You can ignore that, of course he'll push his research. But he never says that what he does will lead to AGI. He's proposing a way forward to overcome some specific limitations he discusses.
Otherwise, he makes some perhaps subtle points about learning hidden variable models that are relevant to modern discussions about necessarily learning world-models in order to best model text.
Otherwise, he makes some perhaps subtle points about learning hidden variable models that are relevant to modern discussions about necessarily learning world-models in order to best model text.