Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124

Confusionan AI-powered search and answers engine, has a new way of turning personal devices into decentralized data centers.
The company said on Tuesday that Adding a new hybrid local server system to your PCits own AI agent that can work across files, apps, and the web. Starting in July, the system will automatically decide which parts of the task should run directly on the user’s device and which should be sent to more powerful AI models in the cloud.
A smaller model that runs locally can handle sensitive data and routine work locally, such as financial records, health information, and personal files. More complex work that requires greater AI model capabilities can still be submitted to the server.
Today we’re announcing that hybrid proxy inference is coming to Perplexity Computer.
The computer can split tasks between the local model running on your device and the leading models in the cloud. This keeps private data on your device and increases the efficiency of the token.
almost. pic.twitter.com/6t3PrmI1FX
– Perplexity (@perplexity_ai) June 2, 2026
Perplexity says its system will make this decision automatically, breaking the larger task into smaller parts and directing each part to the right place. Users will not need to choose between the on-premises model and the cloud-based model before getting started.
PC is currently available through Perplexity app for Mac. It expands the company’s existing PC agent with features that include editing local files, using and browsing through your PC Browser comet confusion. Al-Hira also said so PC is coming to Windows.
Although the current app is available on Mac, Perplexity is promoting the underlying technology as a broader system that can work across different types of devices. The company said that it revealed the system in cooperation with Intel and that the same framework works on other local silicon chips, including… Nvidia’s RTX Spark platform.
Moving more work to users’ devices could also reduce the amount of expensive cloud computing required to complete AI tasks. Perplexity says routine work shouldn’t consume the same data center resources as a request that really needs one of the more capable AI models.