Live data from Hacker News

GPT makes learning fun again

vipshek.com

211–220 of 243 posts

Re: GPT makes learning fun again

#211

Earlier quoted context omitted.

[flagged]

> Every time someone claims ChatGPT doesn’t work they cannot give concrete examples. So I don’t believe you sorry. Are you implying that ChatGPT always works, and that every time someone says it didn't work, they're lying? This feels like a joke to me. The other day it gave me the wrong code to compute indices for a Delta table, possibly because that capability didn't exist in the library it was using when the model…

Lol I’m not sure you understand what an example is.

Re: GPT makes learning fun again

#212

Earlier quoted context omitted.

[flagged]

Maybe you're downvoted for calling a group of people liars rather than for liking AI.

Every single thread someone claims it doesn’t work. And in every thread I see comments asking for examples. And the OP can never give an example. So yes until people can provide reproducible examples to see it fail. They are liars.

Re: GPT makes learning fun again

#213

Earlier quoted context omitted.

Maybe you're downvoted for calling a group of people liars rather than for liking AI.

Every single thread someone claims it doesn’t work. And in every thread I see comments asking for examples. And the OP can never give an example. So yes until people can provide reproducible examples to see it fail. They are liars.

Your reasoning is bad here. You're jumping to uncharitable conclusions without evidence, when there are several other perfectly reasonable explanations for that behavior.

Re: GPT makes learning fun again

#214

Earlier quoted context omitted.

Every single thread someone claims it doesn’t work. And in every thread I see comments asking for examples. And the OP can never give an example. So yes until people can provide reproducible examples to see it fail. They are liars.

Your reasoning is bad here. You're jumping to uncharitable conclusions without evidence, when there are several other perfectly reasonable explanations for that behavior.

And yet still no one can give examples.

Re: GPT makes learning fun again

#215

Earlier quoted context omitted.

Your reasoning is bad here. You're jumping to uncharitable conclusions without evidence, when there are several other perfectly reasonable explanations for that behavior.

And yet still no one can give examples.

Or no one is willing to, which I find understandable for a number of reasons.

Re: GPT makes learning fun again

#217
post #13

You can downvote me but I think OP hasn't learned how to learn yet. If OP reads Wikipedia by understanding every sentence and clicking on every link, that's deliberately sabotaging his own learning. Attitudes like "I don't really feel like spelunking through a ton more articles" simply shows OP isn't interested in learning per se, just quick answers. OP learns in a way that's very child-like. When you are a five-year…

Asking simple questions is a great way to start, it doesn’t matter how old you are. I think Feynman and Schrödinger would agree. Certainly de Broglie would. You can go down as deeply as you like.

Right now, if the level involves advanced math, it’s better to switch to other sources at some point, but that will change.

You can ask GPT-4 to tutor you, also.

Re: GPT makes learning fun again

#218
post #91

I noticed a while back that the internet has made me terribly prone to skimming. It got to a point where I could hardly stand to read anything longer than a short news article. To learn anything useful on the internet, you pretty much have to skim. So much of the internet is so loaded with filler and BS that it is hardly worth reading at all. With ChatGPT, it’s incredibly refreshing to be able to ask a question and g…

It's interesting because that's my biggest gripe against ChatGPT, it's too verbose and very hard to skim through. Compared to stack overflow answers it'll be easily four times longer. Sure compared to for instance news website, it is less verbose, but those are easy to skim. I'm still able to read through well written text without skimming, though yes most of the texts I'll read I'll skim through, then go back and th…

Prepare a statement to copy paste at the start of every session asking it to respond in a concise way. And maybe include an example of how you want its response to look. I guarantee good results. Assuming we’re speaking of 4.

Re: GPT makes learning fun again

#219

Don't forget that GPT was trained on data from all the sources that failed you. So if we all collectively neglect them, and they fall over, we will lose many valuable resources. I think we need to think about how to keep these valuable sites going, because they are ultimately providing most of the value of the various available language models.

The sources didn’t fail. The point is, especially at the beginning, it’s easy to miss seeing the forest for all the trees.

Re: GPT makes learning fun again

#220
post #33

Earlier quoted context omitted.

> It outputs what you want to hear Nonsense. How could it possibly know "what you want to hear"?

Because we tell it what we want. "How do I do this" "How do I do that" "What is this" "What is that"

And it tries to give an answer that would be interpreted as a positive, rather than negative, reply.
Post reply on HN