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

611–620 of 828 posts

Re: Study mode

#611

Post by SwtCyber »

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…

The freedom to ask "dumb" questions without judgment is huge, and it's something even the best classrooms struggle to provide consistently

Re: Study mode

#612

Post by EagnaIonat »

personalyisus wrote: post #529
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…

> 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…

> 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!

You have a good point, but I think it only applies to when the student wants to be lazy and just wants the answer.

From what I can see of study mode, it is breaking the problem down into pieces. One or more of those pieces could be wrong. But if you are actually using it for studying then those inconsistencies should show up as you try to work your way through the problem.

I've had this exact same scenario trying to learn Godot using ChatGPT. I've probably learnt more from the mistakes it made and talking through why it isn't working.

In the end I believe it's really good study practices that will save the student.

Re: Study mode

#613

Post by grodriguez100 »

CJefferson wrote: post #102
scarmig wrote: post #71

Earlier quoted context omitted.

I've found it excels at some things: 1) The broad overview of a topic 2) When I have a vague idea, it helps me narrow down the correct terminology for it 3) Providing examples of a particular category ("are there any examples of where v1 in the visual cortex develops in a disordered way?") 4) "Tell me the canonical textbooks in field X" 5) Posing math exercises 6) Free form branching--while talking about one topic, I…

These things are moving so quickly, but I teach a 2nd year combinatorics course, and about 3 months ago I tried th latest chatGPT and Deepseek -- they could answer very standard questions, but were wrong for more advanced questions, but often in quite subtle ways. I actually set a piece of homework "marking" chatGPT, which went well and students seemed to enjoy!

> I actually set a piece of homework "marking" chatGPT, which went well and students seemed to enjoy!

This. This should be done everywhere. It is the best way to let students see first hand that LLM output is useful, but can be (and often is) wrong.

If people really understands that, everything will be better.

Re: Study mode

#614

Post by CJefferson »

p1esk wrote: post #315
CJefferson wrote: post #102

Earlier quoted context omitted.

These things are moving so quickly, but I teach a 2nd year combinatorics course, and about 3 months ago I tried th latest chatGPT and Deepseek -- they could answer very standard questions, but were wrong for more advanced questions, but often in quite subtle ways. I actually set a piece of homework "marking" chatGPT, which went well and students seemed to enjoy!

When you say the latest chatGPT, do you mean o3?

Whatever was best on a paid account 3 months ago. I was quite disappointed to be honest, based on what I had been hearing.

Re: Study mode

#615

Post by SwtCyber »

apparent wrote: post #564
ramraj07 wrote: post #441

Earlier quoted context omitted.

What exactly did 2025 AI hallucinate for you? The last time I've seen a hallucination from these things was a year ago. For questions that a kid or a student is going to answer im not sure any reasonable person should be worried about this.

ChatGPT hallucinates things all the time. I will feed it info on something and have a conversation. At first it's mostly fine, but eventually it starts just making stuff up.

I've found that giving it occasional nudges (like reminding it of the original premise) can help keep it on track

Re: Study mode

#616

Post by Barbing »

ramraj07 wrote: post #441
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…

What exactly did 2025 AI hallucinate for you? The last time I've seen a hallucination from these things was a year ago. For questions that a kid or a student is going to answer im not sure any reasonable person should be worried about this.

>Thanks all for the replies, we’re hardcoding fixes now

-LLM devcos

Jokes aside, get deep into the domains you know. Or ask to give movie titles based on specific parts of uncommon films. And definitely ask for instructions using specific software tools (“no actually Opus/o3/2.5, that menu isn’t available in this context” etc.).

Re: Study mode

#617

Post by johnnyanmac »

safety1st wrote: post #572
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…

Firstly, I think skepticism is a healthy trait. It's OK to be a skeptic. I'm glad there are a lot of skeptics because skepticism is the foundation of inquiry, including scientific inquiry. What if it's not actually Zeus throwing those lightning bolts at us? What if the heliocentric model is correct? What if you actually can't get AIDS by hugging someone who's HIV positive? All great questions, all in opposition to th…

>So is this really a productivity win or is it just good feels?

Fairly recent study on this: LLM's made developers slightly less productive, but the developers themselves felt more productive with them: https://www.theregister.com/2025/07/11/ai_code_tools_slow_do...

There is definitely this pain point that some people talk about (even in this thread) on how "well at least AI doesn't berate me or reject my answer for bureaucratic reasons". And I find that intriguing in a community like this. Even some extremely techy people (or especially?) just something just want to at best feel respected, or at worst want to have their own notions confirmed by someone they deem to be "smart".

>I don't question the potential of the tech, but I do question the direction that Big Tech may take it, because they're literal repeat offenders at this point.

And that indeed is my biggest reservation here. Even if AI can do great things, I don't trust the incentive models OpenAI has. Instead of potentially being this bastion of knowledge, it may be yet another vector of trying to sell you ads and steal your data. My BOTD is long gone now.

Re: Study mode

#618

Post by SwtCyber »

schmorptron wrote: post #584

Oh, that's pretty good! I've been doing this with various LLMs already, making elaborate system prompts to turn them into socratic style teachers or in general tutors that don't just straight up give the answer, and have generally been impressed with how well it works and how much I enjoy it. The only thing to watch out for is when you're talking about something you don't already know well it becomes harder to spot h…

For the "brain atrophy" concern: I've thought about that too. My guess is that it's less about using tools and more about how we use them

Re: Study mode

#619

Post by _flux »

noosphr wrote: post #563
UltraSane wrote: post #560

Earlier quoted context omitted.

Job's diet didn't kill him. Not getting his cancer treated was what killed him.

Yes, we also covered that jumping off buildings doesn't kill people. The landing does.

Indeed if you're a base jumper with a parachute, you might survive the landing.

Ackshually, this seems analogous to Job's diet and refusal of cancer treatment! And it was the cancer that put him at the top of the building in the first place.

Re: Study mode

#620

Post by friendzis »

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…

LLMs, by design, are peak Duning-Kruegers, which means they can be any good of a study partner for basic introductory lessons and topics. Yet they still require handholding and thorough verification, because LLMs will spit out factually incorrect information with confidence and will fold on correct answers when prodded. Yet the novice does not posses the skill to handhold the LLM. I think there's a word for that, but chadgbt is down for me today.

Furthermore, forgetting curve is a thing and therefore having to piece information together repetitively, preferably in a structured manner, leads to a much better information retention. People love to claim how fast they are "learning" (more like consuming tiktoks) from podcasts at 2x speed and LLMs, but are unable to recite whatever was presented few hours later.

Third, there was a paper circulating even here on HN that showed that use of LLMs literally hinder brain activation.

Post reply on HN