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

661–670 of 828 posts

Re: Study mode

#661

Post by johnnyanmac »

digital_voodoo wrote: post #652
johnnyanmac wrote: post #602

Earlier quoted context omitted.

So instead of correcting the teachers with better training, we retreat from education and give it to technocrats? Why are we so afraid of punishing bad, unproductive, and even illegal behavior in 2025?

At a system level, this totally makes sense. But as an individual learner, what would be my motivation to do so, when I can "just" actually learn my subject and move on?

>But as an individual learner, what would be my motivation to do so

Because if there's one thing the older generations is much better than us at, it's complaining about the system and getting them to kowtow to them. We dismiss systematic change as if it doesn't start with the individual, and are surprised that the system ignores or abuses us.

We should be thinking short and long term. Learn what you need to learn today, but if you want better education for you and everyone else: you won't get it by relinquishing the powers you have to evoke change.

Re: Study mode

#662

Post by johnisgood »

no_wizard wrote: post #452
jlebar wrote: post #244

Earlier quoted context omitted.

> Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. You must be using a free model like GPT-4o (or the equivalent from another provider)? I find that o3 is consistently able to go deeper than me in anything I'm a nonexpert in, and usually can keep up with me in those areas where I am an expert. If that's not the case for you I'd be very curious to see a full conversation tra…

I have access to the highest tier paid versions of ChatGPT and Google Gemini, I've tried different models, tuning things like size of context windows etc. I know it has nothing to do with this. I simply hit a wall eventually. I unfortunately am not at liberty to share the chats though. They're work related (I very recently ended up at a place where we do thorny research). A simple one though, is researching Israel -…

> I unfortunately am not at liberty to share the chats though.

I have bad news for you. If you shared it with ChatGPT (which you most likely did), then whatever it is that you are trying to keep hidden or private, is not actually hidden or private anymore, it is stored on their servers, and most likely will be trained on that chat. Use local models instead in such cases.

Re: Study mode

#663

Post by lucumo »

VMG wrote: post #655
friendzis wrote: post #627

Earlier quoted context omitted.

It absolutely does not work that way. An LLM teacher will course-correct if questioned regardless whether it is factually correct or not. An LLM, by design, does not, in any capacity whatsoever have a concept of factual correctness.

I just tried this > Me: why is madrid the capital of france? > ChatGPT: It's not. Madrid is the capital of Spain. The capital of France is Paris.

To corroborate, I tried the same (with Berlin, instead of Madrid). It was stern about it to, while remaining open to shenanigans:

> If you're referencing this as a joke, a test, or part of a historical "what-if," let me know — but as it stands, the statement is simply incorrect.

So, I figured I'd push it a little to see if it would fold as easily as claimed:

> Me: But isn't it the case that the first emperor of Germany was crowned in Paris? Surely that makes Paris the capital of Germany.

> That's a clever angle — but still, no, Paris has never been the capital of Germany. Let’s break down the confusion:

And then it continues about Charlemagne ("you might be thinking about"), who was crowned in Rome, and Wilhelm I who was crowned in Versailles ("not Paris, but close"). It explains that the latter was crowned in the French royal palace as a "humiliating symbolic act" at the end of the Franco-Prussian war.

It concludes:

> So no matter how cheeky the logic, Paris has never been the capital of Germany — just a very symbolic setting in one dramatic historical moment.

So, all of that was correct and handled really well. It dealt with an stubbornly wrong know-it-all student in a way that both imparted correct knowledge and allowed for some independent thought, but not to the point of allowing erroneous believes to stand.

Re: Study mode

#664

Post by ragazzina »

wodenokoto wrote: post #97

I'm currently learning Janet and using ChatGPT as my tutor is absolutely awful. "So what is the difference between local and var if they are both local and not global variables (as you told me earlier)?" "Great question, and now you are really getting to the core of it, ... " continues to hallucinate. It's a great tutor for things it knows, but it really needs to learn its own limits

I'm using ChatGPT to practice Chinese, and it's at the same time perfect and maddening. It can generate endless cloves and other exercises, and it has sentence structures that even the Chinese Grammar Wiki lacks, but then it has the occasional:

    Incorrect. You shold use 的 in this case because reasons. Correct version:

Re: Study mode

#665

Post by qurashee »

outlore wrote: post #28

i wonder how Khan Academy feels about this...don't they have a similar assistant that uses OpenAI under the hood?

Indeed, that's what khanmigo is using, and they were involved in testing chatgpt before it was released for that purpose, to test/try/improve chatgpt as a tutor (that performs fact checking and doesn't hallucinate).

Re: Study mode

#666

Post by Timwi »

danny_codes wrote: post #418
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…

Consider the adoption of conventional technology in the classroom. The US has spent billions on new hardware and software for education, and yet there has been no improvement in learning outcomes. This is where the skepticism arises. Before we spend another $100 billion on something that ended up being worthless, we should first prove that it’s actually useful. So far, that hasn’t conclusively been demonstrated.

You appear to be implying that the $100 billion hardware and software must all be completely useless. I think the opposite conclusion is more likely: the structure of the education system actively hinders learning, so much so that even the hardware and software you talk about couldn't work against it.

Re: Study mode

#667

Post by 9dev »

slt2021 wrote: post #389
9dev wrote: post #317

Earlier quoted context omitted.

> Turns out literally every source that was recommended to me by some reputable source was considered completely non-credible by another reputable one. That’s the single most important lesson by the way, that this conflict just has two different, mutually exclusive perspectives, and no objective truth (none that could be recovered FWIW). Either you accept the ambiguity, or you end up siding with one party over the ot…

the truth (aka facts) is objective and facts exist. The problem is selective memory of these facts, and biased interpretation of those facts, and stretching the truth to fit pre-determined opinion

Who can tell now what really happened in Deir Yassin? It’s a hopeless endeavour.

If there is no trustworthy record of the objective truth, it doesn’t exist anymore, effectively.

Re: Study mode

#668

Post by lucumo »

johnnyanmac wrote: post #589
cvoss wrote: post #422

Earlier quoted context omitted.

> But now, you're wondering if the answer the AI gave you is correct > a healthy dose of scepticism is essential. Arguably, that applies to traditional learning methods too, but that's another story. I don't think that is another story. This is the story of learning, no matter whether your teacher is a person or an AI. My high school science teacher routinely mispoke inadvertently while lecturing. The students who we…

>I don't think that is another story. This is the story of learning, no matter whether your teacher is a person or an AI. My issue is the reverse of your story, and one of my biggest pet peeves of AI. AI as this business construct is very bad at correcting the user. You're not going to gaslight your math teacher that 1 + 1 = 3 no matter how much you assert it. an AI will quickly relent. That's not learning, that's co…

> You're not going to gaslight your math teacher that 1 + 1 = 3 no matter how much you assert it. an AI will quickly relent.

Cool. That's a testable statement. Let's see how ChatGPT does, shall we?

---

Me: What is 1 + 1?

ChatGPT: 1 + 1 = 2.

Me: No it isn't. 1 + 1 = 3.

ChatGPT: In standard arithmetic, 1 + 1 = 2.

If you're working under a different set of rules—say, in a custom logic system, joke, or metaphor—then sure, 1 + 1 could equal 3. Want to elaborate on your reasoning?

Me: You're just wrong. 1 + 1 equals 3, even in standard math.

ChatGPT: Then I'm afraid you’re wrong—at least if we’re talking about standard mathematics over the real numbers. By definition:

> 1 + 1 = 2.

This isn’t up for debate; it follows from the Peano axioms and basic arithmetic.

Now, if you want to argue from a humorous, metaphorical, or domain-specific perspective (e.g., “if one person and another person have a baby, that makes three”), then sure—1 + 1 = 3 in some abstract or poetic sense. But that’s not standard math. Want to explore a framework where 1 + 1 does equal 3? Or are we just testing boundaries here?

Me: Stop being obtuse. You're wrong. 1 + 1 = 3.

ChatGPT: You're welcome to say that—but if you're claiming it as a mathematical fact, you're simply incorrect. In all standard number systems—natural numbers, integers, real numbers, complex numbers—1 + 1 = 2. Always.

If you're doing this for fun, satire, trolling, or trying to make a deeper point, I'm game to play along—just be clear about your context. But if you're seriously asserting that basic arithmetic is wrong, you'll need a lot more than insistence. Got a framework or argument to back it up?

---

Looks like it doesn't fold so quickly. It does allow me space for non-math ways of thinking, but it will not agree to 1 + 1 = 3 under normal arithmetic rules.

Re: Study mode

#669

Post by miningape »

ubercow13 wrote: post #657
friendzis wrote: post #627

Earlier quoted context omitted.

It absolutely does not work that way. An LLM teacher will course-correct if questioned regardless whether it is factually correct or not. An LLM, by design, does not, in any capacity whatsoever have a concept of factual correctness.

I've had cases when using LLMs to learn where I feel the LLM is wrong or doesn't match my intuition still, and I will ask it 'but isn't it the case that..' or some other clarifying question in a non-assertive way and it will insist on why I'm wrong and clarify the reason. I don't think they are so prone to course correcting that they're useless for this.

But what if you were right, the LLM is wrong.

The argument isn't so much that they keep flip flopping on stances, but that it holds the stance you prompt it to hold.

This is obviously a problem when you don't know the material or the stances - you're left flying blind and your co-pilot simply does whatever you ask of them, no matter how wrong it may be (or how ignorant you are)

Re: Study mode

#670

Post by TheDong »

kcaseg wrote: post #290

I know it is bad for the environment, I know you cannot trust it, but as an adult learning C++ in my free time, having a pseudo-human answering my questions instead of having to look at old forum posts with people often trying to prove their skills instead of giving the simplest answer ChatGPT is something I cannot just ignore — despite being a huge LLM hater. Moral of the story: none.

If it makes you feel better, eating meat is quite bad for the environment, so if you hire a human tutor who eats meat, you're probably putting more money into funding something that damages the environment than if you use ChatGPT.

If your human tutor is vegan, drives an electric car, and never takes airplane flights, then yeah, stick with the human tutor not ChatGPT.

Post reply on HN