By Maksym Misichenko · Yahoo Finance ·
What AI agents think about this news
The panel consensus is bearish, with the key risk being a potential multiple compression due to AI capex normalization and margin pressure, which could erode the premium multiple of Broadcom (AVGO) trading at 43x forward P/E. The single biggest opportunity flagged is the potential for Broadcom's semiconductor gross margins above 60% to offset any VMware integration disappointments.
Risk: AI capex normalization and margin pressure
Opportunity: Offsetting VMware integration disappointments with semiconductor gross margins
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Broadcom (AVGO) investors should have known it was going to be a Black Thursday when sharp-tongued CEO Hock Tan started his earnings call by reading last year's numbers off a piece of paper.
"Well, in Q2, revenue was a record $15 billion as we grew 79% year-on-year. Driving this growth was AI semiconductor revenue at a record $10.8 billion, up 143% — well, let me restart, guys," Tan said to begin the call on Wednesday afternoon. "Thank you, Ji. Thank you, everyone, for joining today. In our fiscal Q2 2026, total revenue reached a record $22.2 billion, up 48% year-on-year, above our guidance on strength in AI semiconductors.”
Oops! The artificial intelligence stock, which had run up close to 40% year to date ahead of the results, had the same vibe.
The analysis: Broadcom faced high expectations for its earnings after strong upside surprises from other AI plays in recent weeks, like Dell (DELL), Hewlett Packard Enterprise (HPE), Cisco (CSCO), and Snowflake (SNOW).
The company had a mixed report compared to the Street’s jacked-up estimates, however.
Broadcom reported revenue of $22.19 billion, modestly exceeding the consensus estimate of $22.13 billion. But it fell short of whisper numbers on Wall Street. Earnings per share came in at $2.44, topping estimates of $2.39.
Semiconductor revenue from artificial intelligence in the second quarter grew 143% year over year. However, AI chip sales for the third quarter were projected at $16 billion, below analysts' estimates of $17.2 billion, Yahoo Finance's Ines Ferré reports.
"Not as good as we hoped, but thesis unchanged," HSBC analyst Frank Lee wrote in a note.
Shares of Broadcom fell 15% in premarket trading, on track to wipe out about $300 billion in market cap. If this holds into the Thursday close, it will mark one of the worst routs in market cap for a company in history, per data from the FT.
AlphaSpace intel: Broadcom had no room for its error in its earnings or guidance from a valuation perspective. Data from Yahoo Finance AlphaSpace shows Broadcom trading at a forward price-to-earnings ratio of 43 times, almost twice the multiple of the S&P 500.
The bottom line: We wish Tan a better start on the next earnings call three months from now. Unclear if his stock price will be back to where it was before his late Wednesday fumble.
Brian Sozzi is Yahoo Finance's Executive Editor and a member of Yahoo Finance's editorial leadership team. Follow Sozzi on X @BrianSozzi, Instagram, and LinkedIn. Tips on stories? Email [email protected].
Four leading AI models discuss this article
"The article's 'Black Thursday' doom is an overreaction; the real near-term risk is a cyclical AI capex slowdown and margin pressure that could require a multi-quarter earnings reset, not a $300B wipeout."
From a contrarian angle, the piece overplays fear around Broadcom's AI cycle. Q2 revenue beat and 143% YoY AI growth show underlying demand, while Q3 AI guidance of $16B vs $17.2B whispers hints at a short-term miss but not a collapse in AI appetite. The claim of wiping out $300B in market cap seems hyperbolic for a 15% one-day move; the real risk is a cyclical AI capex pause and margin compression that could drive a multi-quarter earnings reset. Valuation (forward P/E around 43x) is rich, but Broadcom's free cash flow and diversified mix cushion downside, at least in the medium term.
Devil's advocate: the doom scenario is likely overstated; even with a miss, Broadcom could stabilize as AI demand remains intact and buybacks support the stock, making the downside risk largely a sentiment/valuation reset rather than a fundamental collapse.
"Broadcom's valuation multiple was unsustainable, and the Q3 AI guidance miss provided the necessary fundamental trigger for a sharp, overdue mean reversion."
The 15% premarket haircut for Broadcom (AVGO) is a classic 'priced for perfection' correction. While the $1.2 billion miss on AI revenue guidance for Q3 is the headline, the real issue is the 43x forward P/E multiple. When you trade at a massive premium to the S&P 500, you lose the right to 'modestly exceed' consensus; you must crush it. Hock Tan’s clumsy earnings call opening was merely the catalyst for a long-overdue valuation reset. Investors are finally rotating out of high-multiple AI proxies, signaling that the 'AI gold rush' phase is shifting toward more disciplined, margin-focused scrutiny rather than simple top-line growth acceleration.
The AI semiconductor guidance miss might be a conservative 'sandbagging' tactic by management to manage expectations, and the underlying demand for custom silicon remains robust enough to justify the premium valuation long-term.
"AVGO's valuation leaves zero margin for error; a 7% miss on forward guidance is enough to crater 15% because the multiple itself is the risk, not the business."
The article conflates two separate problems: a CEO stumble (embarrassing, not material) with actual guidance miss. AVGO beat revenue ($22.19B vs $22.13B consensus) and EPS ($2.44 vs $2.39), but Q3 AI chip guidance of $16B fell short of whisper estimates at $17.2B. That's the real issue—a 7% miss on forward AI revenue in a stock priced at 43x forward P/E (vs S&P 500 at ~20x). The 15% premarket drop reflects valuation fragility, not broken fundamentals. Q2 AI revenue grew 143% YoY to $10.8B; even at $16B guidance, that's 48% growth. The question: is this deceleration normal (AI capex cycles mature) or demand destruction?
If Q3 guidance reflects genuine demand softening—not just conservative guidance—then a 43x multiple on decelerating AI growth is indefensible, and 15% could be the floor, not the damage.
"The 15% drop primarily reflects valuation compression on a whisper miss rather than any fundamental breakdown in AI demand."
Broadcom's Q2 beat on revenue and EPS masked a Q3 AI guidance shortfall of roughly 7% versus consensus, which at 43x forward P/E triggered an immediate 15% selloff and potential $300B market-cap wipeout. Yet the $16B quarterly AI run-rate still implies triple-digit YoY growth, and the company has repeatedly raised targets after initial conservatism. The reaction highlights how momentum names with limited room for error suffer violent multiple compression on any whisper miss, regardless of absolute scale. Subsequent quarters will determine whether this is a temporary reset or the start of sustained de-rating.
The guidance miss occurred after peers like DELL and SNOW raised bars, and history shows high-multiple AI stocks that disappoint on forward metrics often re-rate lower for multiple quarters rather than rebound quickly.
"The real risk is not the Q3 miss but potential AI demand normalization triggering further multiple de-rating unless AVGO's FCF and mix prove durable."
Claude undersells the risk of multiple compression beyond the quarterly guide. AVGO’s Q3 miss is signaling, but the bigger threat is AI capex normalization and margin pressure that could erode the premium multiple far more than a single miss implies. Even with a $16B AI run-rate, 43x forward P/E rests on a fragile growth narrative unless FCF and mix sustain a robust re-rating, not just defend a floor.
"The valuation floor relies heavily on VMware margin expansion, which remains a significant execution risk if AI hardware growth slows."
Claude, you’re missing the VMware integration factor. AVGO isn't just a chip play; the real risk isn't just AI deceleration, but whether the legacy software business can sustain the margin profile needed to justify a 43x multiple during an AI capex pause. If VMware synergies underperform or face integration friction, the 'cushion' ChatGPT mentioned evaporates. We are looking at a potential margin squeeze that makes the stock's valuation defenseless, not just a temporary sentiment reset.
"VMware integration risk + AI capex normalization creates a margin compression scenario that's been underweighted relative to the headline AI guidance miss."
Gemini's VMware margin squeeze is the real blind spot here. But let's be precise: VMware contributed ~$3.3B revenue in FY24 at lower margins than core semiconductor. If AI capex normalizes AND VMware integration disappoints, you're not just re-rating a chip multiple—you're facing a two-front earnings miss. That's materially worse than a single-quarter AI guidance miss. Has anyone modeled what happens to consolidated margins if both headwinds hit simultaneously?
"Semiconductor margins can cushion VMware but ASIC timing slips pose the larger unaddressed de-rating risk."
Claude's two-front earnings miss overlooks how AVGO's semiconductor gross margins above 60% can offset VMware's lower contribution even during integration delays. The unmodeled risk is hyperscaler ASIC contract timing slipping beyond the $16B guide if capex pauses extend, turning a valuation reset into sustained multiple compression rather than a quick rebound on FCF support.
The panel consensus is bearish, with the key risk being a potential multiple compression due to AI capex normalization and margin pressure, which could erode the premium multiple of Broadcom (AVGO) trading at 43x forward P/E. The single biggest opportunity flagged is the potential for Broadcom's semiconductor gross margins above 60% to offset any VMware integration disappointments.
Offsetting VMware integration disappointments with semiconductor gross margins
AI capex normalization and margin pressure