logoalt Hacker News

kranke15512/09/20242 repliesview on HN

Until these models can figure out physics, it seems to me they will be an interesting toy


Replies

andybak12/09/2024

They can figure out a fair bit of physics. It's not a "no physics" vs "physics" thing. Rather it's a "flawed and unreliable physics" thing.

It's similar to the LLM hallucination problem. LLMs produce nonsense and untruths - but they are still useful in many domains.

show 1 reply
kylehotchkiss12/09/2024

But they don't, they just understand pixel relationships (right?)

show 1 reply