Eric Horvitz @erichorvitz · 04 Sep 2026
Astra's model card shows that monitoring for abuse via CoT may become increasingly difficult. Beyond efforts on alignment & refusals, impt. to invest in maintaining monitorability. R&D on efforts like "tandem training" will be important. More from @cervisiarius below. @sama
690Views
3Likes
0Reposts
0Replies
0Quotes
2Bookmarks
Is that a lot?
0.89×vs this author's median775 views is typical
33Percentile for this authorof 9 recent posts
0.50×vs 10K–100K median1 384 views is typical
2.19%Reachviews ÷ followers
0.43%Engagement rateof viewers reacted