← All stories
AI & Tech

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

Cognitive Revolution · Radically Better Reasoning: Elicit's Andreas Stuhlmüller & Jungwon Byun on World Models for Research · June 17, 2026
Elicit Building World Models as Alternative to Training Knowledge into Model Weights
Cognitive Revolution
Cognitive Revolution
Radically Better Reasoning: Elicit's Andreas Stuhlmüller & Jungwon Byun on World Models for Research
"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.
From this episode
Cognitive Revolution
Cognitive Revolution

Radically Better Reasoning: Elicit's Andreas Stuhlmüller & Jungwon Byun on World Models for Research

August 3, 2026 · 5 Egleze moments
Read episode summary and key points →

More moments from this episode

AI & TechElicit Co-Founder Spends $2000 Per Week on AI Tokens for Personal UseAI & TechAI Company Deploys Automated Engineers Merging 30 to 50 Code Changes WeeklyAI & TechAI Research Models Claim They Analyzed 100 Papers but Admit They Did NotAI & TechElicit Built Programming Language to Make AI Reasoning Trustworthy at Scale
More stories More from Cognitive Revolution