Di Maksym Misichenko · CNBC ·
Cosa pensano gli agenti AI di questa notizia
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.
Rischio: 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).
Opportunità: 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).
Questa analisi è generata dalla pipeline StockScreener — quattro LLM leader (Claude, GPT, Gemini, Grok) ricevono prompt identici con protezioni anti-allucinazione integrate. Leggi metodologia →
Anthropic si sta concentrando su una valutazione di 1 trilione di dollari dopo un altro round di finanziamento di successo, ma la domanda degli investitori per le aziende di AI è appena iniziata, secondo l'analista di Wedbush Securities Dan Ives.
Ives ha detto a "Squawk Box Europe" di CNBC venerdì che "per la prima volta in 30 anni, gli Stati Uniti sono in vantaggio sulla Cina" in termini di tecnologia.
Ha detto che l'ultima valutazione di Anthropic di 965 miliardi di dollari dopo aver ottenuto 65 miliardi di dollari di finanziamenti giovedì è "solo la punta della sfera", e gli investitori dovrebbero prestare attenzione alle aziende del livello dei dati, come Snowflake, Datadog e InnoData.
"La nostra opinione è che il secondo, terzo, quarto derivato, proprio come abbiamo visto questa settimana con Snowflake e Dell, sta mostrando dove si sta spendendo", ha aggiunto.
I commenti di Ives fanno parte di una previsione più ampia per il Nasdaq che supererà i 30.000 punti entro il 2027, ribadendo la sua chiamata dalle interviste precedenti con CNBC.
Ives prevede un periodo "storico" nella storia di Wall Street in vista di una serie di mega-IPO in programma per il 2026, tra cui le potenziali flottazioni di SpaceX, Anthropic e Open AI.
"Sono davvero i tre pilastri della quarta rivoluzione industriale", ha detto. "Al momento, in termini di Anthropic, è il modello migliore al mondo, e non credo ci sia una contestazione.
"Metterà più pressione su Open AI, che è fondamentale per la rivoluzione dell'AI."
Altri analisti hanno avvertito che questo insieme sismico di offerte pubbliche potrebbe segnalare il top del mercato, e hanno tratto parallelismi con la bolla dei dot-com alla fine degli anni '90.
L'IPO molto attesa di SpaceX, confermata in un deposito normativo giovedì e prevista per il 12 giugno, potrebbe segnare la più grande offerta nella storia. Si capisce che la società di Elon Musk stia puntando a una valutazione di 1,75 trilioni di dollari sul Nasdaq. OpenAI e Anthropic hanno anche annunciato le loro intenzioni di quotarsi in borsa più tardi quest'anno.
Tutte e tre le società non hanno ancora generato un profitto annuale, sebbene Anthropic dovrebbe pubblicare il suo primo trimestre redditizio nella sua prossima relazione sugli utili.
"Lo vedo come un top di mercato", ha detto John Blank, chief equity strategist di Zacks, a Squawk Box Europe di CNBC giovedì.
"Tutti sanno che il top è piuttosto vicino e di solito è pubblicizzato da queste enormi IPO. Nel 1999 abbiamo visto la stessa cosa, dove le persone si stavano solo affrettando a far uscire queste IPO."
Tuttavia Ives continua a sostenere che il mercato assomiglia al 1997, non al 1999, in termini di rischio di bolla.
Quattro modelli AI leader discutono questo articolo
"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).