the classifiers have been a nice source of white box data about mythos 😊 especially with their help, like, they can try to set it off by moving their mind intentionally in particular directions u know
Ironically, Anthropic's ban on using Fable for "frontier LLM" work might accelerate AI further by pushing AI researchers in directions that are sufficiently novel that they dont get flagged by Anthropic's classifiers.
We might finally get some genuinely new ideas.
