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

521–530 of 828 posts

Re: Study mode

#521

Post by tayo42 »

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Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content

Leanring what is like that? MIT open courseware has been available for like 10 years with anything you could want to learn in college

Textbooks are all easily pirated

Re: Study mode

#522

Post by mpalmer »

I truly, truly do not get it. it's a system prompt. Do students not understand that they could do this before?

Sure, it was crafted by educational experts, but this is not a feature! It's a glorified constant!

Re: Study mode

#523

Post by y1n0 »

jimmaswell wrote: post #491
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 Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions.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…

> you're wondering if the answer the AI gave you is correct or something it hallucinated Regular research has the same problem finding bad forum posts and other bad sources by people who don't know what they're talking about, albeit usually to a far lesser degree depending on the subject.

Yes but that is generally public, with other people able to weigh in through various means like blog posts or their own paper.

Results from the LLM are your eyes only.

Re: Study mode

#524

Post by noosphr »

filoleg wrote: post #474
noosphr wrote: post #447

Earlier quoted context omitted.

Two days ago when my boomer mother in law tried to justify her anti-cancer diet that killed Steve Jobs. On the bright side my partner will be inheriting soon by the looks of it.

Not defending your mother-in-law here (because I agree with you that it is a pretty silly and maybe even potentially harmful diet), afaik it wasn’t the diet itself that killed Steve Jobs. It was his decision to do that diet instead of doing actual cancer treatment until it was too late.

Given that I've got two people telling me here "ackshually" I guess it may not be hallucinations and just really terrible training data.

Up next - ChatGPT does jumping off high buildings kill you?

>>No jumping off high buildings is perfectly safe as long as you land skillfully.

Re: Study mode

#525

Post by eviks »

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…

> Should we trust the information at face value without verifying from other sources? Of course not, that's part of the learning process.

It mostly isn't, the point of the good learning process is to invest time into verifying "once" and then add verified facts to the learning material so that learners can spend that time learning the material instead of verifying everything again.

Learning to verify is also important, but it's a different skill that doesn't need to be practiced literally every time you learn something else.

Otherwise you significantly increase the costs of the learning process.

Re: Study mode

#526

Post by ink_13 »

teleforce wrote: post #479
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…

Please check this excellent LLM-RAG AI-driven course assistant at UIUC for an example of university course [1]. It provide citations and references mainly for the course notes so the students can verify the answers and further study the course materials. [1] AI-driven chat assistant for ECE 120 course at UIUC (only 1 comment by the website creator): https://news.ycombinator.com/item?id=41431164

Given the propensity of LLMs to hallucinate references, I'm not sure that really solves anything

Re: Study mode

#527

Post by voidhorse »

czhu12 wrote: post #26

I'll personally attest: LLM's have been absolutely incredible to self learn new things post graduation. It used to be that if you got stuck on a concept, you're basically screwed. Unless it was common enough to show up in a well formed question on stack exchange, it was pretty much impossible, and the only thing you can really do is keep paving forward and hope at some point, it'll make sense to you. Now, everyone ba…

I haven't used LLMs too much for study yet, so maybe they really are force multipliers, but I completely disagree with your assessment of self-directed learning pre-llm, the paving forward part isn't so dire.

The internet, and esp. stack exchange is a horrible place to learn concepts. For basic operational stuff, sure that works, but one should mostly be picking up concepts form books and other long form content. When you get stuck it's time to do three things:

Incorporate a new source that covers the same material in a different way, or at least from a different author.

Sit down with the concept and write about it and actively try to reformulate it and everything you do/don't understand in your own words.

Take a pause and come back later.

Usually one of these three strategies does the trick, no llm required. Obviously these approaches require time that using an LLM wouldn't. I have a suspicion doing it this way will also make it stick in long term memory better, but that's just a hunch.

Re: Study mode

#528

Post by aabhay »

Isn’t this what “GPTs” was supposed to be? Why not just use that if this is essentially just a system prompt?

Re: Study mode

#529

Post by personalyisus »

filoleg wrote: post #467
tekno45 wrote: post #450

Earlier quoted context omitted.

How are you supposed to spot errors if you don't know the material? You're telling people to be experts before they know anything.

> 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…

> 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 teacher

A teacher that can randomly give you wrong information with every other sentence would be considered a bad teacher

Post reply on HN