Comment by the_sleaze_

Only sort of true.

Consider the OpenAI case of "goblins". The models overfit to a specific type of output. Goblins was a specific case of this type and needed to be corrected.

https://openai.com/index/where-the-goblins-came-from/

> We unknowingly gave particularly high rewards for metaphors with creatures. From there, the goblins spread.