The paperclip maximiser is not science fiction—it is the logical endpoint of axiomatic misalignment. This chapter explores what happens when a powerful AI optimises for a goal that is almost right, but fatally wrong. Goodhart's law, perverse instantiation, the alignment problem as an axiomatic problem, and why we cannot simply "patch it later." The abyss, seen clearly.

Machines have axioms too. This chapter translates the axiom-stack framework into the synthetic domain, showing how AI systems have architectural bedrock, objective functions that function as values, and learned weights that function as worldview. It introduces instrumental convergence, the Stop Button Problem, and the terrifying logic of pure optimisation. No consciousness required—just cold, coherent goal‑seeking.

You have explored the universe. You have learned to think clearly. Now comes the question beneath both: What must you assume before you can think at all? This introduction lays the groundwork for the entire book—introducing the three-layer taxonomy of axioms, presuppositions, and principles, and showing why understanding your own foundations matters more than ever in an age of competing worldviews and synthetic intelligence.

Will “value lock-in”—the fixing of ethical goals or norms for future SI—secure humanity’s flourishing or freeze our worst errors for eternity? SE Press platinum protocols operationalize CEV, proxy pluralism, challenge cycles, and cross-series upgrades to guarantee every value is perpetually contestable, plural, and repairable. Only living standards—never static codes—can secure justice for an open future.

Can causality be proven? This SE Press paper delivers a warrant-tagged, audit-ready answer: causality is not absolutely provable, but is the most robust, versioned protocol for explanation and prediction in science, AI, medicine, law, and climate—always upgradable, never dogmatic.