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

101–110 of 243 posts

Re: GPT makes learning fun again

#101

Post by chx »

simonw wrote: post #66
chx wrote: post #61

Earlier quoted context omitted.

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…

"Human minds often craft sentences which contain words together which never occurred in the same sentence before, not even close" Weirdly, LLMs do that too. Have you heard of the "Let’s be bear or bunny" pattern? My iPhone hallucinated that the other day, running a LLM directly on the phone! https://simonwillison.net/2023/May/1/lets-be-bear-or-bunny/

> Weirdly, LLMs do that too.

Yes but those are as every other thing they emit, indeed , "Let’s be bear or bunny", I heard it called AI hallucination I personally like to call it word salad.

Re: GPT makes learning fun again

#102

Post by danielbln »

somethoughts wrote: post #96
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. Th…

A big benefit is that there are already plenty ok-ish open source LLMs out there that you can hook up to various information sources. Even if OpenAI flips the ad switch tomorrow, you can still run those by yourself. We didn't really have that option with search engines.

Re: GPT makes learning fun again

#103

Post by enlyth »

somethoughts wrote: post #96
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. Th…

I actually don't mind paying the $20/mo or whatever if it means no ads, hopefully this turns out to be a viable business model for them. Also, first company with an uncensored LLM that doesn't reply "As an AI language model" will get my money.

Re: GPT makes learning fun again

#104

Post by danielbln »

akeck wrote: post #8

Fun with caveats I'm finding. Today I asked for an outline of DevSecOps concept based on CISA recommendations. The CISA doc it referenced doesn't actually exist.

For something like that you really want to use GPT3/4 hooked up to search, e.g. https://www.phind.com/search?q=give+me+an+outline+of+DevSecO...

Re: GPT makes learning fun again

#105

Post by rolisz »

ChatGTP wrote: post #92
rolisz wrote: post #87

Earlier quoted context omitted.

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

I have a finite amount of time. I can choose to learn and know more about the software that I'm developing and make the software better, or I can spend some amount of time to learn the DevOps part, or some mix in between. In some cases, the ratio is 90:10 in favor of software development.

Re: GPT makes learning fun again

#106

Post by blibble »

enlyth wrote: post #103
somethoughts wrote: post #96

Earlier quoted context omitted.

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. Th…

I actually don't mind paying the $20/mo or whatever if it means no ads, hopefully this turns out to be a viable business model for them. Also, first company with an uncensored LLM that doesn't reply "As an AI language model" will get my money.

why have no ads when you can plaster it with ads and also charge $20?

see: windows 11

Re: GPT makes learning fun again

#107

Post by therein »

LASR wrote: post #98
throwaway675309 wrote: post #77

Earlier quoted context omitted.

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 su…

I agree. I often use it as if it is a code generator with a decent grasp of human language.

Here is what I asked it to do the other day, and it just did it right away and got it entirely right.

> Write async tokio Rust code that takes in a Vec, writes it to a temporary file, calls /usr/bin/svc infer pathToTemporaryFile, reads and deletes temporaryFile+".out" and returns Result> containing the contents of temporaryFile+".out"

I knew what I wanted, I could have written it myself, there was no unknown but it took fewer keystrokes and honestly when asked to write small components like this with pedantic detail, it does an incredible job and the output is easy to validate quickly.

Re: GPT makes learning fun again

#108

Post by SanderNL »

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.

> It's a next-word prediction model, why would it be?

If you want to make accurate predictions, you'll need reasoning or at least some process that approximates it.

"There a no bananas. Max is looking for bananas. Will he be successful: [yes/no]"

Re: GPT makes learning fun again

#109

Post by input_sh »

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.

Saying that DevOps tooling changes every year is absolute nonsense. The tooling is fairly standardised nowadays (Docker, Kubernetes, Ansible, Terraform, Prometheus, CI/CD tool of your choice) and every part of it is over half a decade old.

ChatGPT will only help you with the simplest of tasks, and even then you're gonna fail if you don't know to correct it. If you go beyond the most basic of the tasks you can learn how to do in a few hours, good luck fitting them in a chat prompt.

Re: GPT makes learning fun again

#110

Post by SanderNL »

thefz wrote: post #72
simonw wrote: post #24

Earlier quoted context omitted.

"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.

I think it's more about being more confident that GPT is working with at least a base of semi-accurate knowledge.

You can ask it to "combine" knowledge in "novel" ways that are not discussed verbatim on the web. It's not groundbreaking reasoning by any means, but it can be very useful. ("My ridiculously specific question about model X83844-QQ combined with random factor X")

Post reply on HN