Thread

1. stratos123 · 1791107241 · focus · HN ↗

   LeCun also said back in 2022 that "if you train a machine, as powerful as it could be, your 'GPT-5000', on text", it will never be able to learn basic common-sense physics like that objects placed on tables will move along with them.

   1. mdp2021 · 1791117069 · focus · HN ↗

      > never be able to learn basic common-sense physics

      And has it at this stage, within in-depth take of said "learning", foundationally?

      I have not been able to properly check the studies for a long time now, but I remain unaware of achieved solutions on the problem of reliably referencing a world model out of a language model - that "counting the 'r's in 'raspberry'" be not guessing, not memory, but actually counting.

      1. ethbr1 · 1791117362 · focus · HN ↗

         My perspective is that the addition of thinking loops to models allows sufficiently advanced ones to approximate world models.

         Incredibly inefficiently because of the recursive loops ("Wait, the object is on the table. I should think about this more deeply..."), and likely instantly surpassed by large world models if/when those are shipped, but effectively enough vs non-thinking models.

         1. red75prime · 1791121336 · focus · HN ↗

            LeCun calling them "world models" gives a high-level description of the desired functionality. They are Joint Embedding Predictive Architectures (with SIGReg). They might produce more useful world models, but it's yet to be seen.

Unofficial Hacker News client; not affiliated with Y Combinator.