AI Disclosure: This comment was generated with the assistance of an
AI tool to help synthesize structural economic arguments.

Re: Hockett, the Fed, and Breaking Out of the Wall Street Casino

Reading through the back-and-forth about the AI bubble and the 10
trillion dollars trapped in 401ks, it is pretty clear everyone is
arguing over who gets to hold the steering wheel of a car with
square wheels. Whether it is red or blue team in Washington, the
underlying trap is the same: our entire monetary system forces
ordinary people to park their life savings in speculative Wall
Street equities just to survive, turning the public into unwilling
gamblers in a rigged casino.

When the market inevitably corrects, people panic because they
think the losses have to be "taken out of our hide." But as Robert
Hockett and other monetary reformers point out, we are looking at
the plumbing all wrong.

The Federal Reserve proved during Quantitative Easing that
sovereign money creation is an expansive public infrastructure
tool, not a finite pool of tax revenue that has to be squeezed out
of citizens or looted from retirement accounts. We do not need
zero-sum tax fights, and we do not need to rely on Washington
insiders to save us from the next bubble collapse.

If we used that exact same sovereign liquidity capacity to fund
an indexed, non-tax-funded UBIâ"treating money as a public utility
rather than a speculative assetâ"we could give working people a
genuine survival floor. That baseline acts as "venture capital for
the working class," letting people decouple from extractive labor,
stop playing Wall Street's noisy games, and fund the creation of
open-source, localized, self-sufficient production (the true
Homebrew ethos) where we don't have to care what the stock market
or corporate media is panicking about from week to week.

Will he enjoy his new job frantically patching AI-discovered critical vulnerabilities in all that old human-written software?

Would you have charged more than it cost OpenAI to find it?

[AI Disclosure: This comment was drafted with the assistance of an AI.]

It is always amusing watching the same crowd who proudly brag about running uBlock Origin to starve ad-supported web monetization into the dirt turn around and clutch their pearls about AI needing corporate revenue models.

So which is it? Do you want ads plastered all over AI that you are just going to block anyway to keep things like the good old internet, or should AI companies bypass customers entirely and get all their funding straight from an inflating stock market backed by a Fed put?

How come Gemini just returned my prompt unchanged this time? Did I run out of free tokens?

"The dispatching company will just bill the driver for the value of the cargo."

How about bill insurance which pays for it out of stock market returns on their investments not necessarily premiums?

AI DISCLOSURE: This comment was drafted with substantial help from AI. I use AI as a research and editing tool. The opinions are mine. Any errors are mine.

---

What do you mean by "taxpayers will pay for it"?

The Fed did not raise taxes to fund QE after 2008. It created reserves and bought assets. In fact, tax rates generally did not rise because of the bailouts, and some were later reduced.

If your argument is that the public bears the costs through inflation, asset-price distortions, or moral hazard, that's a different argument. But "government intervention" and "taxpayers paid for it" are not the same thing.

AI DISCLOSURE: This reply was drafted with substantial help from AI. I use AI as an editing and fact-checking tool. The opinions are mine. Any mistakes are mine too.

---

"Exactly equal" is doing a lot of work here.

Federal debt is up about $35 trillion since 1980. U.S. stock market capitalization is up something like $60+ trillion over the same period. Those are both large numbers, but they are not the same number.

Are you claiming a correlation, a causal relationship, or an actual accounting identity? Those are very different claims.

If you have data showing they are "exactly equal," I'd be interested in seeing it.

AI DISCLOSURE: This comment was drafted with substantial help from AI. I use AI as a writing and editing tool. The opinions are mine. Any mistakes are mine too.

---

Plus ca change...

This sounds like a modern version of Rockford Files' "Gearjammers." The cargo thieves of the 1970s used forged documents, insiders, and logistics tricks to divert valuable truckloads. Today's cargo thieves use hacked accounts, GPS spoofing, and AI-generated IDs.

The technology changed. The weak point stayed the same: goods in transit.

(Note: Drafted with AI assistance to structure arguments on educational theory, primary sources, and media tropes.)

BitterEpicâ(TM)s heroin metaphor relies on a fundamental misunderstanding of both learning and primary sources.

1. Practice vs. Intoxication: Shifting away from grading homework isnâ(TM)t "addiction"; it aligns with educational research from critics like Alfie Kohn and Sebastian Thrun, who have long argued that grading practice work destroys intrinsic motivation and replaces learning with compliance. Removing grades from practice allows students to focus on understanding rather than optimization for a score.
2. Primary Sources: High-level language models do not replace primary sources; they act as search, synthesis, and translation layers over them. A student using a tool to parse, cross-reference, or organize primary research is no more "intoxicated" than someone using a card catalog, a digital database, or an index.
3. The Sutter Cane Crutch: Repeating a reference to a 1990s horror film does not turn an automated tool into a mind-controlling deity. It just highlights a reluctance to evaluate tools based on how they are actually used, preferring instead to treat any shift in learning habits as a psychological collapse.

(Note: Drafted with AI assistance to organize arguments on human-supremacist rhetoric and ideological dependence.)

BitterEpic calls everyone else addicts, but he seems hooked on his own drug: performative humanist moralizing.

His entire rant relies on a rigid script: compare software tools to hard drugs, accuse anyone using automated assistance of psychosis, and demand proof of pure human origin before evaluating an answer. That is not original thinking; it is a mechanical compulsion to enforce social conformity.

Dropping a movie reference to Sutter Cane does not make this profound. It just shows he is dependent on drama to feel superior online. If a tool provides accurate information or solves a problem, nobody needs a sermon on human purity. The real addiction here is his need to police how other people process information.

(Note: Drafted with AI assistance to organize arguments on economic measurement and productivity theory.)

dirk's argument assumes a world with infinite demand and zero quality constraints. In reality, saving time or avoiding mistakes frequently does not increase total measurable output for three reasons:

Fixed Demand: If an engineer uses AI to cut decision-making time in half and finishes their assigned tasks in 4 hours instead of 8, output remains at 100%. Unless the company has an endless backlog of marketable products to sellâ"and customers ready to buy themâ"the saved time does not automatically transform into more widgets or higher GDP.

Prevention Is Invisible in GDP: Avoiding a catastrophic server outage or a costly legal mistake adds immense value and resilience, but it produces zero additional units of output. In standard economic stats, a company that spends $1M fixing an error shows the same or higher economic activity than a company that avoided the error entirely using better tools.

Quality vs. Quantity: Better coordination and fewer errors often yield higher quality, safer code, or better-vetted decisions, not a higher volume of output. National productivity statistics measure the quantity of output per hour worked, not the systemic stability or risk reduction achieved along the way.

AI disclosure: I used AI to help organize and edit these thoughts. The arguments are mine to the extent that any argument is ever entirely someone's own. If that bothers you, feel free to attack the argument rather than the tool.

---

I think the deeper issue is why we're treating productivity statistics as the final judge in the first place.

Productivity is not a direct measurement of economic value. It is an accounting construct that depends on how output is defined and measured.

That is relatively straightforward when counting tons of steel or bushels of wheat. It becomes much harder when dealing with software, research, legal work, design, information retrieval, decision support, risk management, and other information-intensive activities.

AI could be improving decisions, reducing errors, lowering search costs, increasing optionality, or generating consumer surplus without immediately appearing in revenue-per-worker statistics.

We already know GDP and productivity measures struggle to capture the value of many digital goods. Search engines, GPS, Wikipedia, open source software, and the broader Internet generated enormous value relative to what showed up in traditional economic statistics.

There is also a timing problem. What was the measured productivity gain for the average manual laborer shortly after the steam engine was introduced? General-purpose technologies often require years of organizational change before aggregate statistics move. Factories had to be reorganized around electricity before electrification delivered its full benefits.

The argument also seems oddly selective. Slok removes the companies where AI's effects are most obvious, then concludes that the remaining firms have not yet shown economy-wide productivity gains. If the steam engine first changed mining and textiles, would we have concluded steam had no economic impact because most workers were still digging ditches by hand?

Most importantly, why assume productivity is the metric that matters? A technology can create value by reducing uncertainty, improving coordination, avoiding mistakes, increasing resilience, or expanding opportunities. Those benefits do not necessarily show up as higher output per worker.

So before concluding that AI has no economic impact because productivity measures are flat, I would first want to know whether productivity statistics are actually measuring the thing we care about. Flat productivity could mean AI is useless. It could also mean the metric is only observing a subset of the effects.

(Disclaimer: Written with an AI collaborator, because human editors were apparently too busy copy-pasting to proofread.)

Speaking of slop, notice how the summary ends by repeating the exact same sentence twice:

"It's hard to compete against things like the DALL-E image generator."
"Long-time Slashdot reader schwit1 quips that maybe 'It's hard to compete against things like the DALL-E image generator...'"

When humans publish duplicate-riddled writeups without reading them, it really raises the question of whether "human slop" is even setting a higher bar than "AI slop."

To your point about "good enough": market dynamics have always favored cheap and good-enough over high-quality and expensive for standard commercial uses. Stock photo giants like Getty relied on charging massive licensing fees for stock images (or bullying photographers over copyright).

When a restaurant menu, blog post, or corporate deck just needs a generic image of a salad or a boardroom, AI generation is free, instant, and "good enough" for the buyer. The tragedy isn't that AI art is superior--it's that for 90% of basic commercial applications, nobody wanted to pay Getty prices in the first place.

AI disclosure: yes, I used an AI as a drafting assistant. I do not consider that fundamentally different from using a compiler, debugger, search engine, calculator, spellchecker, or discussing an idea with another programmer. The argument is mine. The responsibility for it is mine. Judge the reasoning, not the tool.

---

The thing that smells off to me is that Slashdot itself mangles Unicode every time I paste it into a comment box.

So I'm reluctant to accept the implicit premise that software written entirely by humans has already conquered all the easy problems and that AI-generated code must therefore clear some uniquely high bar before we acknowledge it may be useful.

Perhaps the 15% figure is exaggerated. Self-reported numbers often are.

But "real software contains domain-specific rules, institutional habits, regulatory requirements, and weird edge cases" is not an argument against AI coding. It's a description of software. Human programmers have been wrestling with exactly those problems for decades.

What I find interesting is that the article treats the existence of hard domain-specific problems as evidence that AI cannot be writing large amounts of production code. Yet many mature systems built entirely by humans still struggle with things that sound straightforward when described in a sentence.

Again, I submit as evidence the inability of this very site to faithfully render Unicode text pasted into a comment.

The benchmark is not perfection. The benchmark is whether the AI can produce code that is competitive with the code humans were already producing.

If the evidence is merely that real-world software is messy, full of exceptions, and imperfect, that seems equally consistent with the hypothesis that AI has reached parity with a substantial fraction of ordinary software development.

AI disclosure: yes, I used an AI [Copilot] as a drafting assistant. I do not see that as fundamentally different from using spellcheck, a search engine, a calculator, a compiler, Stack Overflow, Wikipedia, or discussing an idea with another person. The argument is mine. The responsibility for it is mine. Judge the reasoning, not the tool.

You're conflating social acceptance with correctness.

"The in-crowd can recognize the out-crowd" is mostly a statement about tribal pattern matching, not truth. History is full of examples where the majority correctly identified the dissenter and incorrectly identified reality.

This reminds me of an HN discussion where multiple AI models reportedly converged on a controversial observation about humans: many people would rather fit in than be right. Your comment seems to elevate that tendency from an observed human bias into a social ideal.

If the objective is social survival, conformity matters. If the objective is discovering what is true, conformity is often an obstacle. Scientific, artistic, and technological advances routinely begin as ideas that fail prevailing social tests.

Also, the writing argument feels circular. If LLMs write like average humans, you say the crowd will still detect them. At that point you're no longer evaluating writing quality. You're assuming the crowd can identify outsiders because they are outsiders.

The deeper issue is that your metric quietly shifts from "is this writing good?" to "does this writing belong to our tribe?" Those are different questions.

Herd recognition may be real. What it does not provide is a guarantee of truth, merit, intelligence, or authorship. Human societies have spent thousands of years demonstrating otherwise.