LeCun's practical recommendations for AI research include: abandon generative models, work on JEPAs and representation-space prediction instead, abandon probabilistic models (they are intractable for high-dimensional outputs), use energy-based models, abandon contrastive methods in favor of regularized methods, abandon reinforcement learning as a primary approach (use it only as a last resort when model or cost functions are inaccurate).
normativepending
Speaker
Yann LeCunEvidence Quote
“abandon generative models...work on jads...abandon contractive methods in favor of regularized methods...abandon reinforcement learning”
Created: 8/11/2026, 1:17:36 AM
Your notes
Loading notes...