> They'll eventually train it to answer this specific question, and then it will perform worse in some other aspect.
Not necessarily. Simply asking models to "check your assumptions" -- note, without specifying what assumptions! -- overcomes a lot of these gotcha questions. The reason it's not in their system prompts by default is I think just a cost optimization: https://news.ycombinator.com/item?id=47040530
Not necessarily. Simply asking models to "check your assumptions" -- note, without specifying what assumptions! -- overcomes a lot of these gotcha questions. The reason it's not in their system prompts by default is I think just a cost optimization: https://news.ycombinator.com/item?id=47040530