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.
yes, it does and its realtime.
personally, I use typst locally, but
the online editor utilises WASM, so if I'm not mistaken, the rendering is real-time and handled by the front-end.
no the depth of graphics API's in latex is really something, and an area that is underdeveloped in typst. it'll take a considerable time for typst to be on par.
no, I pointed towards the joy of writing in a proper IDE.
but to your point: overleaf is a key enabler of latex and its cool to see typst offers a similar route
Robotic wire cutting for architectural purposes has been a relevant innovation.
That process is an order of magnitude more effective: you're cutting with a wire rather then a chipping a way with a milling bit. With a wire you're cutting 2 faces at a time, which is an important advantage over milling.
These diamond wires are also used for quarrying the stone.
The BRG Group at ETH Zürich has delivered some stunning project exploring a modern take on stereotomic / stone construction, both in terms of fabrication and engineering
Insulation is about retaining heat.
In the netherlands there's been too much emphasis on heat retention in houses built over the last ~15 yrs or so -- these houses are uncomfortable during the summer, since retaining too much heat. Another interesting take is that "passive" houses require heaps of mechanical ventilation, and these systems wear out in ~15-20 yrs.
So over the course of the lifespan of a house, that adds up significantly.
Stone actually can work well with the proper detailing (dealing with cold bridging, styrofoam is a good way to break the cold bridging ):
Heat Storage: Stone, being a dense and heavy material, has a high thermal mass capacity. It can absorb and store a significant amount of heat during the day when exposed to sunlight or internal heat sources like heating systems. This stored heat is gradually released back into the indoor space during cooler periods, such as evenings or nights, helping to stabilize indoor temperatures and reduce heating or cooling requirements.
Temperature Regulation: The thermal mass of stone can act as a natural temperature regulator, slowing down temperature fluctuations within a building. During hot summer days, stone absorbs excess heat, keeping indoor spaces cooler. In colder weather, it releases stored heat, helping to maintain a more comfortable and consistent temperature.
Energy Efficiency: By using stone as a thermal mass material, buildings can reduce their reliance on mechanical heating and cooling systems. This, in turn, can lead to significant energy savings and lower utility bills, as the building naturally regulates its temperature with less energy input.
Passive Solar Design: Stone can be strategically placed in a building's design to maximize its exposure to sunlight during the day. This allows for efficient passive solar heating, where the stone absorbs solar energy and releases it slowly, reducing the need for active heating systems.
It seems a bizarre statement to state that OpenCASCADE isn't fully capable. Its the only OS licensed kernel that'll read a STEP file. Also "modern foundation" is a misleading statement, any CAD kernel bearing any kind of relevance seems implying a codebase that's been around for a quarter century. Like it or not OpenCASCADE is the hand that was dealt. I've worked with the technology [1] extensively and it provided the underpinnings for a startup I've founded [2]. pythonocc is the bees knees, it allows you to develop a proper CAD app.
I'd consider CGAL a modern kernel, but it doesn't cover CAD since there is no BRep support [4]
Don't take my word for it, but see also the many publications that have built on the tech [3]
its actually a hard problem: the massive boom that's required to provide reach is inherently quite unstable, not in the mm or cm but we're talking decimeters here. some of the core tech of FBR dating back ~15 yrs addresses this kind of dynamic stabilization. FBR is impressive and they've built decent an IP.
(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)