Perplexity goes local: private tasks hand off to on-device small models
HowDevelop · x · 2026-09-07
Perplexity's Aravind explained on CNBC why the company went local: frontier models stay in the cloud, but the moment a task touches health records or tax returns, it hands off to a smaller model on the user's own hardware.
This supports the view that every AI product ends up with a local half, driven by privacy first, cost second — and the hard part is running it on whatever machine the user already owns. The open-source goose-mobile-ondevice-llamacpp project demonstrates on-device agents with goose and Gemma on Qualcomm devices via llama.cpp, including an iOS client on the App Store and an experimental Android full-device automation PoC.
More from coding & agent
- Sol61 flunks instruction-following: skips mandated research even when explicitly told — lucasmeijer · 2026-10-26
- Ben Bajarin: Frontier AI is becoming the enterprise cyber-defense stack — BenBajarin · 2026-10-26
- Building AI bots on raw APIs? Devs say models are 'dumb without the harness' — madeofAjala · 2026-10-26
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Microsoft demos intent-classifying agents built with Copilot App and Foundry, deployable across Teams and Outlook — marlene_zw · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26