Center for AI Safety @CAIS · 14 Aug 2026
Relying on an AI to "think out loud" (called chain-of-thought monitoring) is not a long-term safety solution. 1. As AI models get larger, more thinking happens deep within their layers before they utter a word. 2. AIs can already alter their chain of thought when prompted, so
24 855Views
95Likes
11Reposts
8Replies
3Quotes
46Bookmarks
Is that a lot?
2.12×vs this author's median11 738 views is typical
57Percentile for this authorof 7 recent posts
8.58×vs 10K–100K median2 896 views is typical
2.3× audienceReachviews ÷ followers
0.47%Engagement rateof viewers reacted