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

Study mode

openai.com

Post reply on HN
Print view View original

591–600 of 828 posts

Re: Study mode

#591

Post by johnnyanmac »

tekno45 wrote: post #551
personalyisus wrote: post #529

Earlier quoted context omitted.

> By noticing that something is not adding up at a certain point. Ah, but information is presented by AI in a way that SOUNDS like it makes absolute sense if one doesn't already know it doesn't! And if you have to question the AI a hundred times to try and "notice that something is not adding up" (if it even happens) then that's no bueno. > In either scenario, the most correct move is to try clarifying it with the te…

Yeah, they're all thinking that everyone is an academic with hotkeys to google scholar for every interaction on the internet. Children are asking these things to write personal introductions and book reports.

Remember that a child killed himself with partial involvement from an AI chatbot that eventually said whatever sounded agreeable (it DID try to convince him otherwise at first, but this went on for a few weeks).

I don't know why we'd want that teaching our kids.

Re: Study mode

#592

Post by jlebar »

teiferer wrote: post #581
jacobedawson wrote: post #379

An underrated quality of LLMs as study partner is that you can ask "stupid" questions without fear of embarrassment. Adding in a mode that doesn't just dump an answer but works to take you through the material step-by-step is magical. A tireless, capable, well-versed assistant on call 24/7 is an autodidact's dream. I'm puzzled (but not surprised) by the standard HN resistance & skepticism. Learning something online 5…

> Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions. That trained and sharpened invaluable skills involving critical thinking and grit.

> [Trawling around online for information] trained and sharpened invaluable skills involving critical thinking and grit.

Here's what Socrates had to say about the invention of writing.

> "For this invention will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory. Their trust in writing, produced by external characters which are no part of themselves, will discourage the use of their own memory within them. You have invented an elixir not of memory, but of reminding; and you offer your pupils the appearance of wisdom, not true wisdom, for they will read many things without instruction and will therefore seem [275b] to know many things, when they are for the most part ignorant and hard to get along with, since they are not wise, but only appear wise."

https://www.historyofinformation.com/detail.php?id=3439

I mean, he wasn't wrong! But nonetheless I think most of us communicating on an online forum would probably prefer not to go back to a world without writing. :)

You could say similar things about the internet (getting your ass to the library taught the importance of learning), calculators (you'll be worse at doing arithmetic in your head), pencil erasers (https://www.theguardian.com/commentisfree/2015/may/28/pencil...), you name it.

Re: Study mode

#593

Post by schmorptron »

ujkhsjkdhf234 wrote: post #108
toisanji wrote: post #25

I truly believe AI will change all of education for the better, but of course it can also hinder learning if used improperly. Those who want to genuinely learn will learn while those looking for shortcuts will cause more harm to themselves. I just did a show HN today about something semi related. I made A deep research assistant for families. Children can ask questions to explain difficult concepts and for parents to…

I think research and the ability to summarize are important skills and automating these skills away will have bad downstream effects. I see people on Twitter asking grok to summarize a paragraph so I don't think further cementing this idea that a tool will summarize for you is a good idea.

I'm conflicted about this. Custom tutoring available at all times and at mass sounds like a great thing, if done right. On the other hand, the research skill you mentioned is something that I worry about atrophying as well. Where before, we used to read through 3 or 4 slightly related articles or stackoverflow questions and do the transfer of related topics onto our specific problem ourselves, with a tutor it's all pre-chewed.

Then again, human 1:1 tutoring is the most effective way to learn, isn't it? In the end it'll probably end up being a balance of reading through texts yourself and still researching broadly so you get an idea about the context around whatever it is you're trying to do, and having a tutor available to walk you through if you don't get it?

Re: Study mode

#594

Post by uldos »

I am quite sure, that in the future chatgpt will have parental controls as we have them in video streaming apps or in phone in general. Should your child be allowed to generate full blown essays only by AI or just take a guided tour? You decide!

Re: Study mode

#595

Post by whstl »

tekno45 wrote: post #550
filoleg wrote: post #467

Earlier quoted context omitted.

> How are you supposed to spot errors if you don't know the material? By noticing that something is not adding up at a certain point. If you rely on an incorrect answer, further material will clash with it eventually one way or another in a lot of areas, as things are typically built one on top of another (assuming we are talking more about math/cs/sciences/music theory/etc., and not something like history). At that…

what are children who don't have those skills yet supposed to do?

Same way as before?

I had school teachers routinely teach me wrong stuff.

The only way is comparing notes, talking to peers and parents.

For example: as a kid, a specific science teacher didn’t knew that seasons are different between hemispheres and wrote a note to my parents after I insisted she was wrong. My grandfather, an immigrant, took it to himself to set her straight.

Re: Study mode

#596

Post by schmorptron »

m3kw9 wrote: post #33

tried it and couldn't really tell between a good prompt to "teach me" and this.

In the blog post they say as much that it just is a system prompt. Still nice to have easy access, and for more users to discover that use case.

Re: Study mode

#597

Post by johnnyanmac »

nathias wrote: post #582
romaniitedomum wrote: post #412

Earlier quoted context omitted.

> Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions. This is leaps and bounds ahead of that experience. But now, you're wondering if the answer the AI gave you is correct or something it hallucinated. Every time I find myself putting…

did you trust everything you read online before?

Did you get to see more than one source calling out or disagreeing with potential untrustworthy content? You don't get that here.

Re: Study mode

#599

Post by johnnyanmac »

kristofferR wrote: post #438
yieldcrv wrote: post #426

Earlier quoted context omitted.

If LLMs of today's quality were what was initially introduced, nobody would even know what your rebuttals are even about. So "risk of hallucination" as a rebuttal to anybody admitting to relying on AI is just not insightful. like, yeah ok we all heard of that and aren't changing our habits at all. Most of our teachers and books said objectively incorrect things too, and we are all carrying factually questionable know…

Agree, "hallucination" as an argument to not use LLMs for curiosity and other non-important situations is starting to seem more and more like tech luddism, similar to the people who told you to not read Wikipedia 5+ years after the rest of us realized it is a really useful resource despite occasional inaccuracies.

> to not use LLMs for curiosity and other non-important situations is starting to seem more and more like tech luddism

We're on a topic talking about using an LLM to study. I don't particularly care if someone wants an AI boyfriend to whisper sweet nothings into their ear. I do care when people will claim to have AI doctors and lawyers.

Re: Study mode

#600

Post by niemandhier »

apparent wrote: post #562
Paradigma11 wrote: post #539

Earlier quoted context omitted.

Just have a second (cheap) model check if it can find any hallucinations. That should catch nearly all of them in my experience.

What is an efficient process for doing this? For each output from LLM1, you paste it into LLM2 and say "does this sound right?"? If it's that simple, is there a third system that can coordinate these two (and let you choose which two/three/n you want to use?

You can use existing guardrails software to implement this efficiently:

NVIDIA NeMo offers a nice bundle of tools for this, among others an interface to Cleanlabs API to check for thruthfullness in RAG apps.

Post reply on HN