Ryan Greenblatt @RyanGreenblatt · 02 Sep 2026
OpenAI's newest AI, Astra, is reported to use an 'opaque reasoning' architecture where more of the reasoning occurs in activations instead of natural language. This may be the single worst development for AI security/safety to date. The details of Astra aren't publicly known,
143 232Views
1 559Likes
247Reposts
98Replies
53Quotes
0Bookmarks
Is that a lot?
6.00×vs this author's median23 864 views is typical
56Percentile for this authorof 9 recent posts
49.5×vs 10K–100K median2 896 views is typical
7.4× audienceReachviews ÷ followers
1.37%Engagement rateof viewers reacted