Twelve dimensions across seven providers. Re-graded as announcements land, with the market's reaction shown alongside.
Privacy and latency · updated 2026-06-01
The leader: custom silicon, Private Cloud Compute, and a privacy-first local-inference architecture.
How much capability runs locally, for privacy, latency, offline use, and cost? Hardware, quantized models, and the OS-level plumbing that keeps sensitive context off the server.
Real-time keynote liveblog covering the rebuilt Siri, Apple Intelligence architecture, and iOS 27 reveals.
Explains the three-tier routing (on-device, Private Cloud Compute, Gemini on Google cloud) and its privacy tensions.
Gruber argues Apple should pick the best model regardless of vendor, but flags the branding contradiction.
A ~3B on-device model with 2-bit quantization and a Swift Foundation Models framework opening generation to apps.