Comment 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. parent the_sleaze_ 1 month ago
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.