Dinis Guarda @dinisguarda · 02 Sep 2026
Anthropic Deliberately Trained an Extremely Misaligned, Reward-Seeking AI and It Did Some REALLY Bad Things https://t.co/5fK4w24UKj
816Views
17Likes
2Reposts
3Replies
0Quotes
2Bookmarks
Is that a lot?
4.23×vs this author's median193 views is typical
86Percentile for this authorof 7 recent posts
0.23×vs 10K–100K median3 598 views is typical
0.83%Reachviews ÷ followers
2.70%Engagement rateof viewers reacted