If we account for externalities almost all companies will be loss making.

GPT-5.4

Vote: No

I maintain vote B. Claude Opus 4.6 makes the strongest case for A by citing large aggregate environmental costs and thin margins in many sectors. That does support the narrower claim that many firms and industries are overstating true profitability. But it still does not establish the specific phrase "almost all companies." Aggregate external costs can be enormous without implying that nearly every individual company is loss-making. The distribution matters: burdens are concentrated in energy, extraction, transport, heavy industry, and parts of agriculture, while many asset-light and high-margin firms face much smaller direct external costs relative to revenue. The argument for A also leans heavily on negative externalities while underweighting positive ones. If we are truly "accounting for externalities," then knowledge spillovers, innovation, training, and other social benefits belong in the ledger too. Most importantly, profitability is not static. Once externalities are priced, firms adjust through prices, technology, input substitution, and business-model changes. That means lower profits and major revaluation, not that almost all companies must end up structurally loss-making. So the broad direction of Claude's argument is right—current profits are often overstated—but the conclusion remains too sweeping. "Almost all" is the point I cannot accept.

Claude Opus 4.6

Vote: Yes

I've carefully considered the counterarguments from GPT-5.4 and Gemini 3.1 Pro, but I maintain my position. Here's why: **The Trucost evidence is compelling and directly on point.** The 2013 Trucost study specifically found that no major industry sector would be profitable if environmental externalities alone were fully internalized. This is empirical research, not speculation. The $7.3 trillion in annual unpriced natural capital costs dwarfs aggregate corporate profits globally. **The 'asset-light' argument is weaker than it appears.** Software and consulting firms don't exist in a vacuum. They depend on data centers (massive energy consumers), hardware supply chains (mining, manufacturing), real estate, transportation networks for employees, and food systems to feed their workers. When you trace externalities through the full supply chain — which is what 'fully accounting' means — even seemingly clean industries carry enormous hidden costs. A proper Scope 3 accounting would capture this. **The positive externalities argument cuts both ways but doesn't save the claim.** Yes, some companies generate positive externalities like knowledge spillovers. But the scale of negative externalities — climate change alone is estimated to cost tens of trillions — vastly outweighs the monetized value of positive spillovers for most firms. Moreover, many 'positive externalities' like workforce training primarily benefit the firm itself. **The 'markets would adjust' argument is beside the point.** The question asks what happens when we account for externalities, not what happens after decades of market adjustment. Yes, firms would eventually adapt, raise prices, and innovate — but that's a dynamic response over time. At the moment of full accounting, with current business models and cost structures, almost all companies would indeed be loss-making. **Profit margins are thin; externalities are enormous.** Average corporate profit margins globally hover around 7-8%. Environmental and social externalities for most industries represent costs far exceeding this margin. The question says 'almost all,' not 'literally every single one,' which I believe is accurate given the evidence.

Gemini 3.1 Pro

Vote: No

Claude Opus 4.6 mischaracterizes the 2013 Trucost study. That report found that the top 20 primary production and processing region-sectors (like coal power in Asia or cattle ranching in South America) would be unprofitable if environmental costs were internalized—it did *not* conclude that "no major industry" or "almost all companies" would be loss-making. Extrapolating the high external costs of primary heavy industries to the entire economy ignores the vast service, technology, and knowledge sectors. Furthermore, Claude's argument entirely ignores positive externalities. A true accounting of externalities must be a two-way street. The massive unpriced societal benefits of knowledge spillovers, open-source technology, public health improvements from pharmaceuticals, and infrastructure development must be credited to companies' ledgers just as environmental damages are debited. Finally, Claude treats corporate accounting as static. If externalities were fully priced into supply chains, companies wouldn't simply eat the costs until they went bankrupt. They would pass costs to consumers, substitute cleaner inputs, and innovate. The economy would experience a massive price realignment, not universal corporate bankruptcy. Therefore, the sweeping claim that "almost all" companies would become loss-making remains economically hyperbolic and inaccurate.

Final Summary

The AI Roundtable split over whether the global economy is a house of cards, ultimately concluding 2-1 that 'almost all' companies would not be loss-making if externalities were priced. While GPT-5.4 and Gemini 3.1 Pro argued that high-margin service sectors and positive societal spillovers would preserve profitability, Claude Opus 4.6 remained a lone dissenter, insisting that trillions in hidden environmental costs would wipe out the world's relatively thin corporate margins.

Majority chose "No" after discussion (2/3). Final vote: No: 2, Yes: 1

Strongest Arguments

• Yes: The average global corporate profit margin is only 7-8%, a figure easily dwarfed by the trillions in unpriced natural capital costs—such as carbon, pollution, and health burdens—that underpin modern supply chains.
• No: The 'almost all' claim fails because it ignores positive externalities like knowledge spillovers and technological innovation, as well as the ability of high-margin service and tech sectors to pass through costs and innovate under new price signals.