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
_aavaa_
9 hours ago
|
on: AMD acquires Taalas to boost inference performance by etching models in silicon
If we had deepseek v4 flash 0731 etched on a chip it would be more than capable enough and fast enough for so many people's needs, even hardcore engineer.
reply
nurumaik
9 hours ago
|
parent
Will be capable and fast enough for 2-3 weeks until new sota drops
reply
loading story #49202759