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. LoganDark · 1791132503 · focus · HN ↗

            I think it's a combination of non-human characters and asking for very specifically detailed physical descriptions of pulling and movement forces, etc. Many of even the most recent frontier models miss details that aren't in my prompt, so I still have to do things like name the other side of a physical interaction so that the model will know what goes together, or describe what leverage means so that the model will remember to also describe the effects on a bracing limb or etc. Some of these things can go in a system prompt but others have to be explained in the moment too which gets exhausting.

            Gemini 3.1 Pro hasn't needed that pretty much at all, which is impressive compared to how much I've learned other models need it. Somehow it's able to mostly handle that stuff itself without needing the constant manual reminders and hand-holding. It still misses the occasional one or two things but it's way better than other models missing entire classes of things constantly. Somehow, it feels appropriate though I have no actual evidence why.

         2. 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.