alex 🏴☠️🇺🇸🇺🇦 @alex · 02 Sep 2026
A very hot take: chain of thought interpretability was always going to be so fragile as to be an unacceptable backstop for long-term AI safety, and while I admire the optimism and effort involved in protecting its fidelity (and consider such effort to have been worthwhile), I do
96 355Views
409Likes
32Reposts
52Replies
25Quotes
140Bookmarks
Is that a lot?
44.4×vs this author's median2 172 views is typical
83Percentile for this authorof 6 recent posts
4.40×vs 100K–1M median21 891 views is typical
91.04%Reachviews ÷ followers
0.54%Engagement rateof viewers reacted