It's fine to be wrong about things not in your area of expertise. We just shouldn't listen to #authorities when they talk about topics that did not make them respected.
@dcz > Our experiment provides evidence supporting that these language models are developing world models and relying on the world model to generate sequences.
CleverLibre Social is an inclusive social instance for open discussion, learning, and community.
All cultures welcome.
Hate speech and harassment strictly forbidden.
@bonifartius The paper is easy to skim through and check the strength of the evidence.