The origins of Automatically Programmed Tools (APT the precursor of g-code) is a fascinating read [1] about the early intentions of -- its a poem forseeing LLM & CAD:
(From THE NEW YORKER) Cambridge, Mass., Feb. Z5-The Air Force announced today that it has a machine that can receive instructions in English, figure out how to make whatever is wanted, and teach other machines how to make it. An Air Force general said it will enable the United States to "build a war machine that nobody would want to tackle. " Today it made an ashtray [2]. -- San Francisco Chronicle, March 28, 1959
That ashtray was teh 1st CNC'd object.
Noble [3] speaks about the political angle that was an underpinning motivation
there is a parallel between managing context windows and hard real-time system engineering.
A context window is a fixed-size memory region. It is allocated once, at conversation start, and cannot grow. Every token consumed — prompt, response, digression — advances a pointer through this region. There is no garbage collector. There is no virtual memory. When the space is exhausted, the system does not degrade gracefully: it faults.
This is not metaphor by loose resemblance. The structural constraints are isomorphic:
No dynamic allocation. In a hard realtime system, malloc() at runtime is forbidden — it fragments the heap and destroys predictability. In a conversation, raising an orthogonal topic mid-task is dynamic allocation. It fragments the semantic space. The transformer's attention mechanism must now maintain coherence across non-contiguous blocks of meaning, precisely analogous to cache misses over scattered memory.
No recursion. Recursion risks stack overflow and makes WCET analysis intractable. In a conversation, recursion is re-derivation: returning to re-explain, re-justify, or re-negotiate decisions already made. Each re-entry consumes tokens to reconstruct state that was already resolved. In realtime systems, loops are unrolled at compile time. In LLM work, dependencies should be resolved before the main execution phase.
Linear allocation only. The correct strategy in both domains is the bump allocator: advance monotonically through the available region. Never backtrack. Never interleave. The "brainstorm" pattern — a focused, single-pass traversal of a problem space — works precisely because it is a linear allocation discipline imposed on a conversation.
yeah, so the turn in EU towards renewable energy is driving fwd the business of earthen construction. our core (validated) product is printing earthen acoustic barriers at ~4-5m3/hr. panels from loam are a great alternative to gypsum; due to the hygrothermic characteristics of earth the moisture content is stabilised (constant in a ~50-55% bandwidth) which is a massive advantage in view of traditional materials. and fully circular. I'm a developer of pythonocc and tesseract-nanobind, and take pleasure in augmenting my thinking with a dash of ai.
A huge share of the gypsum used in drywall is *synthetic gypsum* — a byproduct of flue-gas desulfurization (FGD) at coal-fired power plants. When SO₂ is scrubbed from exhaust using limestone, the reaction produces calcium sulfate dihydrate, chemically identical to mined gypsum. In the US, FGD gypsum has accounted for roughly half of all gypsum consumed by the wallboard industry at its peak.
The "cheap, uniform, and free of defects" story is partly a story about coal. The drywall industry scaled on the back of an abundant, nearly free waste stream from the energy sector. It's a classic example of industrial symbiosis — one industry's pollution abatement becomes another's feedstock.
And it cuts the other way now: as coal plants shut down across Europe and North America, synthetic gypsum supply is shrinking. The drywall industry is facing a real raw material squeeze, with manufacturers having to shift back toward mined gypsum or find alternative sources. There's ongoing work on using phosphogypsum (from fertilizer production) but that comes with its own radioactivity concerns.
For someone in your position this is particularly relevant — the "wonder" of drywall is entangled with the fossil fuel economy in a way that makes earth-based construction methods look increasingly attractive as that supply chain unwinds.
(From THE NEW YORKER) Cambridge, Mass., Feb. Z5-The Air Force announced today that it has a machine that can receive instructions in English, figure out how to make whatever is wanted, and teach other machines how to make it. An Air Force general said it will enable the United States to "build a war machine that nobody would want to tackle. " Today it made an ashtray [2]. -- San Francisco Chronicle, March 28, 1959
That ashtray was teh 1st CNC'd object. Noble [3] speaks about the political angle that was an underpinning motivation
[1] http://portal.acm.org/citation.cfm?doid=960118.808374
[2] https://mitmuseum.mit.edu/collections/object/2007.037.001
[3] forces of production - a social history of industrial automation (Noble, mit press)