Y
Hacker News
new
|
ask
|
show
|
jobs
by
akasakahakada
1025 days ago
TB of original materials condensed into a few GB of neural network weight. If this is memorization, I would like it to be implemented into archive.org.
1 comments
ripvanwinkle
1022 days ago
Its a lot more like deduplication that achieves that compaction.
link