Guanlan Dai @guanlan · 02 Sep 2026
v1.0 focused on software engineering and terminal tasks. Next we will test the full harness × model grid. Much of what we observed points to harness-model fit rather than harness quality, and we want to identify which combinations maximize pass rates while minimizing cost.
17 879Views
109Likes
3Reposts
16Replies
3Quotes
55Bookmarks
Is that a lot?
0.99×vs this author's median18 132 views is typical
20Percentile for this authorof 5 recent posts
2.50×vs under 10K median7 156 views is typical
3.0× audienceReachviews ÷ followers
0.73%Engagement rateof viewers reacted