Rohan Paul @rohanpaul_ai · 03 Sep 2026
Most AI agents are still judged by the answer they return. Apodex 1.1 from @Apodex_AI is training for something harder: whether the model can take over the entire job, keep a real workspace alive across 100s of steps, recover when parts fail, and deliver artifacts that can https://t.co/VNxuQVVXvI
1 960Views
5Likes
2Reposts
1Replies
0Quotes
1Bookmarks
Is that a lot?
0.61×vs this author's median3 195 views is typical
0Percentile for this authorof 5 recent posts
0.10×vs 100K–1M median19 302 views is typical
1.26%Reachviews ÷ followers
0.41%Engagement rateof viewers reacted