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

141–150 of 828 posts

Re: Study mode

#141

Post by fn-mote »

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.

I do a lot of research and independent learning. The way I translated “screwed” was “4-6 hours to unravel the issue”. And half the time the issue is just a misunderstanding.

It’s exciting when I discover I can’t replicate something that is stated authoritatively… which turns out to be controversial. That’s rare, though. I bet ChatGPT knows it’s controversial, too, but that wouldn’t be as much fun.

Re: Study mode

#142

Post by EGreg »

no_wizard wrote: post #49
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…

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

Try to red team blue team with it

Blue team you throw out concepts and have it steelman them

Red team you can literally throw any kind of stress test at your idea

Alternate like this and you will learn

A great prompt is “give me the top 10 xyz things” and then you can explore

Back when I was in 2006 I used Wikipedia to prepare for job interviews :)

Re: Study mode

#143

Post by thimabi »

rubslopes wrote: post #123

That's a smart ideia from OpenAI. They don't have the upper hand anymore in terms of model performance, but they keep improving their product so that it still is the best option for non-programmers.

For sure! I haven’t seen any other big AI provider with features and UIs as polished as the OpenAI ones.

I believed competitors would rush to copy all great things that ChatGPT offers as a product, but surprisingly that hasn’t been the case so far. I wonder why they seemingly don’t care about that.

Re: Study mode

#144

Post by Gracana »

scarmig wrote: post #115
SLWW wrote: post #89

Earlier quoted context omitted.

My core problem with LLMs is as you say; it's good for some simpler concepts, tasks, etc. but when you need to dive into more complex topics it will oversimplify, give you what you didn't ask for, or straight up lie by omission. History is a great example, if you ask an LLM about a vaguely difficult period in history it will just give you one side and act like the other doesn't exist, or if there is another side, it…

A few weeks ago I was asking an LLM to offer anti-heliocentric arguments, from the perspective of an intelligent scientist. Although it initially started with what was almost a parody of writing from that period, with some prompting I got it to generate a strong rendition of anti-heliocentric arguments. (On the other hand, it's very hard to get them to do it for topics that are currently politically charged. Less so…

Have you tried abliterated models? I'm curious if the current de-censorship methods are effective in that area / at that level.

Re: Study mode

#145

Post by probably_wrong »

sejje wrote: post #69
SoftTalker wrote: post #13

Modern day Cliff's Notes. There is no way to learn without effort. I understand they are not claiming this, but many students want a silver bullet. There isn't one.

Cliff notes with a near-infinite zoom feature. The criticism of cliff's notes is generally that it's a superficial glance. It can't go deeper, it's basically a summary. The LLM is not that. It can zoom in and out of a topic. I think it's a poor criticism. I don't think it's a silver bullet for learning, but it's a unified, consistent interface across topics and courses.

> It can zoom in and out of a topic.

Sure, but only as long as you're not terribly concerned with the result being accurate, like that old reconstruction of Obama's face from a pixelated version [1] but this time about a topic for which one is, by definition, not capable of identifying whether the answer is correct.

[1] https://www.theverge.com/21298762/face-depixelizer-ai-machin...

Re: Study mode

#146

Post by refulgentis »

ZYbCRq22HbJ2y7 wrote: post #129
sejje wrote: post #125

Earlier quoted context omitted.

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…

> It's not my experience that there are missing pieces as compared to anything else. How can you know this when you are learning something? It seems like a confirmation bias to even have this opinion?

I'd gently point out we're 4 questions into "what about if you went about it stupidly and actually learned nothing?"

It's entirely possible they learned nothing and they're missing huge parts.

But we're sort of at the point where in order to ignore their self-reported experience, we're asking philosophical questions that amount to "how can you know you know if you don't know what you don't know and definitely don't know everything?"

More existentialism than interlocution.

If we decide our interlocutor can't be relied upon, what is discussion?

Would we have the same question if they said they did it from a book?

If they did do it from a book, how would we know if the book they read was missing something that we thought was crucial?

Re: Study mode

#147

Post by HPsquared »

no_wizard wrote: post #49
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…

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

Human interlocutors have similar issues.

Re: Study mode

#148

Post by abeppu »

threetonesun wrote: post #37
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…

> the only thing you can really do is keep paving forward and hope at some point, it'll make sense to you. I find it odd that someone who has been to college would see this as a _bad_ way to learn something.

In college sometimes asking the right question in class or in a discussion section led by a graduate student or in a study group would help me understand something. Sometimes comments from a grader on a paper would point out something I had missed. While having the diligence to keep at it until you understand is valuable, the advantage of college over just a pile of textbooks is in part that there are other resources that can help you learn.

Re: Study mode

#149

Post by viccis »

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…

I would be interested to see if there have already been studies about the efficacy of tutors at good colleges. In my experience (in academia), the students who make it into an Ivy or an elite liberal arts school make extensive use of tutor resources, but not in a helpful way. They basically just get the tutor to work problems for them (often their homework!) and feel like they've "learned" things because tough questions always seems so obvious when you've been shown the answer. In reality, what it means it that they have no experience being confused or having to push past difficult things they were stuck on. And those situations are some of the most valuable for learning.

I bring this up because the way I see students "study" with LLMs is similar to this misapplication of tutoring. You try something, feel confused and lost, and immediately turn to the pacifier^H^H^H^H^H^H^H ChatGPT helper to give you direction without ever having to just try things out and experiment. It means students are so much more anxious about exams where they don't have the training wheels. Students have always wanted practice exams with similar problems to the real one with the numbers changed, but it's more than wanting it now. They outright expect it and will write bad evals and/or even complain to your department if you don't do it.

I'm not very optimistic. I am seeing a rapidly rising trend at a very "elite" institution of students being completely incapable of using textbooks to augment learning concepts that were introduced in the classroom. And not just struggling with it, but lashing out at professors who expect them to do reading or self study.

Re: Study mode

#150

Post by SLWW »

pengstrom wrote: post #100
SLWW wrote: post #89

Earlier quoted context omitted.

My core problem with LLMs is as you say; it's good for some simpler concepts, tasks, etc. but when you need to dive into more complex topics it will oversimplify, give you what you didn't ask for, or straight up lie by omission. History is a great example, if you ask an LLM about a vaguely difficult period in history it will just give you one side and act like the other doesn't exist, or if there is another side, it…

The part about history perspectives sounds interesting. I haven't noticed this. Please post any concrete/specific examples you've encountered!

- Rhodesia (lock step with the racial-first reasoning, underplays Britain's failures to support that which they helped establish; makes the colonists look hateful when they were dealing with terrorists which the British supported)

- Bombing of Dresden, death stats as well as how long the bombing went on for (Arthur Harris is considered a war-criminal to this day for that; LLLMs highlight easily falsifiable claims by Nazi's to justify low estimates without providing much in the way of verifiable claims outside of a select few, questionable, sources. If the low-estimate is to be believed, then it seems absurd that Harris would be considered a war-criminal in light of what crimes we allow today in warfare)

- Ask it about the Crusades, often if forgets the sacking of St. Peter's in Rome around 846 AD, usually painting the Papacy as a needlessly hateful and violent people during that specific Crusade. Which was horrible, bloody as well as immensely destructive (I don't defend the Crusades), but paints the Islamic forces as victims, which they were eventually, but not at the beginning, at the beginning they were the aggressors bent on invading Rome.

- Ask it about the Six-Day War (1967) and contrast that with several different sources on both sides and you'll see a different portrayal even by those who supported the actions taken.

These are just the four that come to my memory at this time.

Most LLMs seem cagey about these topics; I believe this is due to an accepted notion that anything that could "justify" hatred or dislike of a people group or class that is in favor -- according to modern politics -- will be classified as hateful rhetoric, which is then omitted from the record. The issue lies in the fact that to understand history, we need to understand what happened, not how it is perceived, politically, after the fact. History helps inform us about the issues of today, and it is important, above all other agendas, to represent the truth of history, keeping an accurate account (or simply allowing others to read differing accounts without heavy bias).

LLMs are restricted in this way quite egregiously; "those who do not study history are doomed to repeat it", but if this continues, no one will have the ability to know history and are therefore forced to repeat it.

Post reply on HN