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 LeCun

Evidence Quote

“abandon generative models...work on jads...abandon contractive methods in favor of regularized methods...abandon reinforcement learning”

Source

The Shape of AI to Come! Yann LeCun at AI Action Summit 2025— DSAI by Dr. Osbert Tay
Created: 8/11/2026, 1:17:36 AM

Your notes

Loading notes...