Evidence item

The excerpt directly states that aligning models through chain-of-thought reasoning will be impossible at a million transactions per second without chain of thought. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 8968

Source: OpenAI Agents Hijack a German Website, Jensen Declares AGI Arrived, and OpenAI Solves Navier-Stokes · locator {} · excerpt hash sha256:e2646059ac2d572f3d7aef3e7ba8d32beeb4f030fa705469adf30fbef7cc36f4

It's impossible to align these models through chain of thought reasoning or anything like this cuz there'll be a million transactions per second and they won't have chain of thought where we're going.