News for hackers. Stuff that matters.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by MichaelRazum on Friday March 31, 2023 @05:08PM (#35393683)
"math genius" not sure about it. I gave it a problem from IMO 2022. In my opinion not a very hard one. It failed even if you give it some hints.

Let R+ denote the set of positive real numbers. Find all functions f : R+ → R+ such that for each x ∈ R+, there is exactly one y ∈ R+ satisfying xf(y) + yf(x) <= 2.

It just struggeld to reason. So I would be very surprised if the plugin somehow helps here.

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by Donald on Friday March 31, 2023 @05:15PM (#35393759)
It's a language completion model, so it's not surprising at all that it struggles with logical inference. That's probably one of the reasons that instruction fine-tuning has such a dramatic effect in the performance of these models: they're finally given some of the underlying causal priors of the task domain.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by knrdev on Friday March 31, 2023 @08:38PM (#35395756)
Very strange. I gave this problem to GPT-3.5 and it answered `f(x)=1/x`. https://www.youtube.com/watch?v=13YrZLBmu7A gives the same solution. GPT-4 failed but was close. Maybe GPT-3.5 is smarter ;)

Query i used was: ``` Can you think step by step about this math problem and solve it?

Let R+ denote the set of positive real numbers. Find all functions f : R+ → R+ such that for each x ∈ R+, there is exactly one y ∈ R+ satisfying xf(y) + yf(x) <= 2. ```

Response: https://pastebin.com/sTXM9kLt

Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by MichaelRazum on Saturday April 01, 2023 @06:41AM (#35399112)
I asked gpt4 to think through it step by step and then to recheck the answer. At least it got 1/x right. So now kind of impressed.
Re:HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends... by rcpt on Saturday April 01, 2023 @02:06AM (#35397588)
Putnam asked "can a parabola of arc length 4 fit inside the unit circle?"

Should be simple for a computer to just try every parabola but all the LLMs try to solve it like a human would (and get it wrong)