Evolution does not simply make hardwired machines that execute a predetermined set of steps; instead, it produces problem-solving hardware.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Evolution often produces general-purpose problem-solving machines whose capacities cannot be inferred from the default invariant course of development.claim0.849
  A claim about the outcome of the MCA-enhanced process.
• Evolution learns to generalize beyond default morphologies, producing problem-solving machines.claim0.836
  Argues that evolutionary learning goes beyond specific adaptations.
• Evolution makes problem-solving agents, not solutions; commitment to mutation and uncontrollable environments as ratchet for intelligenceclaim0.820
• Evolution was using developmental bioelectricity long before neurons and muscles appeared, to solve the problem of creating and repairing complex bodies.claim0.807
  Claim about the primacy of bioelectric morphogenesis.
• By using a variational autoencoder-like architecture for genomic compression, evolution is freed from over-training and pushed to evolve general-purpose problem-solving machines.claim0.798
  Claim linking the indirect genotype-phenotype mapping to robustness and open-endedness.
• Evolution re-uses many of the same mechanisms and strategies across scales of organization and problem spaces.claim0.796
  Claims that scale-free dynamics, like bioelectric networks, are ancient and conserved.
• Biology's robustness, open-endedness, evolvability, and unique complexity likely depend on the fact that evolution works with an agential material.claim0.784
  Central claim linking life's properties to the inherent competencies of its material substrate.
• Evolved machines increasingly exhibit self-similar, hierarchical structure like living systems.claim0.781
  Artificially evolved neural networks and robots often lack modularity unless selected for, resembling life.