Skip to content
Sign in
Artwork for Podkey WWDC 2026
Podkey WWDC 2026 · June 19 · 7 min

Machine Learning & AI Group Lab

A Podkey summary of Machine Learning & AI Group Lab, from WWDC 2026. A lot of Apple AI development right now comes down to one practical question: what belongs on the device, and what belongs in the cloud. The big themes here are trade-offs, measurement, and graceful fallback. Faster isn't always simpler, cloud isn't always slower, and the teams that do this well are the ones actually testing their assumptions instead of guessing. On-device or private cloud The evaluation framework matters more than the debate Latency is more nuanced than people think Model updates and version reality Background execution and the limits of local AI Custom models, fine-tuning, and size constraints Migration paths and PyTorch experimentation Graceful user experience when AI isn't available This podcast was created with Podkey. Make your own at https://podkey.fm

0:00-7:20
Play in

transcript

No transcript — this publisher did not publish one.

show notes

A Podkey summary of Machine Learning & AI Group Lab, from WWDC 2026.

A lot of Apple AI development right now comes down to one practical question: what belongs on the device, and what belongs in the cloud. The big themes here are trade-offs, measurement, and graceful fallback. Faster isn't always simpler, cloud isn't always slower, and the teams that do this well are the ones actually testing their assumptions instead of guessing.

  • On-device or private cloud
  • The evaluation framework matters more than the debate
  • Latency is more nuanced than people think
  • Model updates and version reality
  • Background execution and the limits of local AI
  • Custom models, fine-tuning, and size constraints
  • Migration paths and PyTorch experimentation
  • Graceful user experience when AI isn't available

This podcast was created with Podkey. Make your own at https://podkey.fm

links2

more episodes

All episodes