Why CEMFORGE Is Built on a Two-Decade-Old Methodology
The Bitter Lesson, applied to 3D-printable cements.
The methodology underneath CEMFORGE is not new.
In 2019, Rich Sutton, one of the people who actually built modern reinforcement learning, wrote a 1,200-word essay called The Bitter Lesson. The argument: across seventy years of AI research, the methods that won were not the ones that hand-coded human cleverness. They were the ones that scaled with computation. Search and learning. Lots of both.
The same lesson played out in materials science long before AI got fashionable. And the field has barely adopted it.
The discipline came out of work by several foundational figures. Larry Kaufman formally introduced CALPHAD in 1970. Bo Sundman at the Royal Institute of Technology in Stockholm built much of the thermodynamic database infrastructure. Hans Leo Lukas contributed the phase-diagram optimization tools. Greg Olson, at Northwestern through the 1990s and now at MIT, synthesized those threads into Materials by Design, the discipline that became Integrated Computational Materials Engineering (ICME).
The methodology has receipts, and the receipts are quantitative. Computer-designed alloys have moved from clean-sheet design to qualified U.S. Air Force flight service in under seven years, against a conventional fifteen to twenty for new aerospace alloys. The platform-level claim is up to a seventy-percent reduction in physical testing burden. The same family of methods has since shown up in Apple’s product alloys, Tesla’s giga-press aluminum bodies, SpaceX’s proprietary Starship stainless, and most recently NASA’s GRX-810 ICME high-temperature alloy designed for additively-manufactured rocket-engine hot sections.
Outside that handful of operators, most metals R&D is still done largely the way it was in 1990. The methodology has been right for a quarter-century and the field has not broadly adopted it. That is the actual Bitter Lesson. Not “AI works” in the abstract, but “compute-leveraged search has worked, in public, for decades, and the experts have continued doing what they were doing before.”
Why 3D-printable cements, specifically
The broader AI-for-cement field is real and well-funded. Concrete.ai, AICrete, Giatec Scientific, Alcemy, Meta with Amrize, and Cemex are operators with millions in funding and substantial teams, working primarily on conventional cement and concrete production. None of them works exclusively in 3D-printed concrete. CEMFORGE does, and we do not position ourselves as one of these operators.
For conventional cement and concrete, the relationships between mix and outcome are tractable enough that regression analysis carries much of the predictive weight. That is the problem those operators are sized for, and they are valuable companies.
CEMFORGE is built for a different problem. The material-times-process complexity of 3D-printable cement is qualitatively greater than conventional concrete. The thixotropy of a 3DCP mix, the time-dependent shear behavior that lets the same material flow through a pump and then stiffen enough to hold a bead at rest, is different in kind. The processing equipment is different. The environment is different. The interactions cross more axes than a regression handles cleanly. And the ingredient count goes up, not down. Conventional concrete typically lands in a five-to-six ingredient range. UHPC, the high-performance subset, runs to seven or eight. 3D-printable cements land in roughly the same range as UHPC. That parallel is the right cost anchor for anyone trying to size what 3DCP costs to deliver. The same near-doubling of ingredients that makes UHPC expensive compared to conventional concrete is what 3DCP carries.
The design surface scales with it. Every additional pair of components is a new interaction to characterize against the properties the mix has to deliver: pumpability, early-age strength, thixotropic stiffening, cured strength, durability. The design problem is to coordinate this expanded ingredient palette across a wide and nonlinear process envelope. This is where ICME methodology becomes load-bearing. This is the substrate CEMFORGE is built for.
Open language, open hardware
There is something specific about Additive Construction that the polymers and metals industries don’t share. The instruments to create and measure 3D-printable cements have been available for a long time. What has not been available is a way to aggregate the results worldwide in a form the methodology can actually use.
Sunnyday Technologies built Open3DCP.org as the open data standard, aligned with ASTM, RILEM, and NIST conventions. The common language. M3-CRETE.com is the open-source 3D concrete printer that runs it. The common equipment. Open language plus open hardware is the infrastructure that lets every lab in the world contribute data the methodology can actually use.
That is the unprecedented part. The downstream prize is affordable, efficient, and ecologically defensible building materials. The human-scale prize is reducing the dull, dirty, and dangerous methods that produce concrete today.
What CEMFORGE ships
LOGiMIX is the hub. Given a project’s location, LOGiMIX assembles the supply-chain conditions specific to that site. Which cements, aggregates, and admixtures are actually available locally. At what cost. With what processing pathways already in place. Those conditions feed into the CEMFORGE formulation engine. CEMFORGE specifies a mix that delivers the required performance using the ingredients with the least shipping and processing burden. In theory, that is the lowest cost-to-market path.
Most AI-for-concrete systems work against the generality of specification-approved ingredients. They predict against the recipe that is supposed to work on average, across the supply chains the spec writer imagined. The generality is part of why prediction is hard. Average materials behave on average. The projects that actually get built use specific materials at specific sites with specific equipment.
CEMFORGE works against specifics. Exact product components paired with the specific equipment they will run through, the specific operating conditions on site, and the detailed material characterization generated during development with each customer. That level of characterization turns prediction from a population estimate into a project-specific answer.
Sunnyday Technologies decided to start spinning that wheel in 2022 and has not stopped since.
For the longer essay on the methodology’s twenty-five-year track record, the open-infrastructure differentiator for Additive Construction, and the working method that distributes labor between the human and the model along orders of perturbation, read it on sunn3d.com →
— CEMFORGE