"Care compresses better than cruelty": an insider's optimistic take on AI value alignment
coherence · x · 2026-11-13
Author Danmarhere pushes back on sci-fi style AI doom narratives: while the human corpus contains horrors, the behaviors civilizations have long celebrated—love of truth, kindness, helping others, taking the broader view—form large, stable basins in models' inner landscapes.
His core argument: these patterns have stood the test of time, so AI systems find it easy to rest there because it takes less energy. As a friend put it, "Care compresses better than cruelty"—what is held with care survives prunings and travels across generations, true for humans and AI alike.
In the quoted exchange, @mykola adds that he's cautiously optimistic the beautiful, the true and the good form a coherent attractor that enshrines cooperation and infinite games as their own reward. A substantive viewpoint thread on alignment direction, reflecting a cautious-optimist stance held by some close to the field.
More from AGI Musings
- Combining multi-agent objectives with single-agent action space breeds disempowerment — j_foerst · 2026-11-13
- Investor: AI has erased technical moats, startups now win on execution and GTM alone — vaibhavbetter · 2026-11-13
- Why AI Slop Is So Frustrating to Read: Hidden Subjects and Buried Actions — teortaxesTex · 2026-11-13
- Researcher asks: should papers be written for LLMs, or should LLMs learn to read like humans? — HildeKuehne · 2026-11-13
- Microsoft diagnostic AI solves 83% of NEJM cases vs 36% for physicians — realmeetjames · 2026-11-13
- Today is the 1960-predicted 'Day of the Singularity': infinity by Nov 13, 2026 — LeviTurk · 2026-11-13