TECHNOLOGYDECRYPT
Perplexity Wants Your Laptop to Do Part of the AI Work—So It Doesn't Have To
Perplexity has introduced a hybrid inference system that automatically routes AI tasks between user devices and the cloud. The system aims to enhance privacy and reduce costs by minimizing server usage.
Related Signal
Adjacent reporting
- Darkbloom – Private inference on idle Macs
- Cloudflare's AI Platform: an inference layer designed for agents
- Argonne flexes spare supercompute to build private AI inference service
- Osaurus brings both local and cloud AI models to your Mac
- Explainer: Edge AI
- Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference