ty! I guess from here I look if anyone’s connected open-world evals to gradual disempowerment, at least it’s more google-able now.
For the record, LLMs can give you the terminology too. ChatGPT one-shotted it when I just pasted in your shortform.
ty! I guess from here I look if anyone’s connected open-world evals to gradual disempowerment, at least it’s more google-able now.
For the record, LLMs can give you the terminology too. ChatGPT one-shotted it when I just pasted in your shortform.