Einsia @EinsiaAI · 21 Aug 2026
6/ The takeaway: Today’s agents can only occasionally do real algorithmic design—not reliably. Even at the highest reasoning tier, the average score was only 0.196: about 11% of the way from the 0.10 baseline to the theoretical optimum of 1.0. The question isn’t whether agents https://t.co/uu2AGnU9rj
442Views
16Likes
0Reposts
1Replies
0Quotes
2Bookmarks
Is that a lot?
0.78×vs this author's median565 views is typical
14Percentile for this authorof 7 recent posts
0.11×vs under 10K median4 164 views is typical
75.56%Reachviews ÷ followers
3.85%Engagement rateof viewers reacted