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
cmrdporcupine
18 hours ago
|
on: GLM-5.1: Towards Long-Horizon Tasks
I think what Anthropic is doing is more subtle. It's less about quantizing and more about depth of thinking. They control it on their end and they're dynamically fiddling with those knobs.
reply