Skip to content
NewMS Lattice found both sealed targets blind, in 32 minutes, for under 20 cents.See the proof →
Advancing Bits to Master Atoms
← Every post

Insight2 min read

Why 64 candidates beat 32 million.

The number of candidates was never the product.

One crystal of matte graphite, satin silver and cobalt-blue spheres standing sharp and centered in front of a recessed blurred grid of muted slate cubes.One crystal of matte graphite, satin silver and cobalt-blue spheres standing sharp and centered in front of a recessed blurred grid of muted slate cubes.

The field has spent years proving that AI can generate candidates by the million. Microsoft and PNNL screened 32.6 million candidates on about 1,000 cloud machines to reach 18. Materials Nexus analyzed more than 100 million compositions on the way to a magnet. Remarkable work.

But a lab cannot make a million of anything.

MS Lattice holds your requirements inside the search. In the blind benchmark, 64 candidates were enough to find both sealed targets, in 32 minutes, for under 20 cents.

The answer is the product.

More from MatterSpace.

Stop guessing which crystal to make. Ask for it.

Tell us the domain and what the material must do. License MS Lattice for your team, or let Norck take the discovery all the way to finished parts.