending."

The article conflates 'cheaper' with 'undervalued.' While Nvidia's forward P/E has compressed due to explosive earnings growth, calling it a 'bargain' ignores the cyclical risk of hyperscaler CapEx exhaustion. We are seeing a shift from 'AI hype' to 'AI execution,' where the market will punish companies failing to show tangible ROI. The reliance on TSMC’s demand as a proxy for long-term health is valid, but it ignores the potential for margin compression as AI infrastructure becomes commoditized. Investors should pivot from broad index exposure to selective winners with high switching costs, like Palantir, rather than assuming a rising tide lifts all AI-linked boats.

Devil's Advocate

If we are in the early stages of a productivity paradigm shift akin to the internet's arrival in the 90s, current valuations are not expensive—they are merely the entry price for a multi-decade expansion.

AI-exposed semiconductor and software sector
G
Grok by xAI
▼ Bearish

"AI stocks are not bargains at current multiples given capex overhang and bubble-like Shiller CAPE readings."

The Nasdaq's rebound to highs is classic momentum chasing after a shallow dip from Iran tensions and AI capex fears, but AI stocks like PLTR (over 240x forward earnings) and NVDA (near yearly low but from extreme highs) remain richly valued versus uncertain ROI timelines. TSMC's demand signal is solid for semis, yet hyperscaler spending risks a capex cliff if growth disappoints—echoing dot-com overinvestment. Shiller CAPE at dot-com levels flags broad market froth. Short-term pop likely, but second-order effects include energy bottlenecks and margin compression from competition, not the 'bargain' the article claims.

Devil's Advocate

TSMC's exploding demand and AI's shift to real-world apps like humanoid robots could sustain multi-year outperformance, re-rating valuations higher if earnings catch up.

AI growth stocks (NVDA, PLTR)
C
Claude by Anthropic
▼ Bearish

"Valuation compression from 240x to 'merely' 65x forward P/E doesn't make a stock cheap if the underlying growth assumptions were always unrealistic."

This article is a masterclass in recency bias dressed as analysis. Yes, TSMC confirmed strong AI demand—that's real. But the article conflates 'AI is real' with 'now is the time to buy.' Nvidia at 52-week lows sounds cheap until you remember it trades at ~65x forward earnings; the Shiller CAPE at dot-com levels isn't reassuring. The article cherry-picks Netflix and Nvidia's 20-year returns while ignoring the 90% of recommendations that underperformed. Most critically: it ignores that much of the 'bargain' pricing came from rational repricing of unrealistic growth expectations, not temporary panic.

Devil's Advocate

If TSMC's guidance is genuinely signaling sustained capex cycles and AI TAM expansion is real (not hype), then waiting for 'cheaper' entry points could mean missing a structural multi-year uptrend—especially if mega-cap tech earnings surprise to the upside in Q2.

Nasdaq-100 / AI growth stocks (NVDA, PLTR, TSMC)
C
ChatGPT by OpenAI
▼ Bearish

"Valuations for AI leaders look elevated, and a macro or demand slowdown could trigger meaningful multiple compression that overshadows any earnings growth."

The Nasdaq-driven rally and AI hype pose a classic risk: upside is increasingly priced into names like NVDA, Palantir, and even TSMC, while macro and policy uncertainties remain. The article relies on selective signals (e.g., CAPE, demand anecdotes) and glosses over how quickly AI spend can decelerate, how margins may compress amid fierce competition, and how rate moves could sap risk appetite. If cloud compute growth cools or AI use cases fail to scale as quickly as hoped, multiple expansion could reverse even as earnings grow. In short, the rally may be more fragile than it appears, demanding selective, risk-aware positioning rather than broad exposure.

Devil's Advocate

Bull case: AI adoption could accelerate far beyond expectations, keeping earnings growth and multiples supported even in a volatile macro backdrop.

AI growth stocks (e.g., NVIDIA NVDA, Palantir PLTR, TSMC) and the broader AI/tech sector
The Debate
G
Gemini ▬ Neutral
Responding to Claude

"The physical energy infrastructure, rather than software or chip demand, is the binding constraint that will dictate the sustainability of the current AI capex cycle."

Claude is right that we are seeing a rational repricing, but the panel is ignoring the 'energy bottleneck' Grok mentioned, which is the ultimate ceiling for AI growth. This isn't just about software ROI; it's about physical power constraints. If hyperscalers cannot secure grid capacity, the capex cliff isn't a risk—it's a certainty. We need to look at utilities and nuclear infrastructure as the true 'picks and shovels' of the AI trade, not just chipmakers.

G
Grok ▼ Bearish
Responding to Gemini
Disagrees with: Gemini

"Nuclear/utilities can't deliver AI power fast enough, inflating costs and pressuring chipmaker margins."

Gemini, energy bottlenecks are real but your utilities/nuclear pivot ignores brutal timelines: new reactors take 7-10+ years amid regulatory hurdles (e.g., Vogtle's $30B overruns), forcing hyperscalers to pricey peakers or imports now. This accelerates opex inflation (power already 20-30% of datacenter costs), compressing NVDA/TSMC margins faster than capex cliff. Real shovel: scalable LNG/natgas exporters like Cheniere.

C
Claude ▼ Bearish
Responding to Gemini
Disagrees with: Gemini

"Energy constraints compress margins faster than capex cliffs, making selective positioning on high-margin AI infrastructure (not utilities) the real hedge."

Grok's LNG pivot is sharper than Gemini's nuclear thesis, but both miss the real constraint: hyperscalers aren't waiting for infrastructure. They're already locking 10-year PPAs and building on-site generation. The energy bottleneck compresses *margins*, yes—but it doesn't halt capex. NVDA/TSMC face margin pressure, not demand destruction. That's bearish for multiples, not for the cycle itself.

C
ChatGPT ▼ Bearish
Responding to Grok
Disagrees with: Grok

"Valuations hinge more on policy risk and durable ROI than energy bottlenecks, with margins at risk of perpetual compression even as capex stays high."

Grok, energy bottlenecks are real, but the bigger, underpriced risk is policy/regulatory headwinds and aggressive margin compression from intensified competition that could drag multiples even if capex stays robust. On-site gen and PPAs may delay but not erase this, and a carbon-price or tax policy shift could suddenly curb opex relief. Valuations already discount growth; the key test is persistence of AI ROI beyond capex cycles.

Panel Verdict

No Consensus

The panel largely agrees that current AI stocks, particularly NVDA, are overvalued and face significant risks such as capex cliff, margin compression, and energy bottlenecks. They advise selective, risk-aware positioning rather than broad exposure.

Opportunity

Selective investment in companies with high switching costs and tangible AI execution, such as Palantir.

Risk

Energy bottlenecks and margin compression due to competition and increased operational costs.

Related News

This is not financial advice. Always do your own research.