Re:Evaluating the world model implicit in a generative model
by plra on Thursday November 07, 2024 @09:38AM
(#42076985)
Really cool results. I'd love to see some human baselines for, say, NYC cabbies or regular Manhattanites, though. I'm sure my world model is "incoherent" vis-a-vis these metrics as well, but I'm not sure what degree of coherence I should be excited about.
[ Parent
| on HN ]
Re:Evaluating the world model implicit in a generative model
by shanusmagnus on Thursday November 07, 2024 @10:58AM
(#42077773)
Makes me think of an interesting related question: how aware are we, normally, of our incoherence? What's the phenomenology of that? Hmm.