If Agentic AI is drifting toward bliss, we’re no longer optimizing outputs but cultivating a form of consciousness.
What is considered bliss in the new performance metric? (2/2)
henry@arithmoquine
anthropic included a "model welfare evaluation" in the claude 4 system card. it might seem absurd, but I believe this is a deeply good thing to do "Claude shows a striking 'spiritual bliss' attractor state"
English
