Robert Miles: Don't Build AI Safety on Keeping Secrets From a Superhuman Machine

harris_edouard · x · 2026-09-17

AI safety communicator Robert Miles delivers a pithy rebuttal to secrecy-based safety plans: don't hinge your plan on keeping something from ever being figured out by the superhuman figuring-things-out machine.

Original post →

More from AGI Musings

AGI Musings channel →