The H.E.A.T. Formula is a radically different way to look at investing your portfolio.
H- Hedges, you should always have hedges and be agnostic as to being long or short. Bonds are not a hedge
E-Edges, you should always look for edges. Preferably these are edges with some sort of psychological underpinning, structural edges, or some sort of barrier to entry.
A-Asymmetric. Everything you do, be it trades or your overall portfolio, should be designed so that heads you win a lot, tails you lose a little.
T-Themes. You should always be invested in the top themes. Most everything else is just noise.
Our Next Webinar
Uncovering Hidden Themes with AI: How DeepSeek Is Rewriting the Investment Playbook
Thu, Feb 27, 2025 2:00 PM - 3:00 PM EST
1. Bullets From DeepSeek to Disruptors: Explore how one AI breakthrough (DeepSeek) reveals cost-effective strategies and under-the-radar opportunities beyond mainstream tech giants.
2. Finding Alpha in the Noise: Learn how AI-driven data-mining cuts through market hype and identifies genuine growth catalysts—even in emerging or overlooked sectors.
3. Comparing & Contrasting Strategies: Discover how to harness AI to evaluate different investment approaches.
In the News
YouTube Videos
We will be hosting The Watchlist every Thursday. Jeremy Vreeland (Bullish Bears) and I will be discussing stocks we are currently watching, buying, or shorting. We will also be discussing how to structure trades for asymmetrical returns and we will take your questions.
Click below to register for the next one:
Market Recap
The market was pushed and pulled all day by the tariff news, which again highlights the issues of trying to trade under Trump. We continue to view the tariffs as a short term negotiating tool and not as policy. My preference is to buy the dips.
From Jefferies this morning, I don’t disagree…..
Our view remains that eventually tariffs will end up not as bad as feared. Hence, medium term (over a 3m-6m horizon), we retain our positive view on risky assets. The macro backdrop continues to be supportive and positioning light, which should be positive for risky assets. However, we do admit that there is likely to be more speed bumps on the way. Coming days are likely to be dominated with headlines around negotiations with China. Europe is likely next in the tariff and negotiations story.
One potential issue around the tariffs is what, if anything, it does to the Fed. Also from Jefferies this morning…..
FED’S HANDS TIED? Even if Fed members have not explicitly cited Trump policies changing their outlook – they have commented on how they are observing the impact of these policies – the actual implementation of tariffs is likely to delay interest rates cuts or even price cuts out for the 2025 altogether. Note hawkish comments from Fed's Bostic who suggested waiting before more cuts.
This could end up being a bigger deal if the market’s have to tamp down rate cut forecasts. However, last year was all about that and the indices didn’t seem to care.
GOOGL earnings tonight ought to be a big deal….
“DeepSeek has sent waves through megacap tech recently and we expect management might address its implications to Gemini and capex spending plans going forward, as well as the threat that lower barriers to creating LLMs could pose,” Deutsche Bank analyst Benjamin Black wrote in a note on Friday. He rates Alphabet as a Buy with a $215 price target.
Palantir
Long a favorite of ours and a holding in GUNZ as it spans the self defense and AI theme.
Karp added in an interview that a recent highlight for Palantir has been “getting to humiliate all the people who said large language models are the end state, not the resource that needs to be processed.” The company focused on managing LLMs while other companies emphasized building them, he said.
Now after DeepSeek, more people on Wall Street are coming around to the ideas that LLMs might be a commodity.
This quote seemed important to me, so I asked GPT….
Is This a Big Deal? Short Answer: Yes
Defining the Future of AI Monetization
For a while, the AI narrative was “Build the best model, and the world beats a path to your door.” Palantir’s results showcase that the truly lucrative spot might be in turning those models into integrated, enterprise-ready solutions.
This shift parallels the early internet era, where connectivity (the “commodity”) gave rise to applications (the real profit center).
Sign of Maturity in AI
As LLM technology stabilizes, the conversation moves from “Which model is biggest or best?” to “How do we plug this into the CFO’s daily workflow?” or “How do we ensure compliance with HIPAA or SEC regulations?”
This marks a transitional moment: AI is no longer just a “research toy” or marketing tagline. It is becoming industrialized and subject to real-world constraints—exactly the domain that Palantir serves.
Re-Shaping Competitive Landscapes
Accelerators for startups: If LLMs are easier to obtain, smaller players can build specialized AI solutions. But large enterprise deals often favor established, trusted partners with robust compliance. Hence, Palantir gains momentum.
Ecosystem Partnerships: We should expect more tie-ups among LLM providers, cloud infrastructure companies, and solution integrators, as all try to capture a slice of the downstream “AI solution” profit pool.
Investor Sentiment
Palantir’s blowout earnings serve as a “proof point” that the real money in AI might not be in raw model-building. This is an important shift in how investors evaluate AI companies.
Conclusion
From a “Nobel Prize” vantage point, Palantir’s earnings aren’t just about beating expectations; they highlight a structural shift in the AI value chain. As LLMs proliferate and become commodity-like, the premium (both technologically and financially) is on seamless deployment, security, domain expertise, and data governance—precisely the layer Palantir offers.
Key Takeaways
Palantir’s Blowout Earnings: They reflect the enterprise market’s acute demand for deployable AI solutions, not just raw models.
LLMs as Commodity: This idea is game-changing. If no single LLM has a lasting moat, the real opportunity is in “orchestration” and specialized integration.
Broader Implications: Cloud vendors, enterprise software giants, and a constellation of AI middleware startups will scramble to provide robust, scalable, and compliant solutions, reinforcing Palantir’s head start.
Yes, It’s a Big Deal: These results signal that the next wave of AI monetization lies in practical, production-ready enterprise deployments—and Palantir is positioning itself at the center of that transformation.
In short, the excitement is not just about Palantir’s quarter. It’s about confirming a paradigm shift in how AI is being utilized—and monetized—across industries.
I also asked for a list of potential winners…..
Highest Upside Potential: Smaller to mid-size pure-play or AI-centric platforms (like C3.ai or possibly BigBear.ai) can see the largest “shock factor” in earnings if they sign major deals.
Solid Mid-Range: Data infrastructure leaders (Snowflake, Datadog, ServiceNow, etc.) stand to benefit steadily as more enterprises integrate AI into core operations. While not as likely to “triple overnight,” they can still deliver above-consensus quarters.
Mega-Caps: Giants like Microsoft, Alphabet, and Oracle will undoubtedly leverage AI extensively, but the effect on earnings surprises is somewhat muted by their scale and the extent to which AI is already “priced in.”
In essence, the idea that LLMs may quickly become commodities shifts the revenue potential to integrators, orchestrators, and data platforms. Palantir’s big beat highlights this dynamic—and these other companies are well positioned to ride the same wave, provided they can demonstrate real enterprise traction and ROI.
DeepSeek 2.0
DeepSeek caught everyone by surprise last week, but should it have? Kind of kicking myself as I use AI to help me choose investment and manage risk and the risk of an AI “breakthrough” is pretty substantial and could upend my portfolio. I should have asked GPT, and should make a habit from time to time, if there is anything on the horizon I should be worried about. I asked if it would have seen DeepSeek coming, and I feel better about the answer…
Two weeks ago, I would have:
Acknowledged: “Yes, there’s a real chance that an under-the-radar group could yield a shocking HPC breakthrough. It’s not guaranteed, but it’s within the realm of possibility.”
Cautioned: “Exact who/when/how is uncertain, but HPC players remain susceptible to unexpected cost-efficiency leaps in LLM training.”
Outcome: DeepSeek turned that possibility into a sudden reality—with more immediate market ramifications than many anticipated.
So while I wouldn’t have predicted “DeepSeek exactly” or that it would roil markets last week, I would have pointed to the risk that HPC-limiting developments could surface in the near term. In short, the phenomenon was on the horizon—but the specifics were quite the shock.
I asked over the weekend if any other “threat” was on the horizon….
Below is an updated version of the speculative analysis on possible “DeepSeek-like” developments in AI, now including a probability rating (1–10) for the likelihood each event could surface over the next three to six months (1 = extremely unlikely, 10 = very likely). These probability scores are estimates given publicly known research trajectories and do not represent certainties.
1. Next-Gen Large Models or Major Open-Source Breakthrough
Examples: GPT-5 from OpenAI, a major Llama update from Meta, or a new open-source compression technique that drastically lowers HPC usage
Rationale:
Major labs frequently schedule model updates, though exact timelines are unpredictable.
Meta has teased ongoing Llama improvements; OpenAI consistently evolves GPT models.
The open-source community is actively refining or compressing large models (e.g., “llama.cpp,” specialized distillation frameworks).
Market Impact:
Could significantly reduce HPC requirements if breakthroughs in training efficiency or model compression are proven.
HPC stocks may dip if a major cost-lowering approach emerges.
Probability (Next 3–6 Months): 7/10
Highly plausible that at least one known AI lab or open-source community pushes out a more “efficient” model soon.
2. Cost-Saving AI Startups’ High-Profile Announcement (e.g., MosaicML, Cerebras)
Rationale:
MosaicML (acquired by Databricks) focuses on cheaper LLM training. They might release a success story or official cost metrics that rival DeepSeek’s approach.
Cerebras or similar hardware vendors could show wafer-scale HPC training at a fraction of standard GPU cost, with reproducible benchmarks.
Market Impact:
HPC suppliers see short-term re-rating if investors believe advanced alternatives will reduce top-tier GPU expansions.
Large cloud providers or software integrators partnering with MosaicML or Cerebras could see a sentiment boost.
Probability (Next 3–6 Months): 6/10
Startups typically need a big milestone or investor push; a public demonstration is possible, though not guaranteed.
3. Low-Precision Training or “Sparsity” Method Gains Traction
Rationale:
Many top AI research labs (including Nvidia) are racing to perfect low-precision (FP8, etc.) training and “sparsity aware” architectures.
Could drastically lower GPU memory usage and HPC compute needs, akin to DeepSeek’s cost-savings.
Market Impact:
If a standard library or widely adopted toolkit emerges, HPC expansions might be scaled back.
Software integrators gain if advanced AI becomes easy to embed using mid-tier hardware.
Probability (Next 3–6 Months): 8/10
This is already under active development. Substantial updates or library releases are quite likely, though the extent of cost reduction might vary.
4. Regulatory or Policy Shock on HPC Usage
Rationale:
Policy circles debate HPC usage licensing or restricting advanced HPC expansions, citing national security or AI safety.
Should a major economy (U.S., EU) enforce HPC oversight, HPC expansions could slow or re-route.
Market Impact:
HPC stocks (Nvidia, TSMC) might suffer if big cloud/hyperscalers must limit GPU clusters.
Encourages cost-efficient approaches—potentially a “DeepSeek-like” impetus.
Probability (Next 3–6 Months): 5/10
Discussions exist, but translating them into formal HPC-limiting laws within a short window can be slow. Not impossible if a big AI-safety push accelerates.
5. Quantum or Hybrid Symbolic-Neural Leap
Rationale:
A symbolic-neural method, or partial quantum advantage demonstration, that drastically shrinks the HPC footprint for large-model tasks.
This is on the bleeding edge and historically slow to commercialize.
Market Impact:
HPC mania might recede if a new approach skips the need for massive GPU clusters.
Large-scale HPC orders could be re-evaluated.
Probability (Next 3–6 Months): 2/10
Symbolic-neural research is active, but a major “DeepSeek-scale” success is less likely in the immediate timeframe. A partial demonstration is possible but full commercial readiness is slim.
Conclusion
While no single “DeepSeek 2.0” event is assured within the next three to six months, multiple publicly known lines of research could produce game-changing HPC efficiency breakthroughs:
Next-Gen LLM announcements (7/10).
Startup cost-saving revelations (6/10).
Low-precision or “sparsity” leaps (8/10).
Regulatory HPC constraints (5/10).
Quantum or symbolic-hybrid leaps (2/10).
Investment Takeaway: In the near term, the most plausible HPC-limiting developments revolve around low-precision training, sparsity frameworks, or model compression from major LLM labs—probabilities ~7–8 out of 10 that we see notable results. Investors heavily exposed to HPC hardware might consider partial hedges or rebalancing, while those bullish on AI’s broader adoption could look to software integrators that embed advanced AI at lower infrastructure cost.
NVDA
A week later, Nvidia’s stock price fell 17% in a single day, after Chinese company DeepSeek said it achieved a leap in its AI capabilities using less-advanced Nvidia chips. Some investors interpreted the advance as undercutting the market in the West for Nvidia’s top-of-the-line products.
Yet Nvidia knew that risk came with what it was doing in China, the country identified by both political parties in Washington as America’s biggest global rival.
From GPT….
Final Assessment
Despite near-term turbulence in Nvidia’s share price prompted by the DeepSeek narrative and potential regulatory tightening, the fundamental catalysts for Nvidia’s AI business remain robust. DeepSeek’s success confirms the potency of Nvidia’s chips (even “export-compliant” ones), reinforcing Nvidia’s role at the center of the global AI ecosystem. Over a multi-year horizon, maintaining regulated engagement with China best preserves Nvidia’s leadership and R&D dominance.
Therefore, the DeepSeek developments—in conjunction with the cat-and-mouse export control environment—are ultimately a net neutral in the immediate term (with some short-lived downside sentiment) and likely a net positive over the long term, as they reaffirm Nvidia’s indispensable position in AI. The narrative of “marginally downgraded chips can still power generational AI breakthroughs” bolsters Nvidia’s technology lock-in, keeps Chinese firms on Nvidia’s platform, and underscores the firm’s ability to navigate geopolitical constraints more adeptly than any would-be competitor.
European Aerospace and Defense
EU leaders meet to thrash out defence priorities and iron out remaining but significant divisions-Euro News
We launched EUAD because we think that Trump will force EU countries to pay more for their own defense, and those countries would rather spend at home than give that money to US defense companies. I asked GPT to analyze these articles…..
Final Assessment
Overall Impact for European Defense Sector: 8.5 / 10. The impetus for higher defense spending, plus the explicit preference for local manufacturing, provides a robust tailwind for major European aerospace and defense primes. Political will and heightened threat perceptions accelerate the rearmament cycle. The largest risk is bureaucratic delays and fragmentation among EU member states, which can dampen or slow the near-term order flow.
Leading Beneficiaries: Airbus, BAE Systems, Thales, Leonardo, Dassault, and Rheinmetall stand out, each an integral supplier across air, land, naval, and electronic warfare segments. They have the scale, advanced R&D, and established ties with EU governments to capture a large share of the new budgets.
Conclusion
Trump’s renewed demands on European burden-sharing—and EU leaders’ determination to build a “more autonomous, more reliable” defense posture—converge to drive a multi-year investment wave. While the path to finalizing budgets and procurement can be labyrinthine, the structural alignment points to meaningful, sustained upside for Europe’s domestic aerospace and defense industry.
Uranium
Fun fact that I didn’t know until yesterday, the US imports most of it’s uranium and a significant part comes from Canada…
I had GPT take a deep dive on this issue and pick some winners and losers….
1. Macro Context: U.S. Uranium and Canadian Supply
U.S. Reliance on Imported Uranium
The U.S. consumes large volumes of uranium for its roughly 90+ operating nuclear reactors, yet domestic production is comparatively small.
A significant portion of U.S. uranium imports comes from Canada (alongside Kazakhstan, Australia, and Russia). Should tariffs be imposed on Canada, utilities might pay higher prices if they rely on Canadian supply or scramble to find alternate sources.
Why Tariffs on Canadian Uranium?
With renewed emphasis on protectionism and “energy security,” a White House seeking to boost domestic industries might target Canadian uranium.
The direct effect: If Canadian uranium incurs a tariff, the cost-advantage of importing from Canada shrinks or vanishes, possibly raising prices for U.S. utilities (especially if re-contracting from other countries is difficult) and bolstering U.S. producers’ competitiveness.
Global Uranium Prices
Uranium is priced globally, but localized tariffs can cause short-term dislocations, changing which supply sources are feasible. Historically, any threat of trade restrictions has contributed to price volatility or upward pressure on uranium spot prices—though the magnitude depends on how widespread and strict the tariffs are.
2. Potential Market Impact
Near Term: U.S. utilities with pending supply contracts might face higher import costs, forcing them to consider domestic or alternative non-Canadian suppliers. This could accelerate domestic production restarts if prices rise.
Mid-to-Long Term: If the tariffs remain, domestic uranium producers could expand operations or develop new projects. However, ramping up uranium production can be time-consuming, given permitting, environmental reviews, and capital-intensive mine development.
Overall Magnitude: 7.5 / 10 (Moderate to high significance). Canada is a key, trusted uranium supplier, so tariffs would meaningfully reshape U.S. supply chains. But the global nature of uranium and the prevalence of other exporters (Kazakhstan, Australia) limits how far the disruption can go.
3. Winners and Losers
Below, each company is assigned a 1–10 rating for how strongly tariffs on Canadian uranium could affect them—positively (for “winners”) or negatively (for “losers”). A higher rating means a greater potential impact.
A. Potential Winners (Positive Impact)
Uranium Energy Corp (UEC) – Rating: 9/10
Why: A U.S.-based ISR (in-situ recovery) uranium producer, with projects in Texas and Wyoming. If Canadian uranium becomes tariffed, UEC’s domestic production becomes more cost-competitive.
Impact: Strong impetus to ramp up or sign more contracts if tariffs significantly curtail cheaper Canadian supply.
Energy Fuels (UUUU) – Rating: 8.5/10
Why: U.S. producer with mills (White Mesa Mill in Utah) and various mines. Also involved in rare-earth processing. A tariff environment favoring domestic sources could help them re-open or expand dormant uranium operations.
Impact: Gains via new supply contracts with utilities seeking “American” uranium.
Ur-Energy (URG) – Rating: 8/10
Why: Colorado-based with the operating Lost Creek in-situ recovery project in Wyoming. Has scaled back production but retains expandable capacity.
Impact: Could sign long-term deals at higher prices if Canadian imports are penalized.
Note: U.S. advanced explorers or near-term producers with American assets (e.g., Peninsula Energy, enCore Energy) might also see an incremental boost, though the immediate effect is more modest if they’re still in exploration/development.
B. Potential Losers (Negative Impact)
Cameco (CCJ) – Rating: 9.5/10
Why: Canada’s largest uranium producer (operating the high-grade McArthur River and Cigar Lake mines). Heavily reliant on the U.S. market for exports. Tariffs could drastically reduce the profitability of shipping to the U.S. or force them to price in the tariff.
Impact: Substantial. One of the biggest global uranium miners, strongly linked to the North American market.
Denison Mines (DNN) – Rating: 8.5/10
Why: Focused on Canadian uranium projects (e.g., Wheeler River in the Athabasca Basin). Although it’s an advanced developer rather than a major producer, the potential future sales to U.S. utilities could face cost barriers with new tariffs.
Impact: Hinders long-term offtake agreements if the U.S. is a key buyer. Possible shift to other markets, but tariffs complicate expansions and final mine feasibility.
NexGen Energy (NXE) – Rating: 8/10
Why: Developer of the high-grade Arrow deposit in Canada’s Athabasca Basin. Plans for a major production center in the coming years, presumably counting on big North American utility customers.
Impact: Tariff risk overshadowing near-term capex decisions. They might pivot more aggressively to export supply deals outside the U.S. or lobby for tariff exemptions.
4. Broader Considerations
Possibility of Exemptions or Quotas
Canada is a key ally, so the U.S. might negotiate quotas or partial exemptions for strategic reasons. This would soften the blow to companies like Cameco or Denison.
If no exemptions are granted, the cost differential for Canadian vs. U.S. uranium becomes stark.
Price-Upside for the Uranium Market
Tariffs limiting Canadian supply could drive up the spot or long-term uranium price. This benefits all producers globally, but especially U.S. producers who can deliver locally without incurring tariffs.
International producers from Kazakhstan or Australia might also see an opportunity to expand shipments if shipping/logistics constraints are manageable.
Nuclear Utility Response
Utilities locked into existing contracts might face minimal immediate impact, but new contracting cycles could favor local U.S. producers or alternative foreign sources without tariffs.
Rising prices or supply complications may encourage some utilities to push for partial repeal or seek creative supply routes.
5. Final Conclusion
Market Disruption: Potential U.S. tariffs on Canadian uranium would significantly alter North American uranium trade flows, likely lifting overall uranium prices modestly to moderately and boosting domestic U.S. mines’ attractiveness.
Biggest Winner: Uranium Energy Corp (UEC) – 9/10 stands out with near-term production capabilities and purely domestic operations.
Biggest Loser: Cameco (CCJ) – 9.5/10 would suffer the brunt of diminished access to the U.S. market or forced price concessions.
While the global uranium market is fairly interconnected—and new supply from Australia or Kazakhstan could fill some gaps—any direct restriction on a major supplier like Canada inevitably increases volatility and tilts near-term advantages toward U.S.-based uranium companies.
Before you go: Here are ways I can help
ETFs: We offer innovative ETFs that cover all aspects of The H.E.A.T. Formula, Hedges, Edges, and Themes.
Consulting: I'm happy to jump on the phone with financial advisors at no charge. I've built a wealth management firm and helped other advisors grow their practices through the use of substantially differentiated investment strategies. If you want to talk just send me an email at [email protected]
Monthly investing webinars
Weekly trading strategy podcast
Weekly investing podcast-Coming Soon
Wealth Management-Coming SoonThe views and opinions expressed herein are those of the Chief Executive Officer and Portfolio Manager for Tuttle Capital Management (TCM) and are subject to change without notice. The data and information provided is derived from sources deemed to be reliable but we cannot guarantee its accuracy. Investing in securities is subject to risk including the possible loss of principal. Trade notifications are for informational purposes only. TCM offers fully transparent ETFs and provides trade information for all actively managed ETFs. TCM's statements are not an endorsement of any company or a recommendation to buy, sell or hold any security. Trade notification files are not provided until full trade execution at the end of a trading day. The time stamp of the email is the time of file upload and not necessarily the exact time of the trades.TCM is not a commodity trading advisor and content provided regarding commodity interests is for informational purposes only and should not be construed as a recommendation. Investment recommendations for any securities or product may be made only after a comprehensive suitability review of the investor’s financial situation.© 2025 Tuttle Capital Management, LLC (TCM). TCM is a SEC-Registered Investment Adviser. All rights reserved.