Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
samtp
20 hours ago
|
on: Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
more likely that hosting and delivering the models will be commoditized, much like how DO, Linode, Hertzer etc all commoditized VPSs and server hosting. And you'll end up paying for virtual hardware size (or compute resources) rather than tokens
reply