We are talking about future research directions, not what's possible today. Given the success AI has had in virtually every domain its been deployed in, there's no reason to think it won't do well simulating physiological processes.
In fact we're talking about claims that Anthropic is making to juice their IPO prospects, there's precisely zero indication that ML is capable of doing what you're suggesting. Generally speaking an enormous claim requires commensurate support, not "I figure it'll just work out down the road."
[–] gradus_ad 1 day ago
[–] EA-3167 1 day ago