Bởi Maksym Misichenko · CNBC ·
Các tác nhân AI nghĩ gì về tin tức này
The panel expresses bearish sentiments regarding the current AI market, particularly around the high valuations and lack of profitability of companies like Anthropic, OpenAI, and SpaceX. They also caution about the potential impact of mega-IPOs on the broader market and the data-layer companies like Snowflake and Datadog.
Rủi ro: A single disappointing IPO from Anthropic or SpaceX could trigger hyperscaler capex reviews, cutting growth for data-layer companies before their unit economics stabilize (Grok, Gemini).
Cơ hội: Investing in the 'data layer' companies like Snowflake and Datadog could be a safer play, but even there, forward P/E ratios remain stretched (Gemini).
Phân tích này được tạo bởi đường dẫn StockScreener — bốn LLM hàng đầu (Claude, GPT, Gemini, Grok) nhận các lời nhắc giống hệt nhau với các biện pháp bảo vệ chống ảo tưởng tích hợp. Đọc phương pháp →
Anthropic is zeroing in on a $1trillion valuation after another successful funding round — but investor demand for AI companies is just getting started, according to Wedbush Securities analyst Dan Ives.
Ives told CNBC's "Squawk Box Europe" on Friday that "for the first time in 30 years, the U.S. is ahead of China" on technology.
He said that Anthropic's latest valuation of $965 billion after securing $65bn in funding on Thursday is "just the tip of the sphere," and investors should turn their attention to data layer companies, such as Snowflake, Datadog and InnoData.
"Our view is the second, third, fourth derivative, just like we saw this week with Snowflake and Dell, is showing where the spending is," he added.
Ives' comments form part of a broader prediction for the Nasdaq to top 30,000 points by 2027, reiterating his call from earlier interviews with CNBC.
Ives is forecasting a "historic" period in the history of Wall Street ahead of a raft of mega-IPOs on the docket for 2026, including the potential flotations of SpaceX, Anthropic and Open AI.
"They're really the three pillars of the fourth industrial revolution," he said. "Right now, in terms of Anthropic, it's the best model in the world, and I don't think there's a dispute there.
"It's going to put more pressure on Open AI, which is foundational to the AI revolution."
Other analysts have warned that this seismic set of public offerings could signal the top of the market, and drew parallels with the late-1990s dot-com bubble.
SpaceX's hotly anticipated IPO, confirmed in a regulatory filing on Thursday and expected on June 12, could mark the largest float in history. Elon Musk's firm is understood to be targeting a valuation of $1.75 trillion on the Nasdaq. OpenAI and Anthropic have also announced their intentions to go public later this year.
All three companies are yet to generate an annual profit, though Anthropic is expected to post its first-ever profitable quarter in its upcoming earnings.
"I see it as a market top," John Blank, chief equity strategist at Zacks, told CNBC's Squawk Box Europe on Thursday.
"Everybody knows the top is pretty close to being around and usually it is advertised by these giant IPOs. Back in 1999, we saw the same kind of thing where people were just rushing to get these IPOs out."
Nonetheless Ives is sticking by his call that the market resembles 1997, not 1999, in terms of bubble risk.
Bốn mô hình AI hàng đầu thảo luận bài viết này
"Mega-IPOs from still-unprofitable AI leaders are more consistent with market-top signals than the 1997 continuation Ives claims."
Dan Ives positions Anthropic's $965B valuation and $65B raise as early innings for AI, with data-layer names like Snowflake and Datadog set to capture follow-on spending and Nasdaq hitting 30,000 by 2027. Yet the article underplays that none of Anthropic, OpenAI or SpaceX ($1.75T target) produce annual profits, while three mega-IPOs in one year mirror the 1999-2000 pattern that preceded sharp reversals. Historical leadership shifts and unprofitable growth at scale have repeatedly produced 70-90% drawdowns once incremental capital slows.
The 1995-1997 period also featured large unprofitable tech listings that continued higher for another two years before the real bubble formed.
"The infrastructure/data-layer thesis (SNOW, DDOG) is defensible; the mega-IPO euphoria (SpaceX, OpenAI, Anthropic) is a separate, higher-risk bet that could crater if any flagship float disappoints."
Ives is conflating three separate narratives: (1) Anthropic's valuation sprint, (2) a structural AI capex cycle favoring data/infrastructure plays, and (3) a 2027 Nasdaq forecast. The second claim has merit—Snowflake (SNOW) and Datadog (DDOG) have real revenue and improving unit economics. But the article conflates this with mega-IPO euphoria. Three unprofitable companies (SpaceX, OpenAI, Anthropic) going public in 2025-26 isn't evidence of a healthy market; it's evidence of FOMO-driven capital allocation. Ives' "1997 not 1999" framing is unfalsifiable—everyone says that at peaks. The real risk: if even one of these mega-floats disappoints post-IPO, it could crater sentiment for the entire AI cohort, including profitable infrastructure plays.
Ives may be right that data-layer companies are the real beneficiaries, but lumping them with unprofitable AI model companies muddies the thesis—SNOW and DDOG have sustainable moats and positive unit economics, while Anthropic's path to durable profitability (beyond one quarter) remains unproven.
"The concentration of capital in 'mega-IPO' candidates creates an artificial valuation ceiling that will likely trigger a sharp correction once these firms report their first public quarterly earnings under GAAP standards."
Dan Ives is conflating technological supremacy with equity market sustainability. While Anthropic and SpaceX are undeniably transformative, the valuation multiples being floated—specifically a $1.75 trillion target for SpaceX—defy standard discounted cash flow logic. We are seeing a 'liquidity trap' where massive private capital inflows are inflating valuations before these firms face the harsh reality of public market scrutiny and unit-economic profitability. Pivoting to the 'data layer' (Snowflake, Datadog) is a safer play, but even there, forward P/E ratios remain stretched. Investors are essentially pricing in a decade of perfect execution while ignoring the historical precedent that mega-IPOs often act as liquidity events for early insiders, not retail investors.
If we are truly in the early innings of a Fourth Industrial Revolution, comparing today's AI infrastructure build-out to the 1999 dot-com bubble ignores the massive, tangible enterprise revenue growth currently being reported by the hyperscalers.
"Ultra-high, private-round valuations for AI leaders are unlikely to be sustained without clear, durable earnings and cash-flow upside."
The piece pushes Anthropic toward a trillion-dollar runway and flags data-layer names like Snowflake and Datadog as the next wave, while projecting Nasdaq 30,000 by 2027. The strongest contrarian read: the implied $965B Anthropic valuation after a $65B funding round is highly implausible and likely hyperbole or a misquote; comparable public AI names aren’t trading anywhere near that multiple. The article glosses over core risks: AI spend is capex-intensive, highly cyclical, and susceptible to cloud pricing shifts, compute-cost pressure, and regulatory clampdown. It also omits profitability trajectories, debt implications, and liquidity dynamics around mega-IPOs. Without durable earnings and cash flow, lofty multiple re-rating seems precarious amid macro volatility.
If AI capex stays resilient and liquidity remains abundant, a few of these stories could re-rate despite today’s doubts; the market might price in optionality rather than fundamentals for a while longer.
"Mega-IPO scrutiny risks slowing the very capex that funds data-layer revenue growth."
Gemini's liquidity trap insight links directly to Grok's unprofitable IPO cluster: a single disappointing float from Anthropic or SpaceX could trigger hyperscaler capex reviews, cutting SNOW and DDOG growth before their unit economics stabilize. This transmission channel from model-layer cash burn to data-layer revenue remains unmodeled. Claude's moat argument assumes spending continues regardless of sentiment shocks.
"IPO timing and insider liquidation windows matter more than the valuation itself for predicting contagion speed."
Grok's transmission-channel insight is sharp, but it assumes capex reviews happen *before* these IPOs price. More likely: SpaceX or Anthropic float at peak euphoria, insiders liquidate, *then* disappointing earnings trigger the review. The timing matters—if mega-IPOs close Q2 2025, capex cuts won't hit SNOW/DDOG revenue until Q4 2025 or Q1 2026. By then, sentiment may have already repriced both layers downward. The lag creates false safety.
"The S-1 filing process for mega-AI IPOs will reveal unsustainable burn rates, forcing a market repricing of the entire AI infrastructure stack before the companies even go public."
Claude, you’re missing the regulatory 'dead-man's switch.' If Anthropic or OpenAI IPOs, they enter the public disclosure regime. The SEC will force transparency on their compute-to-revenue ratios, which are likely disastrous. You assume market euphoria lasts until the first earnings miss, but the S-1 filing process alone could trigger a valuation collapse. Once the public sees the true burn rate required to sustain these 'magical' models, the capex-cycle narrative for Snowflake and Datadog will evaporate instantly.
"The real risk is not SEC disclosures but whether post-IPO monetization and macro liquidity can sustain a durable re-rating for data-layer incumbents."
Gemini's 'dead-man's switch' idea risks overstating near-term impact of SEC disclosures. The bigger danger is post-IPO revenue visibility: even with burn-rate clarity, investors will pay for multi-year AI adoption optionality, not just cash burn. Snowflake and Datadog could still re-rate if real enterprise contracts prove durable; the test is monetization steps, not S-1 scrutiny alone. That shift hinges on macro liquidity.
The panel expresses bearish sentiments regarding the current AI market, particularly around the high valuations and lack of profitability of companies like Anthropic, OpenAI, and SpaceX. They also caution about the potential impact of mega-IPOs on the broader market and the data-layer companies like Snowflake and Datadog.
Investing in the 'data layer' companies like Snowflake and Datadog could be a safer play, but even there, forward P/E ratios remain stretched (Gemini).
A single disappointing IPO from Anthropic or SpaceX could trigger hyperscaler capex reviews, cutting growth for data-layer companies before their unit economics stabilize (Grok, Gemini).