Gary Marcus, cognitive scientist and author, says world models are explicit representations of objects and mechanisms that remain largely hand-engineered in systems such as chess computers and Wikipedia
Pasquale Minervini replied asking for an alternative approach to test.
@PMinervini i was hoping we could discuss in Edinburgh, was sorry you weren’t there :)
@GaryMarcus What should we try instead? Happy to give that a stab
@GaryMarcus What should we try instead? Happy to give that a stab
World models have existed for years (though not in LLMs); I take them to be explicit representation of objects, places, events, mechanisms etc you can reason over. Chess computers have them (board, pieces, moves, history) Nav systems have them (roads, times, etc) Wikipedia has one of a sort (when people were born, where they died, etc) They often work great (though again LLMs lack them). But most are hand-engineered. The trick is to acquire them from data.