Story
LeMario: Training a JEPA World Model on Super Mario Bros
1 report
1 website
1 discussion
Latest report
Overview
LeMario is a Joint-Embedding Predictive Architecture (JEPA) model trained on Super Mario Bros to learn world dynamics from pixels and actions. The model successfully passed all initial tests.
Summary from benjamin-bai.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · benjamin-bai.com
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-07-15.
- Praise: This paper shines a light on JEPA's potential, especially how it can predict horizontal position effectively after minimal training — a promising step for model-based control.
- Praise: The insights shared by the author about the training process are invaluable, showcasing a real-world application of AI concepts in gaming.
- Concern: Planning in latent space can be noisy and unrepresentative of actual game positions, which raises concerns about control and optimization in dynamic environments.
- Concern: Chunking planning into intermediate goals feels limiting, undermining the essence of model-based control where flexibility is key.