806
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 18 Jul 2024
806 points (99.5% liked)
Technology
59583 readers
2381 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
Most people have pretty decent ai hardware already in the form of a gpu.
Sure dedicated hardware might be more efficient for mobile devices, but that's already done better in the cloud.
Google coral TPU has been around for years and it's cheap. Works well for object detection.
https://docs.frigate.video
There's a lot of use cases in manufacturing where you can do automated inspection of parts as they go by on a conveyor, or have a robot arm pick and place parts/boxes/pallets etc.
Those types of systems have been around for decades, but they can always be improved.
It's not really done better in the cloud if you can push the compute out to the device. When you can leverage edge hardware you save bandwidth fees and a ton of cloud costs. It's faster in the cloud because you can leverage a cluster with economies of scale, but any AI company would prefer the end-user to pay for that compute instead, if they can service requests adequately.
Yeah, you also have to deal with the latency with the cloud, which is a big problem for a lot of possible applications