# Home machines need asynchronous designs to serve production AI

- **Speaker:** Greg Osuri
- **Attribution:** attributed
- **Said:** 2024-08-12
- **Theme:** Local Compute — https://www.gregosuri.com/predictions/local-compute/
- **Source:** BASS 2024 10 Ben Fielding, Greg Osuri, Guy Wuollet, Steven Willinger (Stanford Blockchain Club)
- **Watch at:** 00:05:20 — https://www.youtube.com/watch?v=FQZZiUAmLLI&t=320s
- **Canonical:** https://www.gregosuri.com/predictions/local-compute/2024-08-12-home-machines-need-asynchronous-designs-to-serve-p-2cr5/
- **Cite as:** Greg Osuri, "Home machines need asynchronous designs to serve production AI," BASS 2024 10 Ben Fielding, Greg Osuri, Guy Wuollet, Steven Willinger (Stanford Blockchain Club), 12 Aug 2024, 00:05:20. https://www.youtube.com/watch?v=FQZZiUAmLLI&t=320s

## Quote — verbatim

> A machine sitting in a home may not be able to serve a production workload unless, you know, maybe intelligently designed with asynchronous model — but definitely for an inference type of scenario you need that low-latency access to the user, and that can only be delivered by a professionally managed data center.

## Context — site annotation, not spoken

A rare nuance/caveat in his local-compute thesis: latency-sensitive inference still favors professional data centers; async architectures are the path for home hardware.