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. LoganDark · 1791112315 · focus · HN ↗

      I keep wanting to use LLMs for creative writing that heavily involves physics like this, and it's been a definite struggle to say the least. I recently discovered that Gemini 3.1 Pro is the first model I've found to clearly beat the original November 2022 ChatGPT release in terms of implied physics. Man did the world really take its sweet time to get back here. I think it will continue to be a struggle until another genuine architectural shift happens -- it's still not anywhere close to perfect, just better.

      1. TristanDaCunha · 1791115318 · focus · HN ↗

         Do you have an example prompt I can try where frontier LLMs will stumble on physics?

         1. danielmarkbruce · 1791176562 · focus · HN ↗

            I'll try to find it - but recently one of the GPT 5 models stumbled badly on a baseball pitching physics problem. It continually screwed up because in the problem I gave the pitcher was left handed (my kid is a left handed pitcher). I wasn't even trying to get it to stumble but wow was it bad. I had to correct it over and over again.

Unofficial Hacker News client; not affiliated with Y Combinator.