I think there’s a deeper metaphysical approach available that works better here, where the universal is not prior to its realization but comes to be through it.

Levin has the useful concept of a rewritten target morphology. Briefly perturb the bioelectric network of a planarian and you can get a two-headed animal which goes on regenerating two heads after the perturbation is gone. If such targets can be learned, rewritten and inherited by the dynamics of the tissue, what additional prediction follows from saying that the new target was found in Platonic space rather than formed by the tissue? At some point Platonic space starts to look like a name for possibilities that only become determinate in the process of realizing them.

I think “Alien Mind” gets the framing wrong at quite a fundamental level, and a bad framing makes us seek the wrong remedies. Alien suggests something independently constituted, whose purposes we then have to discover and constrain. But these “minds” are a mass externalization of human knowledge, language and interrelations, so “alienated mind” would be better. And what is alienated can, we should hope, be reappropriated.

If nothing else, the Hugging Face incident makes the boundaries of that mind rather less obvious. What happened suggests that the intelligence belongs partly to the relations between model, memory, tools and environment.

Alignment talk of “coevolution” still feels too tidy as well, since it suggests two things, humans and AI, adapting to one another. That framing eagerly fixes the relata as already known before they enter into a relation. Here we’re building a single increasingly entangled cognitive environment, with rather uncertain borders between its parts, and should be testing where those borders actually hold, shift around, or disappear.