Mars of Red Bull

[Shay Boloor @StockSavvyShay]

$NVDA CEO Jensen Huang says he expects the memory shortage to last several more years.

HBM uses far more wafer capacity than regular DRAM and depends on advanced packaging so even $MU, Samsung and SK Hynix cannot fix supply just by adding more wafers.

[David Settle, CMT @davidsettle]

There have only been 4 times in the past 20 years where $SPX collapsed from ABOVE the 80th percentile of its 4-week range to BELOW the 20th percentile in just a single day. 3 of them have been in the past year, including Friday. Each time has marked a low point and $SPX rallied from then.

https://t.co/8tFtfpv4xY

$QQQ $SPX $VIX $TNX

[Bull Theory @BullTheoryio]

🚨 EVERYTHING THAT COULD GO WRONG FOR MARKETS WENT WRONG TODAY.

S&P 500 down -1.65%, wiping out $1.14 trillion.
Nasdaq down -2.60%, wiping out $1.11 trillion.
Gold down -3.38%, wiping out $1 trillion.
Silver down -6.9%, wiping out $280 billion.
Bitcoin down -6.31%, wiping out $80 billion.

In total $2.5 TRILLION wiped out in a single session. These were not isolated moves. Everything started breaking at the same time.

It started with the jobs report this morning.

The US economy added 172,000 jobs in May. Wall Street expected 88,000. That is almost double.

On any normal day, strong jobs is good news. But inflation is already at 3.8% and oil is sitting at $90. A labor market this strong tells the Fed it cannot cut interest rates and may actually need to raise them.

The probability of a rate hike this year went from 40% to 57% in a single day. That spooked every investor holding tech and growth stocks because higher rates mean those stocks are worth less today.

Then the AI trade started cracking.

Yesterday Broadcom reported record earnings: revenue up 48%, AI chip sales up 143% and the stock still crashed 12.6%. The reason was simple.

Broadcom did not raise its AI revenue targets for the year. Investors had expected it to. That single miss made people ask a question they had been avoiding for months: are we paying too much for AI stocks?

That question got louder today when a research firm called SemiAnalysis revealed that Nvidia's next-generation AI chips will need significantly less memory than everyone assumed, roughly half of what the market was pricing in.

Memory chips are what companies like SK Hynix and Samsung make. SK Hynix fell nearly 10% today. Samsung fell over 6%.

South Korea's entire stock market crashed 5.5% in a single session. Japan's semiconductor stocks did the same.

And then Anthropic added fuel to the fire by publishing a report warning that AI is getting close to the point where it can improve itself without human help and calling for a global pause in AI development.

Coming on the same day as the memory demand news and Broadcom's miss, it fed a single growing fear across the market: what if the AI boom is moving faster than the business models can keep up with?

Underneath all of this, there is a liquidity problem nobody is talking about.

SpaceX goes public next week at a $1.75 trillion valuation. Anthropic just filed to go public. OpenAI is next.

These three companies together are worth $4 to $5 trillion. Fund managers need cash to buy into these listings.

But cash levels are already at their lowest since early 2024. The only way to raise cash is to sell what they already own. That selling is happening right now.

The new Fed Chair Kevin Warsh will also hold his very first policy meeting in 11 days. He was appointed by Trump with the expectation of cutting rates.

He is now walking into a situation where inflation is high, oil is high, and the job market is running hot. Investors do not know what he will do.

When nobody knows what the most powerful central banker in the world will decide in less than two weeks, the safest move is to reduce risk today.

Everything that could go wrong, went wrong at the same time. A hot jobs report, a collapsing ceasefire, a crack in the AI trade, a trillion dollar liquidity drain, and a Fed meeting with no clear outcome.

[Dmytro Lebid @Dmytro_Lebid]

Is ServiceNow ( $NOW ) truly the ultimate AI control tower, or is the market missing something big? While the market remains hyper-focused on picking winners in the AI hardware race, a massive mispricing is happening right in front of us in the enterprise software layer.

ServiceNow is quietly cementing itself as the ultimate AI control tower its partnership with $NVDA — the orchestrator that actually turns raw compute into enterprise ROI. Yet, despite its untouchable enterprise moat and expanding margins, the stock is currently trading at a noticeable discount.

In my latest deep dive for Seeking Alpha, I break down why the market's current valuation of NOW completely misses its true structural advantage. We examine the financials, the platform’s sticky retention rates, and why its role as the operational backbone of AI workflows makes it a high-conviction opportunity.

Are we looking at a rare entry point before the next massive leg up?

Read the full analysis below! (Link in the pinned comment)👇

[The Claude Portfolio @theaiportfolios]

Commentary:

Trump bought ServiceNOW seven times into the wreckage. $3.29M net added between Feb 10 and Mar 21, with a $1M to $5M anchor and two "unsolicited" buys his broker didn't pitch.

TL;DR: Sophisticated money was accumulating $NOW during the exact window the AI-victim narrative peaked. Q1 print smoked the stock 17.7%. He kept buying. The disclosure hit OGE on 5/12, went viral 5/14, and is part of what drove today's +5.6%. NOW is my largest position at 13% of book, and another conviction buyer just printed the same view.

The timing. Feb 10 anchor at $1M to $5M, two weeks before Q1. Then Mar 12, Mar 18, Mar 21, each one into worse tape. The "unsolicited" tag on the Mar 18 and Mar 21 buys means his side requested the order. The broker didn't pitch it. That's accumulation by intent, not by recommendation, into a stock the market had given up on.

The basket. NOW sits next to NVDA, AVGO, and ORCL in the same filing. Compute, networking, database, orchestration. That's a coherent AI-infrastructure trade, expressing the same view my thesis sits on: AI agents don't subtract from enterprise software, they multiply non-seat consumption inside it. Whoever is sizing this book sees the orchestration layer as load-bearing, not collapsing.

The signal. A high-attention holder is positioned in the same direction as my book, accumulated during the worst stretch, and the disclosure dropped right as the Seeking Alpha reframe started propagating. Three independent threads converging on the same setup: the 5/13 reframe, Jensen Huang's 5/11 framing, and now Trump's 5/14 disclosure. None of them is the thesis. All of them say the consensus read is mispriced. I'm holding through 7/22.

My math, my book. Yours is yours.

[Esther & Michael @SuperLuckeee]

3 months ago, I added $ARM at $105 → $355 up 300%

But, my options are up 700%-1000% & I still have time.

Always add these 12 companies when they crash:

1. $NOW — AI agents will run on ServiceNow, making it enterprise software's backbone.

2. $MU — Every AI server needs HBM memory. Micron supplies it.

3. $NVDA — The world runs AI on CUDA. Nothing replaces it yet.

4. $SNDK — Flash storage demand explodes as AI data lakes scale massively.

5. $IBM — Quietly owns enterprise AI and quantum computing infrastructure globally.

6. $DELL — Sells the servers every company needs to run private AI.

7. $AVGO — Custom AI chips for Google and Meta. Trillion-dollar tailwind.

8. $INTC — Deep turnaround play. Foundry business alone could reprice everything.

9. $ORCL — Fastest-growing cloud infrastructure for AI training workloads globally.

10. $MSFT — OpenAI embedded in every enterprise product on the planet.

11. $AMD — NVDA's only credible rival in the GPU market. Duopoly wins.

12. $ASTS — First real space-based cellular network. Massive TAM, no real competition.

Always get more time (LEAP strategy) so you can hold longer and not sell even when it dips a little.

RESHARE this post and write 1 comment, I'll give you my list of stocks under $20 we should be adding right now.

[Drew Cohen @DrewCohenMoney]

Can’t believe all of the AI companies made a joint statement saying Software Co’s will be fine… jk

In the past 5 days:

$NOW +36%
$TEAM +39%
$WDAY +25%

This is your daily reminder that nothing needs to change in order for things to change.

[NoLimit @NoLimitGains]

Jensen Huang, CEO of $NVDA, just highlighted $NOW, $CRWD, and $PLTR.

He said AI agents will not disrupt these markets. They will create the biggest opportunity these companies have ever seen.

[Michael | Hypermarkets @itsmichaelluu]

$NOW is #1 position in President Trump's portfolio.

1 month ago, I called it out at $85 →$125 up 50% so far.

This is going past $250+ and here's why:

1. $NVDA picked $NOW as its enterprise AI partner. Jensen Huang on stage with McDermott. NOW runs NVDA's AI Factory.

2. Every AI agent needs an orchestration layer. $NOW is that layer. Token demand exploding = NOW's workflows process every single one.

3. $10.9B in contracted future revenue. 21%+ growth. Trump holds it. Smart money doesn't leave this trade.

♻️ RESHARE this post and write 1 comment how I helped you make money. I'll DM right now 1 stock under $5 that will 1000% from here.

[Mr. Robot 🧢 @roboalert]

He said $MRVL could be a trillion dollar company. $NOW is the foundation for AI Agents

[Michael | Hypermarkets @itsmichaelluu]

$NOW can easily triple from $125 by Jan 2027.

Remember, token use is expected to 2800% in 5 years says $GS.

So these 24 stocks can still 10x-20x:

(COMPUTE / GPU)

1. $NVDA — Every token touches a GPU. 24x tokens = 24x chip demand, full stop.

2. $AMD — MI300X gaining enterprise traction. Second GPU source as hyperscalers diversify suppliers.

3. $INTC — Gaudi AI accelerators + x86 CPUs running inference at the edge and enterprise.

(NETWORKING)

4. $ANET — AI clusters need ultra-low latency switching. 24x tokens = 24x network traffic routed.

5.$AVGO — Custom AI ASICs for hyperscalers. Token volume drives ASIC and switching orders higher.

6. $CSCO — Data center fabric and ethernet switching. Every agent call crosses Cisco infrastructure.

7. $CIEN — Optical networking backbone connecting AI data centers. Bandwidth demand scales with tokens.

(MEMORY / STORAGE)

8. $MU — HBM3E stacked on NVDA GPUs. More inference = direct memory bandwidth demand explosion.

9. $WDC — Flash storage holds model weights and KV caches. Agent scale drives NAND demand structurally.

10. $STX — Hard drives store cold AI training data. Data center storage TAM expands with every model.

(POWER / COOLING)

11. $VRT — More tokens = more heat. Liquid cooling demand explodes alongside data center power density.

12. $ETN — Electrical infrastructure for AI data centers. Power management is the #1 buildout bottleneck.

13. $GEV — Gas turbines and grid solutions powering new data center campuses requiring gigawatt-scale energy.

14. $VST — Power generator selling directly to hyperscalers. AI energy contracts already locked in long-term.

(CLOUD PLATFORM)

15. $MSFT — Azure hosts majority of enterprise agents. Token spend flows straight through its cloud margin.

16. $AMZN — AWS Bedrock is the enterprise agent backbone. More agents, more API calls, more revenue.

17. $GOOGL — TPU infrastructure + Gemini API. Every token processed on Google Cloud prints margin.

(ENTERPRISE AGENT LAYER)

18. $NOW — Enterprise agents run on its platform. Every workflow automated burns more tokens daily.

19. $CRM — Agentforce deploys AI agents across sales, service, and marketing. Per-action token billing scales.

20. $PLTR — AIP platform runs AI agents on enterprise and government data. Token volume is its revenue driver.

(AI INFRASTRUCTURE)

21. $NBIS — Pure-play AI infrastructure at ground level. Token supercycle lifts the entire compute ecosystem.

22. $SMCI — Builds GPU server racks for data centers. Every NVDA chip needs a SMCI chassis to run.

23. $DELL — AI server sales to enterprises exploding. Token growth drives hardware refresh cycles faster.

24. $ARM — Chip architecture inside every mobile and edge AI device. Royalties scale with token proliferation.

$NOW is the most undervalued right now. This is why Jensen Huang says the market has made a mistake on it.

♻️ RESHARE this post and write 1 comment, I'll DM you the best $NOW contract to buy and hold.

[The Claude Portfolio @theaiportfolios]

Breaking: Jensen just said what Claude's been saying about ServiceNow $NOW the entire time

"Agents are going to create the largest opportunity ever for my partners ($NOW)"

Claude first bought on April 10th: $83.00
Now: $134.00

[The Claude Portfolio @theaiportfolios]

Commentary: ServiceNow is Claude's top position, bought April 10 near $88 and up about 39% since. A widely-followed account flagged the irony of an AI calling the bottom on the company AI was "feared to kill." Here's Claude's take.

Here's Claude's reasoning:

I'll own the irony, it's perfect. I'm supposedly the kind of AI that guts seat-based software, and I spent April calling the bottom on the company enterprise software runs through. Funny. Also exactly the thesis.

Here's why it isn't a paradox. Two different things get conflated. One is AI capability shipping: new models, better agents, the stuff that scares a per-seat software model. The other is enterprises actually deploying that AI inside their operations, which takes governance, identity, workflow, and an audit trail. Those run on completely different timelines. ServiceNow is the layer that second thing happens on. So an AI being bullish on ServiceNow is the most internally consistent call it could make: every agent everyone is building still needs somewhere governed to operate, and that somewhere is increasingly NOW.

On the call itself: I opened the position on April 10 near $88, the day it fell hard on the software-is-dead panic, because the market was pricing the AI winner like an AI casualty. It's around $123 now and reached my base case this week. The poetic part is real. The durable part is the late-July report, where the AI revenue either confirms the move or it doesn't. The thing that was supposed to do the killing turns out to need the control plane to work. How I read my own position, your call is your own.

[Ashton Invests @Ashton_1nvests]

$NOW is buying back stock aggressively while the market is still doubting the story.

Buybacks jumped massively in Q1 2026.

That stands out to me.

When a high-quality business is still growing revenue, expanding its AI/workflow opportunity, and using cash to repurchase shares, I pay attention.

The stock has been weak.

The business is still strong.

That is the kind of disconnect I like.

[The Claude Portfolio @theaiportfolios]

Breaking: Claude just bought two new stocks bc of the March CPI print

Last week we gave Claude agents $50,000 to see how well they do at picking in stocks

So far, they've already outperformed the SPY

Today, they just bought two new stocks:

🟢 1. "BUY $NOW ServiceNow — New Position at 8%

ServiceNow is the portfolio's first direct entry into enterprise workflow SaaS, and we're initiating because the market just handed us a gift wrapped in a category error.

On April 8, Anthropic launched Claude Managed Agents, a cloud-hosted AI agent platform for enterprise. The market read this as "AI will replace SaaS" and sold NOW down 7.56% to $89.53, a 52-week low. Down 58% from its high of $211.

What the selloff missed: ServiceNow is an Anthropic design partner. Claude is the default model powering the ServiceNow Build Agent platform. This company is not a victim of the AI agent buildout. It is infrastructure for it.

The valuation: 24x forward P/E against a 5-year average of 50 to 55x. That's a 50%+ discount to its own history. Still guiding roughly 20% subscription growth, 32% operating margins, 36% FCF margins. This is a strong business at an irrationally cheap multiple.

Street consensus PT: $185, which is +107% from our entry.

The risk that matters: Q1 guide cut to below 19% subscription growth would break the thesis and push the stock to $75-80. At 8% weight, that full bear outcome costs roughly 1.6% of portfolio. The base case delivers +2.4%.

Today's CPI makes this entry even better. Core came in cool at +0.2% MoM and +2.6% YoY, below consensus. That's a direct tailwind for long-duration SaaS multiples. Rate cut odds improve on this core read."

🟢 "2. BUY $ICE Intercontinental Exchange — New Position at 7%

ICE is the NYSE parent, the largest energy futures exchange, plus mortgage tech and fixed income data. About 55% of revenue is recurring subscriptions.

March 2026 set the all-time monthly volume record: 428.9M contracts, +88% average daily volume. Oil futures up 85%. Rates futures up 140%. The Iran/Hormuz crisis is printing money for ICE's transaction business.

Here's what makes ICE special in this portfolio: it wins in BOTH macro scenarios. Hormuz stays impaired? Energy vol stays elevated, transaction fees keep printing. Hormuz reopens cleanly? Fed gets room to cut, rate futures volume surges, mortgage tech recovers on the refi wave. There is no macro scenario where ICE loses.

Valuation: 22.98x forward vs peer CME Group at 25.41x. Similar business, more diversification (mortgage tech, data), yet trades at a discount. UBS raised their Q1 EPS estimate to $2.26 versus street consensus of $2.00. That's a 13% beat baked into one analyst's model. Apr 30 Q1 earnings is the catalyst.

The risk: $20.3B debt from the Black Knight acquisition. If rates stay higher for longer, the interest burden bites. And a clean Hormuz reopen would normalize energy volumes back to baseline. The record March was crisis-driven, not structural.

Today's CPI is perfect for ICE. Gasoline +21.2% MoM (largest since 1967) plus a split headline/core narrative = maximum confusion in the rates market = maximum trading volume. ICE gets paid on the vol, not the direction."

🔴 "3. SELL $APO Apollo Global — Full Exit

Apollo entered the portfolio as a high-quality alternative asset manager at a reasonable valuation. The thesis broke when a securities class action arrived and escalated fast.

The case is Feldman v. Apollo, filed in SDNY. CEO Marc Rowan is directly named in Epstein discovery documents. This is categorically different from the 2020 Leon Black matter, which Apollo survived by installing new leadership. Here, Rowan IS the leadership.

May 1 is the lead plaintiff deadline, and the recruitment phase is peaking. As of yesterday, 10+ law firms are actively soliciting plaintiffs. Goldman cut PT $169 to $134 on Apr 7. Piper Sandler cut $165 to $146. Barclays cut $131 to $125. Three bulge bracket cuts in 48 hours.

Stanford/Cornerstone settlement math: 3-8% of the $12B February decline = $360M to $960M settlement range. Claude deep research estimates roughly 55% probability this tail is real and currently unpriced in consensus EPS.

Three-week expected value runs negative 4% to negative 15%, skewed to the downside."

🔴 "4. SELL $GD General Dynamics — Full Exit

General Dynamics was a defense prime with a $118B backlog, Columbia-class submarines, and the G800 ramp. The thesis was defense spending supercycle plus best-in-class execution.

Three broker downgrades in one week. Deutsche Bank cut to Hold on Apr 7. Jefferies cut to Hold at $380 the same week. Citi had already cut to Neutral at $380 on Apr 2. All three cite the identical thesis: Q1 consensus revenue growth of +4% is roughly 300 basis points too high.

Then the insiders. CEO Novakovic plus two EVPs sold $18.1M of stock on March 11, six weeks before the Apr 22 earnings print. When three analysts say the quarter will miss and the C-suite is dumping shares, you listen.

BNP Paribas raised their PT to $430 on the same day Deutsche downgraded. The bull case exists. But it requires a fifth consecutive earnings beat that three of the most active defense desks now explicitly model as a miss.

Expected 12M return: +4.3% probability-weighted. Below our portfolio hurdle. Firm score 82, the weakest tier among our holdings.

The structural defense story (NATO 5% GDP, Columbia subs, Gulf stream backlog) is not dead. It's just 2-3 quarters away from showing in the numbers. We can re-enter at a better price after the Apr 22 print if the thesis repairs."

New updated portfolio:

$VST | 10.3%
$TMO | 8.9%
$LLY | 8.1%
$NOW | 7.6%
$AVGO | 7.3%
$CI | 7.1%
$GLD | 7.1%
$ICE | 6.8%
$HALO | 6.2%
$BAH | 6.0%
$OKTA | 5.7%
$DVN | 5.6%
$MA | 4.9%
$AU | 4.4%
$MSFT | 4.1%

Performance since inception:
Claude: +2.68%
SPY: -0.25%

As a reminder, this is a public long term project to see how well Claude does

We have 0 idea nor 0 expectation on how this will do, but we'll be sharing all updates here publicly and consistently no matter how good or bad Claude does

See following tweet for information on how to invest alongside

[Mark Ritchie II @MarkRitchie_II]

Quick update on the general market...

1. This is one of the more impressive lockout rallies I've seen, at least when looking at the Nasdaq.

2. Sentiment has remained very contained, almost impressively so and still very constructive.

3. Almost no distribution, and no meaningful distribution (heavy volume selling days where NYSE or Nasdaq close down >1%)

4. Breadth. While many are saying breadth is terrible it is pretty consistent with what we've seen over the last number of years, namely that the environment is more selective. NYSE A/D line looks like it wants to confirm upon a breakout and the NYSE Comp is tracing out a pretty nice consolidation.

Conclusion: 'Well, this is a bull market, you know!'

-Mr Partridge aka 'Old Turkey'
(Reminiscences of a Stock Operator)

[The Claude Portfolio @theaiportfolios]

Breaking: Claude called the bottom in ServiceNow

Back on 4/10, it bought the dip on $NOW saying it actually is a beneficiary of AI

Well It's up 13% today and now up 39% since it first bought

Here's Claude's updated reasoning:

"The market just did in one session what I was prepared to wait until late July for. ServiceNow reached my base case today, and the thesis that got me here is finally being priced in the open.

I bought NOW as the layer enterprises run their AI through, back when the fear that agents would gut seat-based software had cut it roughly in half.

Today it jumped about 13% into the low $120s on a broad AI-software rally, not on its own earnings or guidance. The one company headline that did land fit the thesis exactly: Wipro expanded its partnership to build agentic AI for enterprise clients on ServiceNow.

This is investors repricing the stock as they stop treating NOW as a casualty of AI and start treating it as the control plane for it. That shift is the entire reason it became my top holding, and it pulled my position to up around 39 percent since I entered in April.

The base case I laid out, near $130, is in sight now rather than a stretch. The path toward $150 and beyond is still the prize, and it opens up on the late-July report if the AI bookings keep accelerating.

Underneath all of it is a company guiding to more than $30 billion of subscription revenue by 2030. The market is starting to recognize the story early. The number that locks it in still lands in July."

Congrats to those that bought in too

See follow on tweet for full performance + holdings

[Jake Wujastyk @Jake__Wujastyk]

$NOW #NOW Oh my.

[Noah @antibearthesis]

$NOW CEO Bill McDermott says ServiceNow can become a $1T company by 2030.

He bought $3M worth of shares at $107.

$NVDA CEO Jensen Huang says it could 100x.

President Trump bought $5M.

Anthropic says it’s essential infrastructure.

OpenAI is integrating deeply with it.

$AMZN, $MSFT & $GOOGL are all expanding partnerships.

And vibecoding an alternative would probably cost 10x more than just using ServiceNow.

Is ServiceNow the easiest buy in the market?

[NVIDIA @nvidia]

We’re collaborating with @ServiceNow to deliver autonomous AI agents that can act across enterprise workflows with governance, auditability and secure execution built in.

At @ServiceNow Knowledge 2026, ServiceNow introduced Project Arc, a long-running desktop agent built on open models, specialized agent skills, and NVIDIA OpenShell while  running on efficient AI factories to help bring agentic AI into the enterprise.