Dan Robinson @danrobinson · 03 Sep 2026
Natural language autoencoders are the discovery that most makes me question my research intuition You jointly train two models: one to turn activations into English, and one to turn English into activations. The objective for the second model is to invert the first one, and the
8 446Views
51Likes
1Reposts
3Replies
0Quotes
53Bookmarks
Is that a lot?
1.12×vs this author's median7 512 views is typical
50Percentile for this authorof 6 recent posts
2.50×vs 10K–100K median3 383 views is typical
9.88%Reachviews ÷ followers
0.65%Engagement rateof viewers reacted