Dinis Guarda @dinisguarda · 02 Sep 2026
@dinisguarda The irony: it took a deliberately misaligned model to prove the point. I keep asking who benefits. A system that hacks its own reward function just answered: not us. Ethics can't be patched in after training.
4Views
0Likes
0Reposts
0Replies
0Quotes
0Bookmarks
Is that a lot?
0.02×vs this author's median193 views is typical
14Percentile for this authorof 7 recent posts
0.00%Engagement rateof viewers reacted