Elicit Building World Models as Alternative to Training Knowledge into Model Weights

What was said

"How do you make progress on continual learning in a way that is not stuff just lives in the weights of the language model, but is available to humans as a representation we can inspect and understand?"

Elicit is developing structured world models that exist outside model weights to enable reliable causal and counterfactual reasoning. Rather than relying on models to implicitly learn coherent representations during training, these explicit knowledge structures allow researchers to make predictions about interventions and counterfactuals while maintaining internal consistency that humans can audit.