Seohong Park @seohong_park · 24 Aug 2026
@seohong_park Definitely vibe with a compounding errors perspective. Part of my work with @max_simchowitz (https://t.co/VPFrtszFIi) precisely shows that reducing frequency of feedback (eg action chunking) is key to stable deployment. This can be true even if your demos are Markovian!
966Views
7Likes
0Reposts
1Replies
0Quotes
4Bookmarks
Is that a lot?
0.64×vs this author's median1 510 views is typical
0Percentile for this authorof 4 recent posts
0.36×vs under 10K median2 700 views is typical
16.71%Reachviews ÷ followers
0.83%Engagement rateof viewers reacted