PatronusAI @PatronusAI · 03 Sep 2026
Most game benchmarks measure “can the agent complete the game”? That metric basically saturates the moment frontier models complete the game. Human speedrunning communities have spent decades pushing the same games well past completion by discovering new routes and techniques, https://t.co/8jjvXXK1Xt
404Views
8Likes
1Reposts
1Replies
0Quotes
1Bookmarks
Is that a lot?
1.30×vs this author's median311 views is typical
57Percentile for this authorof 7 recent posts
0.11×vs under 10K median3 808 views is typical
15.45%Reachviews ÷ followers
2.48%Engagement rateof viewers reacted