Thread

1. thoughtpeddler · 1790830845 · focus · HN ↗

   For those running local models on macOS with Apple Silicon, how does Magnitude differ from what Apple's own first-party Core AI now does during its "specialization" procedure, wherein it performs some kind of "model optimization and conversion" (vis-a-vis AOT compilation) into a Core AI "compiled model" file that is optimized for Apple Silicon (leveraging custom Metal 4 kernels, or so Apple says), per WWDC labs from this year that discuss this? [0]

   --

   [0] <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;videos&#x2F;play&#x2F;wwdc2026&#x2F;326&#x2F;" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;videos&#x2F;play&#x2F;wwdc2026&#x2F;326&#x2F;

   1. anerli · 1790832140 · focus · HN ↗

      Core AI is a way to ship a model inside an app rather than an inference engine you can point agents to, and it&#x27;s not meant for agent workloads.

      1. thoughtpeddler · 1790836259 · focus · HN ↗

         Understood that&#x27;s the general use-case, but couldn&#x27;t one use it &#x27;single-purpose&#x27; to ship a model as an inference engine (to point agents to)?

Unofficial Hacker News client; not affiliated with Y Combinator.