Comment by mattnewton

1 year ago

Claude 3.5 seems to get it, (thought the method is not what I would use?) -

———

Let's think through this step-by-step:

  We're looking for three numbers a, b, and c where:
    (a / b) / c = a + b + c

————

Certainly, let's approach this problem step-by-step:

1) First, let's write out our equation: (a / b) / c = a + b + c

2) To simplify the left side, we can rewrite it as: a / (b * c) = a + b + c

3) Now, to solve this, we need to find values for a, b, and c that satisfy this equation. Let's start by considering some properties: - All numbers must be positive (because we're dividing by b and c) - The left side is a fraction, while the right side is a sum

4) One way to approach this is to try to make the left side equal to 1, which would mean: a = b * c

5) If we substitute this into our original equation: 1 = b * c + b + c

6) Now we're looking for two numbers b and c where their product plus their sum equals 1.

7) Let's try some small numbers: If b = 1/2 and c = 1/2: (1/2 * 1/2) + 1/2 + 1/2 = 1/4 + 1 = 5/4 ≠ 1

8) Let's try smaller numbers: If b = 1/3 and c = 1/3: (1/3 * 1/3) + 1/3 + 1/3 = 1/9 + 2/3 = 7/9 ≠ 1

9) Even smaller: If b = 1/4 and c = 1/4: (1/4 * 1/4) + 1/4 + 1/4 = 1/16 + 1/2 = 9/16 ≠ 1

10) We're getting closer. Let's try b = 1/4 and c = 1/3: (1/4 * 1/3) + 1/4 + 1/3 = 1/12 + 1/4 + 1/3 = 1/12 + 3/12 + 4/12 = 8/12 = 2/3 ≠ 1

11) Let's adjust further. If b = 1/3 and c = 1/4: (1/3 * 1/4) + 1/3 + 1/4 = 1/12 + 1/3 + 1/4 = 1/12 + 4/12 + 3/12 = 8/12 = 2/3 ≠ 1

12) One more try. Let's use b = 1/2 and c = 1/3: (1/2 * 1/3) + 1/2 + 1/3 = 1/6 + 1/2 + 1/3 = 1/6 + 3/6 + 2/6 = 6/6 = 1

13) We found it! When b = 1/2 and c = 1/3, the equation holds.

14) Remember, we set a = b * c, so a = 1/2 * 1/3 = 1/6

Therefore, one solution to the equation (a / b) / c = a + b + c is: a = 1/6, b = 1/2, and c = 1/3

We can verify: (1/6 / 1/2) / 1/3 = (1/3) / 1/3 = 1 1/6 + 1/2 + 1/3 = 1/6 + 3/6 + 2/6 = 1

This solution satisfies the equation.

——

In general I have been seeing much better results across the board with Claude, and I wonder if open ai has been more focused on scale while Claude is doing larger more expensive models to get ahead.

It's crazy that it just tries to bruteforce it by picking numbers, and in your case it took more steps before concluding a success/failure, which seems quite to be random to me, or at least dependent on something.

What's clear is that it doesn't have any idea about mathematical deduction and induction – a real chain-of-thought which kids learn in 5th grade.

  • Lots of people don’t either. I think it probably just needs more 5th grade math problems in the rlhf corpus :)

    • It certainly needs them, but nothing will stop openai from making marketing claims like this today:

      "places among the top 500 students in the US in a qualifier for the USA Math Olympiad (AIME)"

      Like the top 500 students in the US are just popping random numbers into the problems, lol