I wouldn't claim to be an AI datacentre expert—good ol' fashioned PC gaming circuitry, that's my bread and butter—but I, along with everyone else and their collective brothers, know that those servers stack memory like nobody's watching. That's the reason we're living through a veritable RAMpocalypse, after all. So I can certainly laugh along with the various bewildered posts on X responding to OpenAI's latest patent.
The chip architecture patent [PDF], published on April 2, 2026, is for "a system of high bandwidth memory (HBM) chiplets and compute chiplets [which] includes embedded logic bridges that extend communication distances from the HBM chiplets to other chiplets beyond the ~6 mm limit imposed by the JEDEC standard."
