Andy E Williams

A Func­tional Model of In­tel­li­gence May Be Re­quired to Solve Align­ment. Why Can’t We Test That Hy­poth­e­sis?

Why the Align­ment Cri­sis Asks Coders to Be­come Philoso­phers—and Philoso­phers to Be­come Coders

The Con­cep­tual Near-Sin­gu­lar­ity: The Mother of All Hal­lu­ci­na­tions?

The Illu­sion of Iter­a­tive Im­prove­ment: Why AI (and Hu­mans) Fail to Track Their Own Epistemic Drift

Pre­serv­ing Epistemic Novelty in AI: Ex­per­i­ments, In­sights, and the Case for De­cen­tral­ized Col­lec­tive Intelligence

Why Lin­ear AI Safety Hits a Wall and How Frac­tal In­tel­li­gence Un­locks Non-Lin­ear Solutions