Ryan Greenblatt @RyanGreenblatt · 02 Sep 2026
I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4. OpenAI has worked to preserve and utilize chain-of-thought monitoring since
1 215 251Views
5 747Likes
469Reposts
236Replies
165Quotes
1 502Bookmarks
Is that a lot?
29.3×vs this author's median41 417 views is typical
70Percentile for this authorof 10 recent posts
442×vs 10K–100K median2 751 views is typical
62.9× audienceReachviews ÷ followers
0.54%Engagement rateof viewers reacted