at://
/
app.bsky.feed.post
/
3lzijazoqed2w
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
That makes it hard to tell whether wins come from the model design or just from more data/compute or favorable benchmarks. We fix this by holding the pretraining dataset and compute constant and standardizing evaluation across tasks,