LeCun's 2022 position paper: the JEPA blueprint that predicted world models' rise
TheTuringPost · x · 2026-11-21
From TheTuringPost's thread: LeCun's June 2022 position paper "A Path Towards Autonomous Machine Intelligence" placed a predictive world model at the center of an agent and proposed JEPA—predicting the representation of what comes next, not the pixels. It was a blueprint without benchmarks; four years later the line has progressed from features to planning and action.
More from Research
- WorldTrace beats sliding window recall by 32.6% at same cache size, tops all 12 LoopBench conditions — cindy_x_wu · 2026-11-21
- Proposed proof of Generalized Riemann Hypothesis released; mathematician stresses it is entirely human, no AI — paulabartabajo_ · 2026-11-21
- Arcfront turns real hospital and factory work records into RL environments and frontier model evals — rohanpaul_ai · 2026-11-21
- Goodfire probes Inkling 2 Mini: looped model layers read from "future" layers — fatihdin4en · 2026-11-21
- Terence Tao offers a bet to anyone who really believes RH will be proved next year — jaivin · 2026-11-21
- Terence Tao: AI is winning at math but we've learned almost nothing from it — bansalg_ · 2026-11-21