
Leaker says Apple Harbor will run local AI models on Macs
Harbor, in a Claris private preview, pools Thunderbolt 5 Macs so open-weight models stay on device.
11 stories, newest first · one card per story

Harbor, in a Claris private preview, pools Thunderbolt 5 Macs so open-weight models stay on device.
Drex Max v1 27B decision model is open-sourced by Nace AI for local inference on Apple Silicon.
The title names Metal Performance Shaders support in PyTorch 2.15; the post body was not available.

Meta released Muse Spark Open, an 816B multimodal open-weight model with 42B active parameters and a 1M-token context.

Apple’s Minions paper turns idle Apple Silicon Mac GPUs into a distributed cloud for ML inference.

AWS open-sourced Strands Box, a developer-preview sandbox confining AI agents on Apple-silicon Macs with policy-enforced shell, Python, MCP, and network checkpoints.

Ars Technica reviews macOS 27 Golden Gate, highlighting an unavoidable Apple Intelligence upgrade, new AFM 3 Core models, and dropped Intel Mac support.

CVE-2026-90894 in Parallels Desktop for Mac lets any local user gain root via argument injection; patched in v27.0.0, PoC withheld.

JFrog's 'ParaShells' research details CVE-2026-90894, a Parallels Desktop local privilege escalation letting unprivileged macOS users gain root via tar argument injection.

JFrog researchers disclosed CVE-2026-90894, a critical Parallels Desktop local privilege escalation letting non-admin Mac users execute code as root; fixed in 27.0.0.
A community MLX inference engine evaluates constrained JSON schema fields in parallel on Apple Silicon, reporting 5.6-7.0x latency speedups with guaranteed schema validity.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views