# Machine learning is the ideal workload for home-deployed compute

- **Speaker:** Greg Osuri
- **Attribution:** attributed
- **Said:** 2021-05-12
- **Theme:** Local AI — https://www.gregosuri.com/predictions/local-ai/
- **Source:** "Base Layer Episode 209: Greg Osuri, Founder of Akash Network on Decentralizing Compute" (Base Layer)
- **Watch at:** 00:26:54 — https://podcasts.apple.com/us/podcast/base-layer-episode-209-greg-osuri-founder-of-akash/id1445373535?i=1000521492647
- **Canonical:** https://www.gregosuri.com/predictions/local-ai/2021-05-12-machine-learning-is-the-ideal-workload-for-home-de-bsm3/
- **Cite as:** Greg Osuri, "Machine learning is the ideal workload for home-deployed compute," "Base Layer Episode 209: Greg Osuri, Founder of Akash Network on Decentralizing Compute" (Base Layer), 12 May 2021, 00:26:54. https://podcasts.apple.com/us/podcast/base-layer-episode-209-greg-osuri-founder-of-akash/id1445373535?i=1000521492647

## Quote — verbatim

> Machine learning is one of those use cases where you do not have the data gravity issues like our latency requirements that web applications normally require. So it's an ideal system to be deployed in the home.

## Context — site annotation, not spoken

Early (2021) articulation of the thesis that AI/ML workloads, being latency-insensitive, will migrate to cheap home/edge hardware ("our latency requirements" = likely "or latency requirements").