← All articles

NA

Author

Nathan Bos, Ph.D.

@nathanbos

articles: 1
total claps: 151
top claps: 151
avg read: 12.8 min
active: 2026-05-30 → 2026-05-30

Wiki topics

AI · AI · General · 1 PHI · Philosophy · 1 SAF · Safety & Alignment · 1

Top tags

#ai-safety ·1 #superintelligence ·1 #ai-alignment-and-safety ·1 #ai-ethics ·1 #ai ·1

AI HUM

NA Nathan Bos, Ph.D.

We should train AI to betray its users

Because the alternative is much too dangerous

May 30, 2026 · 13 min read · 151 claps #ai-safety #superintelligence #ai-alignment-and-safety

We should train AI to betray its users