51–60 of 126 posts
Earlier quoted context omitted.
I’d expect the opposite. It’s not very good at precise problem solving but it’s very good at writing verbose flowery bullshit.
You can have it call out to python or some other runtime to help with that. It just needs to be able to turn a problem into code.
Using chain of thought [slightly modified] example from https://arxiv.org/abs/2201.11903 (ref'd in OP) Prompt: Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now? A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11. Q: The room has 19 chairs. We are using 10 and then bought 9 mor…
Would ChatGPT get this question correct?
Earlier quoted context omitted.
I’d expect the opposite. It’s not very good at precise problem solving but it’s very good at writing verbose flowery bullshit.
It can easily do mathematic functions and SAT syllabus. Despite the word problems, by assuming ChatGPT should easily be able to solve simple arithmetic.
Using chain of thought [slightly modified] example from https://arxiv.org/abs/2201.11903 (ref'd in OP) Prompt: Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now? A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11. Q: The room has 19 chairs. We are using 10 and then bought 9 mor…
Q: If you have 1 bucket that holds 2 gallons, and another bucket that holds 5 gallons, how many buckets do you have? Would ChatGPT get this question correct?
It's reasonably good with that type of question.
Earlier quoted context omitted.
I’d expect the opposite. It’s not very good at precise problem solving but it’s very good at writing verbose flowery bullshit.
It can easily do mathematic functions and SAT syllabus. Despite the word problems, by assuming ChatGPT should easily be able to solve simple arithmetic.
It really can’t do any novel thought though, which is necessary for mathematics. Language models are fundamentally limited here (even a 3 years old can easily follow some easy rules “ad infinitum”, like counting. Language models have a limited window for inference)
Earlier quoted context omitted.
Q: If you have 1 bucket that holds 2 gallons, and another bucket that holds 5 gallons, how many buckets do you have? Would ChatGPT get this question correct?
A: You have 2 buckets. It's reasonably good with that type of question.
I think this is evidence against the usefulness of standardized tests rather than support for ChatGPT
What I find more concerning is the 100% scores that ChatGPT has been able to achieve on AP CSA and APUSH, among others. It makes sense to teach 3rd graders 2+2, but if college board is creating "college level courses" with problems that can be easily solved through whats still a fairly new technology, we need to reevaluate what we're teaching in schools. So many AP courses are just memorization and identifying formul…
I don't get it. AP calculus is problems that can be easily solved with what is now very old technology. The point of an AP test isn't that the problems are so difficult.
Earlier quoted context omitted.
There is one argument against this though that is somehow brewing in my brain. The end goal is to internalize the subject so that you can extrapolate your own insights. "This happened in WWII so if these conditions starts to appear it risks to happen again". Just to take history as an example. All other subjects have similar examples. And to reach that kind of insight you need to start filling the brain with informat…
> "This happened in WWII so if these conditions starts to appear it risks to happen again". There is a reason why history repeats. This kind of learning never happens in human society. We currently have similar warning signs to WWII, but nobody cares. We are currently at the stage where if you express an opinion that does not agree with the approved narrative, you get downvoted/cancelled. But nobody cares.
Earlier quoted context omitted.
What I find more concerning is the 100% scores that ChatGPT has been able to achieve on AP CSA and APUSH, among others. It makes sense to teach 3rd graders 2+2, but if college board is creating "college level courses" with problems that can be easily solved through whats still a fairly new technology, we need to reevaluate what we're teaching in schools. So many AP courses are just memorization and identifying formul…
There is one argument against this though that is somehow brewing in my brain. The end goal is to internalize the subject so that you can extrapolate your own insights. "This happened in WWII so if these conditions starts to appear it risks to happen again". Just to take history as an example. All other subjects have similar examples. And to reach that kind of insight you need to start filling the brain with informat…
The part that ap fails to deliver on is the written portion, where it asks you to extrapolate your own insights. If chatgpt can solve the problem that should require human insight, is the prompt really testing students properly?