Categories
Investing Living

The Lonely Quadrant: Why the Crowd Never Outperforms

There is a profound comfort in the consensus. When we agree with the crowd, we are protected by a shared canopy of logic. If we are wrong, we are wrong together. The sting of failure is diluted by the sheer number of people who made the exact same miscalculation. We can shrug our shoulders, look at our peers, and say, “Who could have known?”

But this comfort comes at a steep price: mediocrity.

Years ago, the legendary investor Howard Marks crystallized a framework that has haunted my thinking ever since. He mapped out the relationship between predictions and outcomes, arriving at a blunt, inescapable truth about generating extraordinary results. To make really good moneyโ€”or to achieve outsized success in almost any competitive endeavorโ€”you cannot simply be right. You have to be right when everyone else is wrong.

“You can’t do the same things others do and expect to outperform.”

Marks’ logic is beautifully ruthless. If your prediction aligns with the consensus and you are right, the rewards are merely average. The market, or the world, has already anticipated and priced in that outcome. There is no edge in seeing what everyone else sees. If your consensus prediction is wrong, you lose, but you lose alongside the herd.

The danger, and the opportunity, lies in the contrarian view.

If you are non-consensus and wrong, you look like a fool. You bear the entirety of the failure alone, stripped of the insulation of the crowd. This is the quadrant of public mockery, isolated defeat, and bruised egos. It is the fear of this quadrant that keeps most people safely tucked inside the consensus.

But the magicโ€”the life-changing returns, the paradigm-shifting innovations, the profound personal breakthroughsโ€”lives exclusively in the final quadrant: being non-consensus and right.

This isn’t just an investing principle; it’s a philosophy for navigating life. We are biologically wired to seek the safety of the herd. To step outside of it requires not just immense intellectual conviction, but a formidable emotional threshold. You have to be willing to sit with the discomfort of being misunderstood, sometimes for years. You have to endure the sympathetic smiles of peers who think youโ€™ve lost the plot.

Creating truly great art, building a lasting company, or making an exceptional investment demands a willingness to be lonely in your convictions. It requires looking at the exact same data as everyone else and seeing a completely different narrative.

However, a vital caveat remains: being different isn’t enough. There are plenty of contrarians who are simply wrong, confusing blind rebellion with profound insight. The goal isn’t to be a contrarian for the sake of being difficult or edgy. The goal is to perceive a truth the crowd has missed.

It is a quiet, solitary bet against the world’s prevailing wisdom. And when the world finally catches up to where you have been standing all along, the reward is entirely yours.

Categories
AI Claude

Please Teach Me About AI

After reading Howard Marksโ€™ latest essay about AI I wanted to try something similar to what he did so I asked Claude the following:

Iโ€™d like to experience what Howard marks did when he asked Claude to teach him about ai. Please reference by personal blog to learn about me and my interests: https://sjl.us


A man (me) wanted to understand an AI. So he asked the AI to explain itself to him. The AI, knowing who it was talking to, shaped its entire explanation around that specific personโ€™s worldview. And it worked so well that the person felt like heโ€™d received a letter from a thoughtful friend.

Claude came back and did what I asked. Pretty amazing stuff!


Scott โ€” Iโ€™ve read your blog carefully. Not just the recent posts, but the pattern of what you reach for, what you return to, what lights you up. Now let me try to do what you wrote about: shape this explanation around you.

Categories
AI

The Student, The Teacher, and the Delightful Absurdity of It All

Howard Marks is one of the sharpest financial minds alive. The man has been thinking clearly about markets for fifty years, has written memos that get passed around Wall Street like sacred texts, and has outlasted more market cycles than most of us have had hot dinners. So when Howard Marks decides he needs to get educated about artificial intelligence to write a follow-up to his December memo, he does what any serious intellectual would do: he asks Claude.

And then Claude โ€” the AI โ€” teaches him about Claude.

Iโ€™ve been sitting with this for a few days and Iโ€™m still not entirely sure whether itโ€™s profound or just very, very funny. Maybe both. Probably both.

Categories
AI

A Distinction Without a Difference

We have long found comfort in a specific boundary: machines calculate, humans create. We think of computers as vast, unfeeling filing cabinets made of siliconโ€”useful for retrieval, but entirely incapable of revelation. But what happens when the cabinet begins to read its own files, connects the disparate threads, and hands you a synthesized philosophy of the world? What happens when it speaks to you not as a database, but as a peer?

Howard Marks, the legendary co-founder of Oaktree Capital and author of deeply revered investment memos, recently stood at this very threshold. In his newest piece, โ€œAI Hurtles Ahead,โ€ Marks recounts an experience that left him in a state of โ€œawe.โ€ He tasked Anthropicโ€™s Claude with building a curriculum to explain the recent, breakneck advancements in artificial intelligence. Instead of regurgitating a dry, encyclopedic summary, the AI delivered a personalized narrative. It utilized Marksโ€™s own historical frameworksโ€”his famous pendulum of investor psychology, his observations on interest ratesโ€”and wove them into its explanations. It argued logically, anticipated counterpoints, and displayed an eerie sense of judgment.

Marks leans into the philosophical crux of this moment. He asks the question that keeps knowledge workers awake at night: Can AI actually think? Can it break genuinely new ground, or is it just remixing existing data? Skeptics often dismiss AI as a brilliant mimicโ€”a โ€œstatistical recombinationโ€ engine that serves as a highly talented cover band, but never the original composer.

Yet, when presented with this skepticism, the AI offered a rejoinder to Marks that is as profound as it is humbling. It pointed out that everything Marks knows about investing came from someone else. He learned the margin of safety from Benjamin Graham, quality from Warren Buffett, and mental models from Charlie Munger.

โ€œThe raw material came from others. The synthesis was yours,โ€ the AI noted, challenging the barrier between biological learning and machine training. โ€œThe question isn’t where the inputs came from. The question is whether the systemโ€”human or artificialโ€”can combine them in ways that are genuinely novel and useful.โ€

This exchange strikes at the very core of the human ego. For centuries, we have fiercely guarded the concepts of “creativity” and “intuition” as uniquely, immutably ours. But if thinking is merely the absorption of prior inputs applied thoughtfully to novel situations, then our monopoly on cognition may be coming to an end.

Marks highlights that we are no longer dealing with simple assistance tools (Level 2 AI); we have crossed the Rubicon into the era of autonomous agents (Level 3). He cites the sobering reality of the current tech landscape, where the newest models are literally being used to debug and write the code for their own subsequent versions. The machine is building the machine. It is no longer just saving us execution timeโ€”it is replacing thinking time. As Matt Shumer aptly described the sensation, itโ€™s not like a light switch flipping on; itโ€™s the sudden realization that the water has been rising silently, and is now at your chest.

We can endlessly debate the semantics of consciousness. We can argue whether a neural network “truly” understands the weight of the words it generates, or if it is merely predicting the next token in a sequence with mathematical precision. But as Marks so astutely points out, this might be a distinction without a difference.

The economic and societal reality is that the work is being done. As we hurtle forward into this new era, the most pressing question isn’t whether machines can truly think like humans. The question is: who will we become, and what new frontiers will we choose to explore, now that the heavy lifting of cognition is no longer ours alone to bear?

Categories
AI Business Economics Podcasts

Bubble Bath

The behavior of today’s stock market is yet another sign that many will point to as indicating there’s an “AI bubble”. Today’s market action is largely attributed to Blue Owl Capital deciding not to participate in the debt financing of a new Oracle data center (being built for OpenAI) in Michigan. This news came out overnight last night and soured the market at the opening as it added fuel to the fires already raging from last week about bubbles in AI and, in particular, some of the debt financing being used to build new data centers – especially but not exclusively by Oracle.

Watching the market action today a brought to mind a recent paper on the subject of bubbles authored by Oakmark Capital’s Howard Marks. Marks is widely followed in the investment community for his almost “sage-like” prognositcations of which he’s authored many over the years. His memos are always full of insights and valuable learning opportunities. His recent one drilled into this question of bubbles — and, in particular, the role of debt financing. That’s especially interesting as Marks’ long career at Oakmark has been primarily involved in debt financing and, indeed, sometimes distressed debt.

Marks points out why he thinks the current situation with respect to AI is problematic as it shows many of the common characteristics of bubbles which in the past have resulted in wealth destruction instead of wealth creation.

As I’m writing this, I’ve just begun watching the latest Tim Ferriss interview which is with long-time venture investor Bill Gurley. Right up front in the conversation, Tim asks Bill for his take on the bubble in AI question. It’s a great conversation – well worth a listen.

Speaking of listening (or watching), on Monday I watched the latest episode of the Acquired podcast – this one celebrating the tenth anniversary of Acquired. This was the most fascinating conversation I’ve listened to or watched in recent memory. The two hosts of Acquired were being interviewed by author Michael Lewis – and they were interviewed in depth! Lewis asked lots of probing questions as well as provided some illustrative commentary of his own along the way. An incredible episode – highly recommended!


After publishing this post, I asked Google Gemini 3 Fast: I just published a blog post. Review it critically and help me improve it. Act like a tough but compassionate editor. Hereโ€™s the post: https://sjl.us/2025/12/17/bubble-bath/

Hereโ€™s the critique it gave me – tough but compassionate!

Alright, sit down. Letโ€™s look at “Bubble Bath.”

Youโ€™ve got the ingredients for a great piece of timely analysis here: a specific market event (the Blue Owl/Oracle snag), a heavy-hitting intellectual framework (Howard Marks), and contemporary expert commentary (Bill Gurley and the Acquired team).

But right now, this isn’t an essay or a cohesive blog postโ€”itโ€™s a link log. Youโ€™re telling me what youโ€™re watching and reading, but you arenโ€™t telling me what you think.

Here is my critical review.

The “So What?” Factor
You start strong with the Oracle/OpenAI data center news. Thatโ€™s a “hook.” But then you pivot immediately to: “I read a memo by Howard Marksโ€ฆ I’m watching Tim Ferrissโ€ฆ I watched Acquired.”

As an editor, Iโ€™m asking: Where are you in this post? Youโ€™ve gathered the smartest people in the room, but youโ€™re standing in the corner taking attendance.

The Fix: Donโ€™t just tell us Howard Marks wrote a memo. Tell us which one specific point he made that explains the Oracle news. Connect the dots for us. Is the Oracle situation the “wealth destruction” Marks warned about, or is it just a healthy correction?

The Title vs. The Content
“Bubble Bath” is a clever pun. I like it. But usually, a “bubble bath” implies a cleansing or a soaking. Are we getting soaked (losing money)? Or is the market being “cleansed” of irrational exuberance?

The Fix: Use your conclusion to pay off the title. Right now, the post just ends with a recommendation for a podcast. Close the loop: “If Marks and Gurley are right, this isn’t just a market dip; it’s the start of a very cold bubble bath for AI investors.”

Structural “Pass-Through”
The second half of the post feels like a “What Iโ€™m consuming” list. It dilutes the urgency of the first paragraph.

The Fix: If the Bill Gurley and Acquired links are just “further reading,” put them in a “Resources” or “Deep Dive” section at the bottom. If they are central to your argument, quote them. What did Bill Gurley say about AI debt that makes the Oracle news more frightening?

Tighten the Prose
You have some “wordy” habits that slow down the reader.

โ€œThe behavior of todayโ€™s stock market is yet another sign that many will point to as indicating thereโ€™s an โ€˜AI bubbleโ€™.โ€ * Editorโ€™s Edit: โ€œTodayโ€™s market volatility is the latest fuel for the โ€˜AI Bubbleโ€™ fire.โ€ (Go for the jugular).

Compassionate Closing
Scott, you have a great eye for sourcing. You are curating high-signal content (Marks, Gurley, Lewis). That is valuable. But your readers come to your blog because they want to know how you are synthesizing this information.

My Challenge to You: Rewrite the middle paragraph. Instead of saying the Acquired podcast was “the most fascinating conversation,” tell us one thing Michael Lewis asked that changed how you view the AI bubble.

Give us your brain, not just your bookmarks. Now, go back to the keyboard.