Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT makes learning fun again

vipshek.com

Post reply on HN
Print view View original

71–80 of 243 posts

Re: GPT makes learning fun again

#71

Post by krainboltgreene »

LASR wrote: post #64
devjab wrote: post #7

I'm in two minds about it. On one hand the internet (in general) has become so hard to find information on, and I agree with the author that GPT is a breath of fresh air. On the other hand I've seen GPT fail so miserably at topics that I'm knowledge about that I have a very hard time trusting anything it tells me. I'm not sure what the answer really is, but I'm not sure it's GPT. I wish we could go back to having sea…

I want to use this comment to state one thing, not directly addressed to you. Stop using GPT as a database! GPT is far more useful a reasoning engine that can accumulate fuzzy data and then provide various views or transformation of that data. So asking GPT to parse a Wikipedia page and then asking it to teach you from it - this is a much more successful usage than what the author in the original article is doing. It…

> GPT is far more useful a reasoning engine

Hilarious to read this advice when GPT, by it's own designers, cannot reason.

Re: GPT makes learning fun again

#72

Post by thefz »

simonw wrote: post #24
devjab wrote: post #7

I'm in two minds about it. On one hand the internet (in general) has become so hard to find information on, and I agree with the author that GPT is a breath of fresh air. On the other hand I've seen GPT fail so miserably at topics that I'm knowledge about that I have a very hard time trusting anything it tells me. I'm not sure what the answer really is, but I'm not sure it's GPT. I wish we could go back to having sea…

"I'm not sure what the answer really is, but I'm not sure it's GPT." My suggestion is to stick with it and get a feel for what it's good at. I've found that after a few months of using ChatGPT every day I've developed a pretty solid intuition for which questions are likely to get good answers and which are likely to trigger hallucinations. It's difficult to describe what those intuitions are though! One rule of thumb…

> One rule of thumb I've developed: if something is likely to be "common knowledge" - if it's something that is likely to have been discussed accurately on the internet by many different people - then ChatGPT is very likely to answer questions about it accurately.

If so, this information is already easy to find, making GPT redundant.

Re: GPT makes learning fun again

#73

Post by pulvinar »

chx wrote: post #61
p-e-w wrote: post #47

Earlier quoted context omitted.

Do you have any evidence that human minds work substantially different from that?

Yes. Human minds often craft sentences which contain words together which never occurred in the same sentence before, not even close: > There was a boy called Eustace Clarence Scrubb, and he almost deserved it > Everything starts somewhere, although many physicists disagree. > It was a nice day. All the days had been nice. There had been rather more than seven of them so far, and rain hadn't been invented yet > My fa…

It's easy to cherry pick from the vast human repertoire. Here's a sample from GPT4, where I picked one from a total of two:

> The man on the moon fell off his ladder one Tuesday, a common enough occurrence that nobody really paid it any mind. Truth is, gravity's always been a bit of a show-off, even in the star-dusted emptiness of space.

Re: GPT makes learning fun again

#74

Post by andai »

simonw wrote: post #70
andai wrote: post #69

Earlier quoted context omitted.

GPT-3 or 4? Re: reasoning, apparently it gives much better performance if you ask it to write out its thought process step by step (because it has no "internal" thought process; it must be externalized).

Yeah, that sounds like a GPT-3.5 problem to me. I wouldn't trust 3.5 to write me an Nginx config, but I'd give 4 a shot at it. I just tried using GPT-4 to translate a random htaccess file I found to nginx and it seemed to do a good initial job: https://gist.github.com/simonw/8174f653a0c08c120830c56332054...

I tried your prompt and it works with 3.5 too, but I'm not qualified to verify the output (75% of it looks the same to me though).

Re: GPT makes learning fun again

#75

Post by rapsacnz »

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.

Re: GPT makes learning fun again

#76

Post by burglins »

LASR wrote: post #64
devjab wrote: post #7

I'm in two minds about it. On one hand the internet (in general) has become so hard to find information on, and I agree with the author that GPT is a breath of fresh air. On the other hand I've seen GPT fail so miserably at topics that I'm knowledge about that I have a very hard time trusting anything it tells me. I'm not sure what the answer really is, but I'm not sure it's GPT. I wish we could go back to having sea…

I want to use this comment to state one thing, not directly addressed to you. Stop using GPT as a database! GPT is far more useful a reasoning engine that can accumulate fuzzy data and then provide various views or transformation of that data. So asking GPT to parse a Wikipedia page and then asking it to teach you from it - this is a much more successful usage than what the author in the original article is doing. It…

I'm curious - how do you pass the article to GPT? Are you doing any formatting?

Re: GPT makes learning fun again

#77

Post by throwaway675309 »

hammyhavoc wrote: post #65
LASR wrote: post #64

Earlier quoted context omitted.

I want to use this comment to state one thing, not directly addressed to you. Stop using GPT as a database! GPT is far more useful a reasoning engine that can accumulate fuzzy data and then provide various views or transformation of that data. So asking GPT to parse a Wikipedia page and then asking it to teach you from it - this is a much more successful usage than what the author in the original article is doing. It…

Is it? I couldn't even get it to figure out an NGINX config, despite feeding it the documentation and URL rewrites it would need, and the prior Apache .htaccess file. Spent days on it. Consulted with people who know more than me about prompt engineering. Nope. Reasoning is not its strong point, IMO. It's a next-word prediction model, why would it be? It's doing what an LLM does. Frequently, nonsensically.

I've actually had great success with the automation of boiler plate DevOps nonsense using GPT-4, including: GitHub actions, Caddy scripts, Docker files, etc.

Every second that I didn't have to:

- go look up a similar problem on Google

- open three or four stack overflow tabs

- read through the stack overflow links

- copy out the answer

- change all the variables to match variable names that I want

All of this represents a huge time saver for me. I'm honestly baffled that people lack the ability to use LLMs in a productive and optimal manner.

Re: GPT makes learning fun again

#78

Post by waterhouse »

chazeon wrote: post #9

I really found asking GPT to put a math concept under a physics context very helpful for me. As a computational physics student, that is really how I understand math and the world. Only very few textbooks can help me with this. From [ Make Something Wonderful: Steve Jobs in His Own Words ][1], Steve once said in a interview in 1983: > The problem was, you can't ask Aristotle a question. And I think, as we look toward…

You might like the quote from Vladimir Arnold: "Mathematics is a part of physics. Physics is an experimental science, a part of natural science. Mathematics is the part of physics where experiments are cheap."

Re: GPT makes learning fun again

#79

Post by consp »

throwaway675309 wrote: post #77
hammyhavoc wrote: post #65

Earlier quoted context omitted.

Is it? I couldn't even get it to figure out an NGINX config, despite feeding it the documentation and URL rewrites it would need, and the prior Apache .htaccess file. Spent days on it. Consulted with people who know more than me about prompt engineering. Nope. Reasoning is not its strong point, IMO. It's a next-word prediction model, why would it be? It's doing what an LLM does. Frequently, nonsensically.

I've actually had great success with the automation of boiler plate DevOps nonsense using GPT-4, including: GitHub actions, Caddy scripts, Docker files, etc. Every second that I didn't have to: - go look up a similar problem on Google - open three or four stack overflow tabs - read through the stack overflow links - copy out the answer - change all the variables to match variable names that I want All of this represe…

Did you learn anything in the process? You'd still have to over the output and understand it, otherwise nothing has changed except the method of producing something you don't understand.

Re: GPT makes learning fun again

#80

Post by WA »

kccqzy wrote: 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…

I agree, especially if you consider these were the questions on OP's mind:

> just out of curiosity, I wanted to learn more. I get that LEDs consume less energy and release less heat, and that they're made using semiconductors. But what kinds of semiconductors? How do semiconductors work in general, anyway?

And they proceed to type "LED" into Google. Why not "led what kind of semiconductor" and "how do semiconductors work in leds"?

I assume, OP didn't write "LED" in the ChatGPT text box without any context either.

Post reply on HN