Snorkel AI @SnorkelAI · 03 Sep 2026
Yesterday's virtual Reading Group brought in @yuan_mengq43669 of @XLangNLP to break down OSWorld 2.0: Why Long-Horizon Computer-Use Agents Still Fail Four Out of Five Tasks. Recording/transcript: https://t.co/hSlmCHmKMU The best AI agent evaluated in the paper completes only https://t.co/b7ATTZve1h
976Views
19Likes
3Reposts
6Replies
1Quotes
2Bookmarks
Is that a lot?
2.72×vs this author's median359 views is typical
56Percentile for this authorof 9 recent posts
0.60×vs 10K–100K median1 637 views is typical
5.50%Reachviews ÷ followers
2.97%Engagement rateof viewers reacted