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

131–140 of 828 posts

Re: Study mode

#131

Post by dcbb65b2bcb6e6a »

sejje wrote: post #125
dcbb65b2bcb6e6a wrote: post #109

Earlier quoted context omitted.

> and it was wrong sometimes, sure. A known limitation. But that's the entire problem and I don't understand why it's just put aside like that. LLMs are wrong sometimes, and they often just don't give you the details and, in my opinion, knowing about certain details and traps of a language is very very important, if you plan on doing more with it than just having fun. Now someone will come around the corner and say '…

It's not my experience that there are missing pieces as compared to anything else. Nobody can write an exhaustive tome and explore every feature, use, problem, and pitfall of Python, for example. Every text on the topic will omit something. It's hardly a criticism. I don't want exhaustive. The llm taught me what I asked it to teach me. That's what I hope it will do, not try to caution me about everything I could do w…

You are right and that's my point. To me it just feels like that too many people think LLMs are the holy grail for learning. No, you still have to study a lot. Yes, it can be easier than it was.

Re: Study mode

#132

Post by fkyoureadthedoc »

ZYbCRq22HbJ2y7 wrote: post #112
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…

> It used to be that if you got stuck on a concept, you're basically screwed No, not really. > 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. Your experience isn't universal. Some students learned how to do research in school.

They should have focused on social skills too I think

Re: Study mode

#133

Post by roadside_picnic »

My key to LLM study has been to always primarily use a book and then let the LLM allow you to help with formulae, ask questions about the larger context, and verify your understanding.

Helping you parse notation, especially in new domains, is insanely valuable. I do a lot of applied math in statistics/ML, but when I open a physics book the notation and comfort with short hand is a real challenge (likewise I imagine the reverse is equally as annoying). Having an LLM on demand to instantly clear up notation is a massive speed boost.

Reading German Idealist philosophy requires an enormous amount of context. Being able to ask an LLM questions like "How much of this section of Mainländer is coming directly from Schopenhauer?" is a godsend in helping understand which parts of the writing a merely setting up what is already agreed upon vs laying new ground.

And the most important for self study: verifying your understanding. Backtracking because you misunderstood a fundamental concept is a huge time sync in self study. Now, every time I read a formula I can go through all of my intuitions and understanding about it, write them down, and verify. Even a "not quite..." from an LLM is enough to make me realize I need to spend more time on that section.

Books are still the highest density information source and best way to learn, but LLMs can do a lot to accelerate this.

Re: Study mode

#134

Post by thimabi »

potatolicious wrote: post #98
Workaccount2 wrote: post #65

An acquaintance of mine has a start-up in this space and uses OpenAI to do essentially the same thing. This must look like, and may well be, the guillotine for him... It's my primary fear building anything on these models, they can just come eat your lunch once it looks yummy enough. Tread carefully

> "they can just come eat your lunch once it looks yummy enough. Tread carefully" True, and worse, they're hungry because it's increasingly seeming like "hosting LLMs and charging by the token" is not terribly profitable. I don't really see a path for the major players that isn't "Sherlock everything that achieves traction".

But what’s the future in terms of profitability of LLM providers?

As long as features like Study Mode are little more than creative prompting, any provider will eventually be able to offer them and offer token-based charging.

Re: Study mode

#135

Post by JoRyGu »

Is that not something that was already possible with basically every AI provider by prompting it to develop learning steps and not to provide you with a direct answer? I've used this quite a bit when learning new topics and pretty much every provider does this without a specialized model.

Re: Study mode

#136

Post by precompute »

eternauta3k wrote: post #29
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…

You can always ask in stack exchange, IRC or forums.

This is the way to go.

Re: Study mode

#137

Post by aethrum »

JoRyGu wrote: post #135

Is that not something that was already possible with basically every AI provider by prompting it to develop learning steps and not to provide you with a direct answer? I've used this quite a bit when learning new topics and pretty much every provider does this without a specialized model.

even chatgpt is just a chatgpt wrapper

Re: Study mode

#138

Post by Barrin92 »

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…

>Unless it was common enough to show up in a well formed question on stack exchange, it was pretty much impossible

sorry but if you've gone to university, in particular at a time when internet access was already ubiquitous, surely you must have been capable to find an answer to a programming problem by consulting documentation, manual, or tutorials which exist on almost any topic.

I'm not saying the chatbot interface is necessarily bad, it might be more engaging, but it literally does not present you with information you couldn't have found yourself.

If someone has a computer science degree and tells me without stack exchange they can't find solutions to basic problems that is a red flag. That's like the article about the people posted here who couldn't program when their LLM credits ran out

Re: Study mode

#139

Post by tptacek »

Neat! I've been doing MathAcademy for a couple months now, and macOS ChatGPT has been a constant companion, but it is super annoying to have to constantly tell it no, don't solve this problem, just let me know if the approach I used was valid.

Re: Study mode

#140

Post by precompute »

righthand wrote: post #10
jryio wrote: post #5

I would like to see randomized control group studies using study mode. Does it offer meaningful benefits to students over self directed study? Does it out perform students who are "learning how to learn"? What affect does allowing students to make mistakes have compared to being guided through what to review? I would hope Study Mode would produce flash card prompts and quantize information for usage in spaced repetit…

It doesn’t do any of that, it just captures the student market more. They want a student to use it and say “I wouldn’t have learned anything without study mode”. This also allows them to fill their data coffers more with bleeding edge education. “Please input the data you are studying and we will summarize it for you.”

Bingo. The scale they're operating at, new features don't have to be useful, they only need to look like they are for the first few minutes.
Post reply on HN