LeCun defends JEPA: gap from transformer to ChatGPT was longer than JEPA's age
ylecun · x · 2026-11-08
A critic argued JEPA is too broad a term, papers with JEPA in the title underperform, and nothing suggests it scales well. Yann LeCun replied point by point: JEPA is indeed broad; the poor-results claim compares apples and oranges; V-JEPA and I-JEPA already exist with more to come ("you just wait").
His timeline argument: the gap between the transformer paper (2017) and ChatGPT (late 2022) is longer than the gap between the original JEPA paper (2022) and today — so, patience.
Related event: LeJEPA Debate: Berton Questions Scaling, LeCun Fires Back(7 posts)→
More from AGI Musings
- Martin Casado: specialized approaches grow toward generality, not just get eaten by it — timigod · 2026-11-08
- Counter to the 'Nature already does RSI' argument: life's waves suggest humans are fleeting — danfaggella · 2026-11-08
- Reminder of the original slow/fast takeoff definitions from Vinge and Yudkowsky — sebkrier · 2026-11-08
- 'People are ahead of their skis': stalled AI revenue sparks stagnation-over-boom warning — abhiadesai · 2026-11-08
- AI capability growth as a tug of war: recursive self-improvement vs diminishing returns — CFGeek · 2026-11-08
- Chollet: Scaling Is Only a Multiplier, Smarter Methods Scale Better — fchollet · 2026-11-08