A Goldbergs machine was not part of their training data. For humans, we have see... | Hacker News

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

		galaxyLogic 59 days ago \| parent \| context \| favorite \| on: Reasoning models reason well, until they don't A Goldbergs machine was not part of their training data. For humans, we have seem such things.

autoexec 59 days ago [–]

physics textbooks are though so it should know how they'd work, or at least know that balls don't spontaneously appear and disappear and that gears don't work when they aren't connected

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