Portable Intelligence Architecture: When the Runtime Becomes the Hard Problem

The useful part

Now, we're seeing a massive shift: we have to move the intelligence to the data. The meeting that changed how I think about AI infrastructure had almost nothing to do with models. We debated what happens when two versions of the same model disagree under replay.

How it works

• For two decades, we focused on moving data to the intelligence.
• We worried about whether one tenant's inference could starve a neighbor's on a shared accelerator.

Details worth keeping

We spent months obsessing over model quality. Then, over a few weeks, the agenda quietly reorganized itself. We were talking about onboarding third-party units.