Sayash Kapoor @sayashk · 30 Jul 2026
Can AI agents conduct open-ended AI research? Most evaluations of agents conducting AI research focus on narrow, verifiable tasks. But AI research is often open ended. Researchers pick hypotheses, decide what evidence is appropriate, and recognize a failing approach. We gave https://t.co/bjoJDC4UQq
173 584Views
705Likes
145Reposts
68Replies
38Quotes
597Bookmarks
Is that a lot?
25.8×vs this author's median6 724 views is typical
86Percentile for this authorof 7 recent posts
63.1×vs 10K–100K median2 751 views is typical
11.7× audienceReachviews ÷ followers
0.55%Engagement rateof viewers reacted