at://
/
app.bsky.feed.post
/
3lq5y26z75c24
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
🧵2/10 MLLMs lack the visual understanding to plan edits. 🧠So, we use expert photos as our ground truth and work backward, procedurally creating puzzles by assuming any change to an expert edit makes it less optimal