HackerTube 中文?

Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI | Lex Fridman Podcast #416

Lex FridmanYouTube ↗

Further reading 1

Where does learning get a signal without an answer key? →Start with an unlabeled patch of an image, then switch to a game that requires a sequence of actions. Neither has an answer key, but finding structure and choosing a move need different signals.This video helps answer · What must be recovered behind the mask?

Caption notes

LeCun describes JEPA as predicting a representation of a full input from a corrupted observation. Its target can ignore individual leaf pixels, making what the representation preserves a substantive choice.

Video or transcript source ↗
Original passages · 2
you’re only trying to predict an abstract representation of the inputs
Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI | Lex Fridman Podcast #416 · ▶ 29:02–30:59 · passage interval
you’re not going to have to predict every single pixel of every leaf
Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI | Lex Fridman Podcast #416 · ▶ 29:02–30:59 · passage interval

Hacker News comments

View original on HN ↗