Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
On the Expressive Power of Transformers
Phokion Kolaitis, Rik Sengupta
Multi-layer transformers form the critical component of essentially all large language models (LLMs) in use today. Because of their ubiquity and computational capability, there is…
cs.AI2026
Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)
Sam Mao
Contemporary AI alignment research treats self-preservation as an instrumental nuisance to be suppressed by external mechanisms. We argue the framing is inverted: self-preservation…