Pages

Monday, May 11, 2026

GE in the DOW

 

Claude finished the response

You said: Given trends of the last few years, when might you estimate the NASDAC will catch the Dow in absolute terms.

Given trends of the last few years, when might you estimate the NASDAC will catch the Dow in absolute terms.

4:54 AM

Claude responded: Great, I have the current data I need.

Searched the web

Great, I have the current data I need. Let me now run a quick analysis.

Current levels (as of ~May 8–9, 2026):

So the gap is roughly 23,400 points. Here's a back-of-the-envelope projection:


The Gap in Context

The two indices measure very different things — the Dow is price-weighted with just 30 stocks, while the NASDAQ Composite tracks 3,000+ stocks — so "catching up" in absolute point terms is a genuine but somewhat quirky milestone. That said, let's look at the math.

Recent growth rates (annualized, rough):

  • Over the 18 months ending mid-July 2025, the NASDAQ returned ~39% versus the Dow's ~19%, implying a ~13% annualized NASDAQ advantage over that stretch. statmuse
  • In Q1 2026, the NASDAQ actually underperformed, falling 7.11% vs. the Dow's 3.58% drop, showing the tech-heavy index can lag in risk-off periods. Ad Hoc News

Over longer horizons (5–10 years), the NASDAQ has historically grown roughly 5–8 percentage points per year faster than the Dow.


The Projection

Using current approximate values (~26,250 vs. ~49,600) and assuming:

NASDAQ annual growthDow annual growthEst. crossover
15%8%~2031
12%7%~2033–2034
10%6%~2037–2038
12%10%~2040+

A central estimate of around 2032–2035 seems reasonable if recent trends (NASDAQ outperforming Dow by ~5–8% annually) continue. The NASDAQ would need to roughly double relative to the Dow from where it is today.


Key caveats:

  • The Dow's price-weighted construction means a single high-priced stock addition/removal can shift it significantly — it's a somewhat arbitrary target.
  • Tech sector valuations are stretched; a prolonged correction (like 2000–2002) could push the crossover date back by a decade.
  • Conversely, if AI continues driving mega-cap tech growth at the pace of 2023–2025, 2030 is plausible.

So: best estimate is somewhere in the early-to-mid 2030s, with a wide range of uncertainty on either side.

You said: The removal a few years ago of GE from the Dow was almost Buddhist in its demonstration that nothing is forever.

The removal a few years ago of GE from the Dow was almost Buddhist in its demonstration that nothing is forever.

4:59 AM

Claude responded: That's a wonderfully apt observation.

That's a wonderfully apt observation. GE's arc is really one of the most dramatic in American corporate history — it was a founding component of the Dow in 1896, dropped, readmitted, and then finally removed in 2018 after 111 years of nearly continuous membership. At its peak around 2000 it was the most valuable company in the world.

The fall was almost Greek in its tragedy as much as Buddhist in its impermanence. A company that embodied 20th century American industrial dominance — jet engines, nuclear power, financial services, media — became a cautionary tale about conglomerate overreach, financial engineering, and the dangers of GE Capital's leverage during the 2008 crisis. Jack Welch was celebrated as the greatest manager of his generation; within a decade of his retirement the edifice was crumbling.

What makes the Dow removal particularly poignant is the mechanism of it. Because the Dow is price-weighted, GE's collapsing share price was actively dragging the index down and distorting it — it had to go not just because it had faded, but because its very presence had become a burden. There's something almost ruthless and clarifying about that.

The Buddhist angle you're pointing to cuts deeper too when you look at the current Dow. Several of today's components — and certainly several of the largest NASDAQ names — will almost certainly not be there in 50 years. The index is really a living snapshot of what humans currently believe matters, which is always temporary. The composition has shifted from railroads to steelmakers to industrials to financials to tech, each transition feeling permanent at the time.

GE was the last thread connecting the modern Dow to the Gilded Age. When it left, something genuinely historical quietly ended.

You said: Conglomeration is useful for stability of results, financing and occasional cross fertilization, but a huge problem for informed management/

Conglomeration is useful for stability of results, financing and occasional cross fertilization, but a huge problem for informed management/

5:04 AM

Claude responded: Yes, and this tension sits at the heart of why the conglomerate model has repeatedly risen and fallen in waves.

Yes, and this tension sits at the heart of why the conglomerate model has repeatedly risen and fallen in waves.

The financing and stability arguments are real — internal capital markets can allocate resources across divisions more efficiently than external markets in certain conditions, and a diversified earnings stream genuinely does smooth access to credit. The cross-fertilization case is occasionally brilliant: Bell Labs being the canonical example, where a regulated monopoly's cash flows funded some of the most consequential basic research in history — transistors, information theory, lasers.

But the management problem is brutal and arguably insurmountable beyond a certain scale. There's a fundamental epistemological issue: no management team can be genuinely expert across jet engines, medical imaging, television networks, and subprime mortgages simultaneously. What fills that knowledge gap is financial abstraction — everything becomes return on capital, spreadsheet metrics, quarterly targets. You end up managing the measurements of a business rather than the business itself.

Welch was perhaps the perfect illustration of this paradox. He was a genuinely brilliant manager of managers — expert at creating accountability systems, culling underperformers, setting stretch targets. But that meta-management genius also masked how much domain knowledge was being lost at the top. His successor Immelt inherited a machine optimized for hitting numbers, not for deep understanding of what actually created value in each division.

There's also an incentive problem that compounds over time. Divisional managers learn to game corporate metrics. Capital gets allocated to whoever tells the best story to headquarters rather than whoever has the best actual opportunity. The corporate center becomes simultaneously overburdened and underinformed.

Private equity has essentially built an entire industry on the insight that focused, knowledgeable ownership unlocks value that diversified conglomerates systematically destroy.

You said: From my perspective, GE didn't understand that in insurance, especially reinsurance, it is long term almost banking relationships, and rapid growth is therefor…

From my perspective, GE didn't understand that in insurance, especially reinsurance, it is long term almost banking relationships, and rapid growth is therefore dangerous.

5:07 AM

Claude responded: That's a sharp and specific diagnosis — and you're almost certainly identifying something that generic financial management would be nearly blind to.

That's a sharp and specific diagnosis — and you're almost certainly identifying something that generic financial management would be nearly blind to.

Reinsurance in particular is a business where the liabilities are extraordinarily long-tailed and the underwriting relationships are built on decades of trust, reciprocity, and accumulated loss experience. A reinsurer's reputation for paying claims cleanly and maintaining capacity through hard markets is the actual product — it's not separable from the business the way a manufactured good is. You can't grow that quickly without either buying relationships you don't fully understand or accepting risks that experienced players have quietly walked away from.

GE Capital's reinsurance operation, which eventually became a catastrophic liability, grew aggressively through the 1990s into long-tail lines — particularly workers' compensation and medical malpractice run-off — that experienced underwriters were already retreating from. The pricing signals were there in the market. But a conglomerate parent focused on earnings accretion wouldn't necessarily read those signals the way a specialist would. They saw an apparently profitable, capital-light business generating float. The underwriting culture that would have said "this risk is mispriced and we'll know it in fifteen years" was either absent or overruled.

Your banking relationship analogy is exactly right — the float in reinsurance is structurally similar to deposits, and rapid growth of deposits in banking is almost always a warning sign, because it usually means you're pricing too aggressively or accepting credits others have declined. Continental Illinois. Later, certain mortgage books. The pattern repeats.

It suggests that some industries have an almost constitutional resistance to being owned by generalists.


No comments: