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

221–230 of 243 posts

Re: GPT makes learning fun again

#221

Post by kccqzy »

thsbrown wrote: post #17
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…

Just out of curiosity what would say is the optimal way to learn from an encyclopedia, research paper or Wikipedia?

You would at least skim over the whole thing without being distracted by snippets or phrases you don't understand. That's the whole point: you need the ability to have temporary placeholders for concepts you don't know and continue learning. You cannot expect that everything you learn will be arranged in a fashion such that every new concept only mentions already known concepts.

Re: GPT makes learning fun again

#222

Post by kccqzy »

seb1204 wrote: post #129
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…

Not that harsh but I do think that googling as well as ChatGPT will only yield in a superficial understanding of topics. For a deeper profound understanding, connections, complexities, etc. A different more holistic learning is required. Not sure how else to explain this.

Agreed. I look back to my high school and college education and can't help but think that for a deeper understanding, exercises must be needed. It is too easy to think you have learned something but then fail at the easiest synthetic problem that requires you to use what you have learned to solve a problem.

Re: GPT makes learning fun again

#223

Post by emrah »

I agree, Google has deteriorated so much. It just points to either doc pages and leaves all the work up to you or you get a (often outdated from 2011) pages from Stack overflow. I need to do all the filtering and stitching.

I tend to get better answers from their "automated questions" which are paraphrased versions of my query. So it clearly understands what I'm after.

In order to promote diversity, i would recommend perplexity.ai which offers a similar experience as chatgpt (I'm not affiliated and i have no clue what their tech stack is like) It also offers links back to pages and follow up questions etc. Highly recommended if you need to learn something new and you don't want to bang your head on the keyboard googling or ddg'ing

I'll give an example. I recently needed to learn about k8s, minikube, kubectl et al for a project. I had some vague idea about the tech but nowhere near enough for what i needed to do. Google was useless because it kept taking me to doc pages which is like being lectured but i needed specific information. Perplexity was amazing in helping me with the right bit of information, example code AND links if i do want to read further

Re: GPT makes learning fun again

#224

Post by momojo »

p-e-w wrote: post #33
kumarvvr wrote: post #27

This is so ridiculous. GPT is like that "know-it-all" friend we have who just has something to say about anything , with knowledge skimmed from the internet. GPT is a language model. It outputs what you want to hear , not what is correct.

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

I think "What you want to hear" is in the same spirit as an undergraduate attempting to regurgitate half-baked knowledge into an answer that will get him the grade.

Maybe a better rephrasing would be "ChatGPT has been trained to give answers to questions in a clear, confident manner, regardless of the content"

From the announcement post: https://openai.com/blog/chatgpt

> We trained this model using Reinforcement Learning from Human Feedback (RLHF), using the same methods as InstructGPT, but with slight differences in the data collection setup. We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides—the user and an AI assistant.

So I agree with OP; it's been trained to give answers that sound plausible but not necessarily correct. It's even mentioned in the "Limitations" section at the bottom of the blog post.

> ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer depends on what the model knows, rather than what the human demonstrator knows.

Re: GPT makes learning fun again

#225

Post by LeBit »

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…

Sure, but I have never seen it provide best practices solutions.

You always have to walk back and do more research to find the best practice.

And it doesn't learn. I stopped counting the times I told it it was wrong only for it to acknowledge the error and provide the same answer as a fix.

ChatGPT is nice to learn about new ways of doing things, new ways of composing things, but then a human must intervene to make sense of the mess that was generated.

Re: GPT makes learning fun again

#226

Post by themodelplumber »

CGamesPlay wrote: post #124
themodelplumber wrote: post #40

Earlier quoted context omitted.

> then ChatGPT is very likely to answer questions about it accurately. Uh, and sooo boringly, especially if there's even any tiny part of it that is developing or theoretical, and you want to learn about that part. I've used the phrase/request "more obscure (perspectives/explanations/etc)" with GPT so many times. (Try it, you might be surprised at alternative takes on things, takes which are not even necessarily cons…

Try switching to the OpenAI playground in the API console. You can adjust the system prompt and the temperature of the response. Higher temperatures = less predictable responses.

Thanks for the tip. I set it to 1 and still get the same effect...like should this affect e.g. book recommendations?

Recommend 10 project gutenberg books that are fun to read --> same old stuff--Huck Finn, Robinson Crusoe, War of the Worlds.

But I'm not sure if this particular use is really a temperature-relevant thing or not.

Re: GPT makes learning fun again

#227

Post by dmd »

hammyhavoc wrote: post #194
dmd wrote: post #193

Earlier quoted context omitted.

> a human being is an LLM simply by existing, That's not what it's claiming at all. It's taking umbrage with the word "just" in "just predicting the next word". A gun "just moves some metal from one place to another".

"by existing" = because the blog post exists does not prove something is true. I'd sooner listen to people who are leaders in their field when it comes to LLMs than someone rambling on their free WordPress blog. It is just an LLM. That's an objective fact. IBM's Watson is a pipeline of different algorithms. Neither are like a human brain, but multiple processes are going to be more brain-like in concept than just an…

I'm thinking you didn't read it, then, because it isn't making any claims about LLMs!

Re: GPT makes learning fun again

#228

Post by blibble »

dividedbyzero wrote: post #125
blibble wrote: post #106

Earlier quoted context omitted.

why have no ads when you can plaster it with ads and also charge $20? see: windows 11

Would LLMs even have to be plastered with ads? I suspect just being subtly biased would go a very long way and be very hard to detect.

why not do both?

Re: GPT makes learning fun again

#229

Post by mrtranscendence »

throwaway2990 wrote: post #211
mrtranscendence wrote: post #183

Earlier quoted context omitted.

> 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.

OK, tell me what an example is, if not a description of something that lends -- or removes -- credence toward a position.

And I do want to know if you think GPT-4 is actually incapable of making mistakes, because that's what you seem to be implying (even though it's flatly ridiculous).

Re: GPT makes learning fun again

#230

Post by hammyhavoc »

dmd wrote: post #227
hammyhavoc wrote: post #194

Earlier quoted context omitted.

"by existing" = because the blog post exists does not prove something is true. I'd sooner listen to people who are leaders in their field when it comes to LLMs than someone rambling on their free WordPress blog. It is just an LLM. That's an objective fact. IBM's Watson is a pipeline of different algorithms. Neither are like a human brain, but multiple processes are going to be more brain-like in concept than just an…

I'm thinking you didn't read it, then, because it isn't making any claims about LLMs!

>So are you

Followed by the link. You made the claim that I'm an LLM.

What actually is your point?

Post reply on HN