Ryan Greenblatt @RyanGreenblatt · 02 Sep 2026
@tszzl I think it's unlikely that white-box techniques will be able to provide as much monitorability as CoT currently provides within a year. Currently, they are capable of catching some unverbalized thoughts / plans, but nowhere near as reliably as CoT seems to. I'm optimistic about
23 864Views
249Likes
22Reposts
9Replies
9Quotes
0Bookmarks
Is that a lot?
0.58×vs this author's median41 417 views is typical
40Percentile for this authorof 10 recent posts
8.67×vs 10K–100K median2 751 views is typical
123.55%Reachviews ÷ followers
1.21%Engagement rateof viewers reacted