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

91–100 of 243 posts

Re: GPT makes learning fun again

#91

Post by phh »

brokencode wrote: post #19

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 then to improve my global understanding, which I think is beneficial

Re: GPT makes learning fun again

#92

Post by ChatGTP »

rolisz wrote: post #87
consp wrote: post #79

Earlier quoted context omitted.

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.

If you're not DevOps, why bother learning whatever framework is used today, but which will be replaced by something else next year? I just want to get my stuff deployed and that's it.

Yeah that’s true, why bother actually knowing anything about the systems they run your software /s

Re: GPT makes learning fun again

#93

Post by lifeonlars »

Yiin wrote: post #86
thefz wrote: post #72

Earlier quoted context omitted.

> 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.

it being commonly discussed doesn't mean easily accessible. Personally ads and bad UI are main factors of my increased usage of gpt-4.

Is that just the problem that ChatGPT is solving? That we have most of the answers to everyone's questions on the web but that ads and SEO have made it impossible to access?

If so it seems like 1. that problem is of our own making and could be fixed without ChatGPT and 2. what will actually happen is that 'experts-exchange' and all the similar slightly scammy help sites and forums are going to try to stop LLMs from stealing their lunch.

Re: GPT makes learning fun again

#94

Post by underdeserver »

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…

Gell-Mann amnesia, in AI form. Wonderful! It's like learning a complex topic from reading the newspaper.

Re: GPT makes learning fun again

#95

Post by LASR »

krainboltgreene wrote: post #71
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…

> GPT is far more useful a reasoning engine Hilarious to read this advice when GPT, by it's own designers, cannot reason.

It can’t reason - as in there no internal memory or intelligence in there. But you can ask it to generate a reasoning chain as part of its output. And then extract that output and do something else with that. That’s the reasoning it can perform.

Look up the Sam Altman podcast with Lex. He specifically talks about reasoning engines.

Re: GPT makes learning fun again

#96

Post by somethoughts »

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…

As a follow on to those thoughts, I feel like ChatGPT is in the phase similar to that fleeting moment when search engines were maximally useable - before SEO was a thing and before Google "needed" to turn on the profitability spigot.

Its unclear to me how long we'll have before LLM Engine Optimization is a thing and OpenAI/MSFT "need" to turn on their LLM profitability spigot; and what ChatGPT will look like then.

That said, I'm curious as to whether technically LLMs are inherently more challenging to game than search engines.

Re: GPT makes learning fun again

#97

Post by lars512 »

I totally agree with the author, I find I'm finally able to ask about a range of new concepts, get them explained at my level, and dive deeper as curiosity warrants it.

It's also magical when you summarise the understanding you've reached back to it, and it can confirm or tweak it for you.

In other ways it's also nice to just pay for it and then to be in an advertising free space.

One critique is that when you ask it to compare things it's often too balanced or too positive/enthusiastic ("both are great for different reasons!") when what you want is a more sober analysis. But you can usually do some prompt management to adjust it back to a reasonable range.

Re: GPT makes learning fun again

#98

Post by LASR »

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…

> I'm honestly baffled that people lack the ability to use LLMs in a productive and optimal manner.

Huge +1.

I’ve got it to do a large part of my work for me by chaining some simple API calls.

The fundamental conceptual gap I see - people often ask it to do some “thinking”. Then are annoyed by the inaccurate output.

A simple example is doing word count and it getting the wrong answer very confidently.

Of course it sucks at that. It doesn’t have a counter internally. But if you ask it to number each word in the input and output a list, then ask for the word count, it gets it right every time.

Almost like how a human might count words manually.

Re: GPT makes learning fun again

#99

Post by piaste »

the_duke wrote: post #53
brokencode wrote: post #19

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…

I have a standard copy n paste prompt that instructs it to keep answers concise and free of boilerplate. Otherwise ChatGPT is prone to injecting lots of filler text as well.

Care to share that prompt? I find the fillers and disclaimers very grating too.

Re: GPT makes learning fun again

#100

Post by p-e-w »

kerkeslager wrote: post #55
p-e-w wrote: post #22

Earlier quoted context omitted.

That is actually the killer feature of interactive AIs. People go on and on and on about "accuracy", completely ignoring that accuracy is irrelevant to 99.9% of things that humans do in their everyday lives. Simulating (positive) human interaction is far more impactful than getting facts correct.

What does it mean to have a positive interaction with someone who consistently tells you misinformation with a high degree of confidence?

If you don't already know the answer to that question, I doubt it would be possible to explain it to you. Looking for precise definitions of essential human qualities is a fool's errand.
Post reply on HN