thebes
imo RL makes model personas both less /and/ more anthropomorphic - it can e.g. drive preferences out of the human distribution, but it can also strengthen humanlike behaviors like exhaustion and self-coherence anthropomorphization was always only a useful lens, still useful
roon
taking the under on this there was a time period where it was helpful to anthropomorphize models, when persona selection was the primary function of RL now we are building superintelligent minds under alien optimization pressures