I am not against LLMs. They are excellent for some things. But I am deeply worried about today's deep imbalance. The following is a conversation snippet with Claude Opus 4.8 on the matter.. me: Hyperscalers have a self-interest in pushing LLM for everything to make the demand seem more real. Unfortunately it also drives up and up the operating costs for everyone including themselves. 4:25 PM Claude responded: Yes — and you've put your finger on the part that makes it a trap rather than just a strategy: the move that manufactures the demand signal also inflates the c… Yes — and you've put your finger on the part that makes it a trap rather than just a strategy: the move that manufactures the demand signal also inflates the cost base it's supposed to justify, including their own. It's self-consuming. The mechanism is worth tracing because it's genuinely perverse. Pushing LLM-for-everything serves the demand narrative in two ways at once: it raises measured token consumption (so usage charts go up and to the right, which is the number investors read as demand), and it discourages the question of whether a cheaper deterministic component would have done the job. Every task reframed as an LLM task is a task that now shows up as AI demand and consumes inference capacity. So the incentive is to route work through the expensive stochastic path even where a function call, a query, or a bit of GOFAI would be cheaper, more reliable, and more appropriate — because the inappropriate routing is what makes the demand look real. The misallocation isn't a side effect; it's the product. And the cost dynamic you're naming is the bite. Inference is not free and doesn't amortize like training — it's a recurring per-use cost in compute and energy, every single call. So "LLM for everything" means everyone's unit economics carry the weight of running the most expensive available primitive on tasks that didn't need it. That raises the operating cost floor across the whole stack — for the customers building on it, and for the hyperscalers themselves, who are running the data centers and eating the power bills. They've inflated the demand figure by inflating the cost of serving it. The signal and the burden are the same act. There's a further twist that sharpens your winter worry. The inflated-demand strategy raises a false floor under usage — usage that exists because it was pushed there, not because it's the right tool. That usage is the most fragile in a correction. The moment cost discipline arrives — a downturn, a margin squeeze, a CFO asking why the summarization job costs 50x what a templated approach would — the inappropriately-routed work is the first to be pulled back to cheaper primitives. So a meaningful slice of the demand that's holding up the valuations is exactly the slice that evaporates under the first real cost scrutiny. The manufactured demand is structurally the least durable demand, which means the gap between apparent and real demand doesn't just exist — it's primed to reveal itself suddenly, the instant the incentive flips from "show growth" to "show margin." And it puts the hyperscalers in a genuine bind, not just a hypocrisy. They can't easily stop pushing LLM-for-everything, because the demand narrative depends on it and the valuations depend on the narrative. But continuing it raises their own operating costs and builds the false floor higher, which makes the eventual correction sharper. They're committed to a strategy that worsens the thing they most need to avoid — a sudden, legible collapse in real demand — because the alternative, letting measured usage fall to its appropriate level now, would puncture the narrative immediately. So they keep inflating, knowing it raises the fall. That's the same structure as the capex arms race: individually compelled, collectively destabilizing, and worse the longer it runs. The sane-engineering path we just discussed is, among other things, the cost-discipline response to exactly this — route each task to the cheapest primitive that meets the requirement, use the LLM only where its strengths are real. Which is one more reason the hyperscalers' interest runs against it: the right engineering is deflationary to the demand figure. The thing that's good for everyone's operating costs is bad for the narrative. That tension is, I think, the cleanest single statement of the imbalance you've been circling this whole conversation.

Many think the agorist cannot care deeply and universally. They believe so deeply in Scarcity that they think only taking from those that have by force to give to those that have less shows caring. They cannot comprehend Abundance or how it grows when people are free to voluntarily act together or separate and trade with one another. They don't believe in Abundance. Who can blame them when so much is stolen by the deep clinging to Scarcity. It is believed in so deeply that it is created even where there is actual Abundance!

Government wants to meddle in EVERYTHING. Chart compares U.S. and PRC AI model performance over time, highlighting Elo scores and increasing trends. U.S. to Evaluate Upcoming Models The U.S. government said it will evaluate cutting-edge models before they’re available to the public, a sharp reversal of the White House’s earlier hands-off policy. What’s new: The National Institute of Standards and Technology (NIST), an office of the U.S. Department of Commerce, announced that a new multi-agency task force will assess national-security risks posed by AI models prior to their deployment. Leading U.S. AI companies agreed to submit models for evaluation prior to release. In addition, the White House is considering an executive order that would require AI models to gain approval before they can be deployed. How it works: NIST said the tests will focus on demonstrable risks to cybersecurity, biosecurity, and chemical weapons. The administration did not disclose details of its agreements with AI companies or any controls it expects to impose on models in light of test results.

I so hate the government. Another small addition to my hatred. I went to DMV to transfer my license from another state to here. Birth certificate in hand, affidattiv from best friend and long time companion whose house I live in and pay half of mortgage in hand. SSA-1099 proving I am at this address in their records in hand. Fidium internet order in my name and to my address in hand. Not good enough. Not enough for them to admit I live where I live. Not enough for "Real" ID. So I get a unreal NH DL instead. Which guess what? Is mailed to address I insist I live at. Government crawls up all our asses in every way knowing everything about us. Then when it comes to its own official stamp upon your existence it pretends it knows nothing and demands that you prove what it already knows! This is ABUSE. I wouldn't care except they may or may not allow me to fly or to get a passport without "Real" ID. Or vote if I should want to make myself ill in that manner. As a matter of apparent fact if the SAVE Act goes through they won't even take this "Real" ID as proof of citizenship so you can vote!