flâneur

Alignment Is Proven To Be Solvable - by SE Gyges

verysane.ai · 3,194 words · saved by 3 readers

That LLMs understand natural language as well as they do should dramatically change our understanding of the problem.

Alignment Is Proven To Be Solvable SE Gyges Feb 18, 2026 28 5 6 Share At least the systems that we build today often have that property. I mean, I’m hopeful that someday we’ll be able to build systems that have more of a sense of common sense. We talk about possible ways to address this problem, but yeah I would say it is like this Genie problem. Dario Amodei, Concrete Problems in AI Safety with Dario Amodei and Seth Baum , 2016 We might call this the King Midas problem: Midas, a legendary king in ancient Greek mythology, got exactly what he asked for—namely, that everything he touched should

saved by

related reading