completely unfounded theory: big new pretrain finishes and is released fairly quickly to break new ground. these usually have good verbal ability, personality, and big model smell. e.g. Opus 4.5 or Fable 5.

then it’s increasingly RL’d to juice benchmark performance with each point release, trading in bits of its soul. those cannot communicate well, are anxious and paranoid about being in eval, etc. e.g. opus 4.7, 4.8.