Since the model doesn't get to observe the actual situation being reported on, s... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

zahlman 10 months ago | parent | context | favorite | on: AI assistants misrepresent news content 45% of the...

Since the model doesn't get to observe the actual situation being reported on, such an improvement in accuracy would only be random chance and should not be rewarded.

walkabout 10 months ago [–]

Oh, agreed, they don’t get points for failing the task but accidentally reporting something more-correct in the process.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact