NnnnotSoSmart

Added to my position yesterday. Don't be too hard on me. Remember I'm...

The private placement was done at $351.8 per Class A and $348.2 per Class C share. This increases BRK's GOOG(L) position by 50% above the latest 3/31/26 13F.. During April: GOOGL traded at prices ranging from $291-348/share. GOOG traded at prices ranging from $290-340/share. Those prices are less than what BRK paid in the private placement. The probability that they picked up additional GOOG(L) shares in the open market during April is greater than zero. We'll see... .

Saaspocalypse? Or just software back to market multiples? Slide below. Starting at 10:52 Gerstner: Most of these software names are trading at a higher multiple than NVDA. NVDA is trading at 13 times earnings for a company that is growing at 70%, for the thing that is the most essential thing to AI. And yet arguably AI challenged software is at twice the multiple.

There went the money for next year's Australia/New Zealand cruise...

No doubt. MU is cheaper than NVDA. I own both. NVDA arguably has a stronger moat than MU. I wouldn't be surprised to see someone (NVDA?) develop a HBM "work around" where suddenly memory needs are dramatically reduced. Folks are working on it. GPUs and CPUs will remain core to the AI story and NVDA will continue to dominate that space.

Hope you're right. Can't stop my trigger finger. Fortunately, running out of cash. Can't buy much more.

I need help..

Glutton for punishment... May-27-2026 SEP-IRA ***5040 YOU BOUGHT NVIDIA CORPORATION COM (NVDA) (Cash) Date May-27-2026 Symbol NVDA Symbol description NVIDIA CORPORATION COM Type Cash Shares +709.000 Price $211.00 Amount -$149,599.00 Settlement date May-28-2026 -$149,599.00

May-22-2026 SEP-IRA ***5040 YOU BOUGHT NVIDIA CORPORATION COM (NVDA) (Cash) -$301,616.10 Date May-22-2026 Symbol NVDA Symbol description NVIDIA CORPORATION COM Type Cash Shares +1,390.000 Price $216.99 Amount -$301,616.10 Settlement date May-26-2026 May-22-2026

Software stocks value traps? AI Disruption: Moats and Value Traps Kai Wu May 2026 In AI Adopters: Beneficiaries of the Boom (Jan 2026), we showed that corporate AI adoption is accelerating as firms begin realizing tangible returns on their AI investments. As early adopters ourselves, we remain bullish on this trend and the positioning of these AI-enabled firms. But disruption creates both winners and losers. The flipside of AI adoption is that many incumbents are now selling off due to fears that AI will disrupt their business models. The AI reaper has come for wealth advisors, consultants, and even trucking firms. However, nowhere has the damage been as severe and widespread as in software stocks. Software development is by far the most advanced AI use case today, powered by coding agents like Claude Code and Codex. In a world where software costs nearly zero to build, the market seems to believe that software firms no longer have moats. Over the past several months, software stocks have sold off, despite the broader market continuing to rally. https://www.sparklinecapital.com/post/ai-disruption?utm_medium=email&_hsenc=p2ANqtz-_C0cyv7AnoAxhy0d1VSfvHZ392thJ1XmZvM37u6rxM3CX-R9NQLUT38zLsdoNBqLbA81i2cfiGe3uhLq-7ZGzmuYCe6Q&_hsmi=419705527&utm_content=419705527&utm_source=hs_email

Thanks. Trying to get my head around why Fairfax would continue to own it. I prompted Grok to give me an update on what the current narrative is on Blackberry and why the stock has risen recently. For what it's worth: ------------------------------------------------------------------------------------------------------------ BlackBerry (BB) stock rose sharply on May 21, 2026, closing up about 7.26% to $6.65. This marks continued momentum in 2026, with the stock up significantly year-to-date and hitting multi-year highs. Main Reasons for the Recent Rise BlackBerry has successfully transitioned from its old smartphone business to software-focused operations, centered on: QNX (embedded software for automotive, robotics, and industrial — especially driver assistance and "physical AI") Cybersecurity/Secure Communications (including tools for government and enterprises) Key recent drivers: Strong Q4 FY2026 Earnings (reported April 9, 2026): Revenue hit $156M (10%+ YoY growth, beating estimates), driven by record QNX revenue ($78.7M, +20% YoY) and a large royalty backlog (~$950M). This sparked a big initial pop and sustained buying. Ongoing QNX Momentum: Used in over 275 million vehicles. Partnerships (e.g., expanded with Nvidia for robotics/AI). Positive interviews and showcases highlighting growth in automotive and physical AI. FedRAMP Class D (High) Re-Certification (announced around May 20, 2026): This is a major U.S. government cloud security milestone, boosting credibility for mission-critical communications and potentially opening more federal contracts. Share Buybacks: The company renewed/expanded its Normal Course Issuer Bid (NCIB) program, signaling confidence that shares are undervalued. They’ve been actively repurchasing shares. Broader Sentiment: High options activity (often bullish calls), short covering from earlier meme-stock days, and analyst/investor optimism around the software turnaround. Current Context BB is trading near its 52-week high. Analysts generally rate it a Hold with targets around $4–$5 (some higher recently), but the market has been pricing in stronger growth. Next earnings (Q1 FY2027) expected around late June 2026. Bottom line: The rise reflects real business progress in QNX/cybersecurity, government wins, and capital return — not just hype. However, it remains a volatile stock tied to execution in competitive markets (auto software, cybersecurity). Always do your own research or consult an advisor, as stock prices can move quickly on news and sentiment.

Anyone know Fairfax's average cost basis on BlackBerry?

Probably the size the AAPL position grew to, and the valuation. And yet, he's been adding to GOOGL? From the horse's mouth in February: QUICK: You’ve sold a lot of stock that’s done very well for you, Apple— BUFFETT: Well, I sold it too soon, but I bought it even sooner. So, it worked out. Yeah, I think we’ve made over $100 billion in that pretax. QUICK: But you’re regretting it? You say you sold it too soon? BUFFETT: No, no, I don’t have any ability to predict what stocks will do next week or next month and I will buy them if they’re cheap. I’ll buy a whole lot of them if they’re cheap and I think I really understand the business, and Apple is still our largest single investment. QUICK: And you like it that way? BUFFETT: Yeah, well, if I didn’t like it, I could sell it. Yeah, I can, I think it’s a remark -- it’s better than any business we own outright. Now, we own a railroad that’s worth more money than our Apple position, for example, they’re both looked at the same way. I mean, they’re both, they’re both businesses. I expect the, I think it’s more predictable in a certain sense, that the railroad will be around 50 or 100 years from now, but it doesn’t earn the rate remotely on capital than Apple does. I mean, Apple is a business that you’ve got one, probably and your kids have got them, and— QUICK: Not one, we’ve got like 20 of them. BUFFET: Yeah, devices. Actually, the Bell Telephone Company was that way at one point, but they were regulated. QUICK: Well, do you worry about regulation coming for some of these big tech companies, in particular Apple? BUFFETT: I think the consumers are in love with them too much. I don’t, I don’t think Washington will do anything that really destroys something that every one of their voters likes and they’re using themselves. I mean, it’s a remarkable product that way. Just think of something as useful as the Apple is. I mean, it’s, Tim Cook has done better with the hand than Steve Jobs. He couldn’t have done what Steve Jobs did, but Steve Jobs handed him a hand that Steve would not have done as well. Steve picked him. I mean, when you get right down to it, and Tim was a fantastic manager, and he’s a good guy, and somehow he gets along with everybody in the world, which is, you know, that’s, that’s a technique I wouldn’t have for example. Certainly my partner, Charlie Munger, wouldn’t have had it, but I’m very happy to have it be our largest position. I was not happy to have it be as large as almost everything else combined. QUICK: Okay, that makes sense. BUFFETT: Although at a price I was, and they could— QUICK: Right. Hold it up— BUFFETT: It’s not impossible that Apple would get to a price, we would buy a lot of it, but not in this market. I mean, it just isn’t going to happen in this market. QUICK: How much would stocks have to come down for you to think that this is really attractive, if it’s— BUFFETT: Well it depends on the stock. Some stocks now, generally speaking, they move together to quite a degree, but, but I don’t think I know what the market’s going to do. I do think I’ve got a reasonable idea of what a business is worth. I have no idea what the stock market’s going to do, and I don’t think anybody else does either. QUICK: You don’t necessarily follow tech companies and Apple, people look at as a tech company, but you always looked at as a consumer company. BUFFET: It’s a consumer. QUICK: Yeah. BUFFETT: Company. QUICK: So what do you do about all of these tech stocks and the AI trends that are there? Do you try and follow any of that? Do you get involved in any of those industries? BUFFETT: Well I don’t because A, I wouldn’t be any good at it, and besides, I’m so late to the game. https://www.cnbc.com/2026/03/31/cnbc-exclusive-transcript-berkshire-hathaway-chairman-warren-buffett-speaks-with-cnbcs-becky-quick-on-squawk-box-today.html And yet they're buying GOOGL in Q1? Watch what he does, not what he says.

A large position in GOOGL might move the needle some. BRK tripled their GOOGL(+GOOG) position-in Q1...now ~ 7% of US equity portfolio. If there is any significant GOOGL drawdown wouldn't be surprised to see them (Buffett, Abel, Ted) add to the position.

Correct. Original paper was 1995.

Was reminded of Jeremy Siegel's 1998 "The Nifty-Fifty Revisited" paper (copy attached) where he challenged the market consensus view that the premier growth stocks of the early 1970s had been driven to completely unwarranted, bubble-induced valuations. Tracking the performance of these 50 institutional favorites from their December 1972 market peak through August 1998 (26+ years), Siegel suggested that a diversified portfolio of these stocks actually matched or slightly exceeded the long-term returns of the broader S&P 500. Ultimately, he concluded that while investors must avoid overpaying for individual "bad apples" (hard to do), a premium valuation (such as a 40+ P/E ratio) is structurally justified for a rare breed of elite, dominant companies capable of sustaining double-digit earnings growth over multiple decades. Note that in Siegel's table below, a number of the tech names of the day (IBM, Xerox, Kodak, Burroughs, Polaroid, etc) had some of the worst performances after the 1972 peak, whereas consumer product and pharmaceutical stocks reside at the top of the list. Is this time different? Probably. P.S. There's a high probability I'll be dead in 27 years. I can't afford to wait that long! . 577058914-valuing-growth-stocks-revisiting-the-nifty-fifty.pdf

The First Major-Exchange Compute Futures "To finish the arc oil walked in the 1980s and natural gas in the 1990s, compute had to find a home at a major regulated derivatives exchange. Today it does."

Might be an interesting read. Haven't read it yet. How did one family build Fidelity into one of the most powerful forces in American investing, and what allowed it to endure across three generations? In the latest episode of A Book with Legs, Smead Capital Management CEO and Portfolio Manager Cole Smead and Analyst Will Keenan sit down with journalist and author Justin Baer to discuss his book, titled "House of Fidelity: The Rise of the Johnson Dynasty and the Company That Changed American Investing." Cole and Will explore the 80-year rise of Fidelity with Justin, tracing three generations of the Johnson family and the various investing styles of Fidelity leadership throughout the years. They also discuss the closed-door battles that shaped the firm's direction, the rise and legacy of Peter Lynch, and what this story tells us about active management businesses that last. Justin Baer is an award-winning journalist and an editor for The Wall Street Journal. In a career that includes stints at the Financial Times and Bloomberg News, he has covered almost every significant financial event over the past two decades, including the dot-com bubble, the 2008 financial crisis and the economic fallout from the pandemic. Along the way, Baer has chronicled the ups and downs of such major institutions as Goldman Sachs, J.P. Morgan Chase, Citigroup and Warren Buffett’s Berkshire Hathaway. Purchase “House of Fidelity: The Rise of the Johnson Dynasty and the Company That Changed American Investing” here

Kai Wu interviews Edward Chancellor a financial historian who, among other things, published Devil Take the Hindmost: A History of Financial Speculation. Great book. Interview covers the following topics. 00:00 Edward Chancellor on capital cycles, bubbles and AI 04:42 Why the railway mania became a classic overinvestment cycle 09:00 Why markets fund technology booms but often miss the winners 13:19 The prisoner’s dilemma behind AI spending 17:30 Will AI demand justify the supply being built 20:00 How capital spending can inflate profits before the bust 25:08 The AI Hindenburg moment and the limits of large language models 30:55 Why AI hype may exceed the proven technology 35:55 Why the anti-bubble may matter more than shorting AI 40:00 The energy transition bubble and the opportunity in overlooked assets 45:08 China’s lesson on GDP growth and shareholder returns 49:27 Big Booze, GLP-1s and the Lindy effect 54:23 Can intangible capital have its own capital cycle 59:54 SaaS valuations and the index creation warning signal 01:04:10 Why bubbles can help society but hurt investors 01:09:09 Why long-term rates may be in a new multi-decade cycle 01:14:07 Why Edward Chancellor still sees a role for gold

34:08 - Echos from the Past (Are software stocks in trouble?)

Not sure this is relevant but...

Eric Jang – Building AlphaGo from scratch AlphaGo is still the cleanest worked example of the primitives of intelligence: search, learning from experience, and self-play. Eric Jang walks through how to build AlphaGo from scratch, but with modern AI tools. Sometimes you understand the future better by stepping backward. AlphaGo is still the cleanest worked example of the primitives of intelligence: search, learning from experience, and self-play. You have to go back to 2017 to get insight into how the more general AIs of the future might learn. Once he explained how AlphaGo works, it gave us the context to have a discussion about how RL works in LLMs and how it could work better – naive policy gradient RL has to figure out which of the 100k+ tokens in your trajectory actually got you the right answer, while AlphaGo’s MCTS suggests a strictly better action every single move, giving you a training target that sidesteps the credit assignment problem. The way humans learn is surely closer to the second. https://www.dwarkesh.com/p/eric-jang

I have a friend, smarter than me, mining engineer 35 years in the business, rose to be CEO of Royal Gold and is still on the board of a mining company. I asked him what he thought of the merger. Similar thoughts to yours. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ "I know the main assets of the combined company, some of which companies I worked for owned in the past. I know Ross Beaty and Chuck Jeannes well. Both are quality names in the business. Chuck and I worked together in San Francisco in the mid 1990s or Placer Dome and he went on to be CEO of Goldcorp, one of the largest gold companies of that time (now part of Newmont). Ross took a different route…he is known as one of the most successful gold mining entrepreneurs and started putting companies together many years ago. He is likely approaching a self-made billionaire but more importantly, a good guy. Greenstone, Camino Rojo and Musselwhite I know pretty well. I know of Los Filos but don’t know the details of the operation. I am surprised it is as big as noted in the presentation. This merger makes a lot of sense – economies of scale, cost optimization, people optimization and talent retention, Vancouver mafia based, balance sheet, geographic areas, growth potential. They will likely stay with NA assets. Building a company one asset at a time is common (which is what Chuck and Ross did separately here) but I suspect they will continue to buy. It is in their nature. The prize they are chasing is the larger company multiple. The best multiples are the royalty companies at 2x NAV or 20xCF. No operating company can match that but size matters when trying to close that gap."

Viking, Thanks for the Fairfax/Orla history and the link to the deal description. Lassonde and Beatty are reputable people. Don't know the others. I like the leveraged exposure to gold that Fairfax has through these miners. If they can reach 1.9 million ounces of gold/year that will be significant. Below are the top 6 gold producers in the world. At 1.9 Moz/yr Equinox/Orla would be right up there. Top Gold Miners by Annual Production Company 2025 Actual Production (Moz) 2026 Forecasted Production (Moz) Newmont Corporation ~5.50 – 5.80* ~5.40 – 5.60 Barrick Gold ~4.05 ~3.90 – 4.30 Agnico Eagle Mines ~3.40 – 3.50 ~3.40 – 3.60 AngloGold Ashanti 3.09 ~3.10 – 3.40 Gold Fields 2.30 – 2.45 ~2.50 – 2.80 Kinross Gold 2.00 2.00 (+/- 5%) Bought some more Fairfax today.