John Schulman @johnschulman2 · 04 Sep 2026
Bullish on this direction. Having a metric for explanation quality makes it possible to hillclimb, and counterfactual simulatability seems right. Adam et al. created a dataset+pipeline that creates more diverse+realistic test cases than prior work & do interesting exps on it. Can
49 293Views
523Likes
45Reposts
13Replies
2Quotes
394Bookmarks
Is that a lot?
0.48×vs this author's median102 925 views is typical
0Percentile for this authorof 6 recent posts
32.0×vs 10K–100K median1 540 views is typical
61.59%Reachviews ÷ followers
1.18%Engagement rateof viewers reacted