Hacker News Reader

I feel like JEPA is a mild infohazard; because everyone who studies it feels like it has huge potential and will quickly overtake autoregressive next-token prediction. Meanwhile, autoregressive next-token prediction keeps exponentially increasing capabilities.

View on HN

It's an incredibly obvious optimization on the autoregressive model, and converting a training pipeline to adopt it, with how good autoregressive models are now, is as easy as saying "do this but jepa" to codex or claude. It's gonna be like how everything is becoming rust now.

Reply on news.ycombinator.com