Warp @warpdotdev · 03 Sep 2026
Introducing Factory Benchmarks: The first model bench generated from your own coding tasks. Measure, test and improve coding agents by replaying past agent runs, and cut cost-per-PR by 63%+ Here’s how it works 🧵 https://t.co/uZXVdRt8LZ
64 856Views
179Likes
13Reposts
22Replies
15Quotes
125Bookmarks
Is that a lot?
13.2×vs this author's median4 903 views is typical
78Percentile for this authorof 9 recent posts
33.3×vs 10K–100K median1 948 views is typical
110.52%Reachviews ÷ followers
0.35%Engagement rateof viewers reacted