Einsia @EinsiaAI · 21 Aug 2026
5/ More reasoning means more exploration: 13× more code, 10× more tokens, 4× more evals. But gains lag behind: score improves only ~2×, reaching just 0.196 at max effort. https://t.co/SfajILjlWp
498Views
13Likes
0Reposts
2Replies
0Quotes
2Bookmarks
Is that a lot?
0.88×vs this author's median565 views is typical
29Percentile for this authorof 7 recent posts
0.12×vs under 10K median4 164 views is typical
85.13%Reachviews ÷ followers
3.01%Engagement rateof viewers reacted