Perplexity AI unveils hybrid local-cloud inference system at Computex 2026
Summary
Perplexity AI unveiled what it calls the first hybrid local-server inference orchestrator at Computex 2026, demonstrating software that autonomously decides in real time which AI workloads stay on a user's device and which get routed to cloud models. CEO Aravind Srinivas demonstrated alongside Intel CEO Lip-Bu Tan during Intel's keynote, using Perplexity's 'Personal Computer' agent to process confidential deal materials. Local models ran on Intel Core Ultra Series 3, keeping sensitive data local while sending heavier reasoning tasks to the cloud. The product is not yet available to users and will launch in the coming months.
Why it matters
This event showcases intelligent orchestration between local and cloud AI inference, involving joint demonstration by Intel CEO and Perplexity CEO, with significant implications for AI chips and cloud services.
Source links
Market reaction
The following is market reference information for related companies, and does not constitute investment advice.