Ryan Greenblatt @RyanGreenblatt · 02 Sep 2026
I don't think there will be strong+working mech interp in <1 year. Model internals methods could pareto dominate cot monitors in a year via cot losing ~all value, but this isn't exactly encouraging. Depending on AIs decoding other AI's opaque activations for oversight is spooky
21 991Views
391Likes
21Reposts
11Replies
5Quotes
65Bookmarks
Is that a lot?
0.53×vs this author's median41 417 views is typical
30Percentile for this authorof 10 recent posts
7.59×vs 10K–100K median2 896 views is typical
113.85%Reachviews ÷ followers
1.95%Engagement rateof viewers reacted