On: Ente: Open-Source, E2E Encrypted, Google Photos Al...

[davidmurdoch]

> Now to run algorithms over your photos, all the computation must be done on the edge.

Edge is an overloaded and fuzzy term [0]. It just means "on device" here, right?

[0] https://www.cloudflare.com/learning/serverless/glossary/what...

[vishnumohandas → davidmurdoch]

Yes, it means on device.

[ignoramous → vishnumohandas]

Might want to s/edge/device/g in your docs.

[vishnumohandas → ignoramous]

"Edge" unfortunately is a broad term whose definition depends on the scope of the system. But "Edge ML" is the precise way to communicate what we're doing.

I agree that "on device ML" is less ambiguous, so will give this some more thought.

Thanks for the suggestion!

[davidmurdoch → vishnumohandas]

Your can probably communicate both without consequence. A change as simple as:

> all the computation must be done on the edge: your own device.

Might do the trick.