We knew, but the proof is nice.
"Apple just proved that AI models cannot do math. Not advanced math. Grade school math. The kind a 10-year-old solves"
The guess-the-next-words machines don’t actually understand anything.
https://nitter.poast.org/heynavtoor/status/2041243558833987600#m
@davidaugust Of course an LLM cannot do math, but to be honest, that is also not what they're designed for. An LLM these days like Claude knows that it should take a calculator and type the equation in there, instead of hallucinating an answer. Complaining that an LLM can't do math is like complaining a screwdriver can't drill a hole.
You can counter that there are plenty of people who are using the screwdriver to drill the hole, but that is not on the tool, that is on the user.
@erwinrossen like a surprisingly large number of people, LLMs do not have actual understanding is the key take away.
Not only do LLMs (and some people) not understand stand what is overtly said, they cannot and do not have the ability for nuanced understanding either because that subset of understanding is just as inaccessible to them as the entire super set of understanding.
I am share this with an LLM (and some people) but I cannot make them understand it.
David August ❌👑
Erwin Rossen 🔸