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

291–300 of 828 posts

Re: Study mode

#291

Post by terabyterex »

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.

This can happen if you use the free model and not a paid deep research model. You can use a gpt model and ask things like , "how many moons does Jupiter have?" But if you want to ask, "can you go on the web a research the affects that chamical a has had on our water supply a cite sources?", you will need to use a deep research model.

Re: Study mode

#292

Post by jasondigitized »

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.

If we have custom trained LLMs per subject doesn't that solve the problem. The shallow problem seems really easy to solve

Re: Study mode

#293

Post by smokel »

no_wizard wrote: post #75
sejje wrote: post #60

Earlier quoted context omitted.

I learned how to code using the library in the 90s. I think it's accurate to say that if I had to do that again, I'm basically screwed. Asking the LLM is a vastly superior experience. I had to learn what my local library had, not what I wanted. And it was an incredible slog. IRC groups is another example--I've been there. One or two topics have great IRC channels. The rest have idle bots and hostile gatekeepers. The…

>Asking the LLM is a vastly superior experience. Not to be overly argumentative, but I disagree, if you're looking for a deep and ongoing process, LLMs fall down, because they can't remember anything and can't build upon itself in that way. You end up having to repeat alot of stuff. They also don't have good course correction (that is, if you're going down the wrong path, it doesn't alert you, as I've experienced) It…

Most LLM user interfaces, such as ChatGPT, do have a memory. See Settings, Personalization, Manage Memories.

Re: Study mode

#294

Post by naet »

"Under the hood, study mode is powered by custom system instructions we’ve written...."

It seems like study mode is basically just a different system prompt but otherwise the exact same model? So there's not really any new benefit to anyone who was already asking for ChatGPT to help them study step by step instead of giving away whole answers.

Seems helpful to maybe a certain population of more entry level users who don't know to ask for help instead of asking for a direct answer I guess, but not really a big leap forward in technology.

Re: Study mode

#295

Post by ascorbic »

lbrito wrote: post #220
poemxo wrote: post #119

As a lifelong learner, experientially it feels like a big chunk of time spent studying is actually just searching. AI seems like a good tool to search through a large body of study material and make that part more efficient. The other chunk of time, to me anyway, seems to be creating a mental model of the subject matter, and when you study something well you have a strong grasp on the forces influencing cause and eff…

>big chunk of time spent studying is actually just searching. This is a good thing in many levels. Learning how to search is (was) a good skill to have. The process of searching itself also often leads to learning tangentially related but important things. I'm sorry for the next generations that won't have (much of) these skills.

Searching is definitely a useful skill, but once you've been doing it for years you probably don't need the constant practice and are happy to avoid it.

Re: Study mode

#296

Post by jennyholzer »

GaggiX wrote: post #83
adamsb6 wrote: post #40

Earlier quoted context omitted.

When ChatGPT came out it was like I had the old Google back. Learning a new programming language used to be mediated with lots of useful trips to Google to understand how some particular bit worked, but Google stopped being useful for that years ago. Even if the content you're looking for exists, it's buried.

And the old ChatGPT was nothing compared to what we have today, nowadays reasoning models will eat through math problems no problem when this was a major limitation in the past.

I don't buy it. Open AI doesn't come close to passing my credibility check. I don't believe their metrics.

Re: Study mode

#297

Post by cthalupa »

rawgabbit wrote: post #247
pyuser583 wrote: post #203

Earlier quoted context omitted.

> 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 aggre…

He's referring to the Arab sack of St. Peters. https://en.wikipedia.org/wiki/Arab_raid_against_Rome

His point is that this was not part of the crusades, not that he was unaware of his happening.

Re: Study mode

#298

Post by ghrl »

It would be incredible if OpenAI would add a way for schools and other educational institutions to enforce the use of such a mode on a DNS level, similarly to how they can force sites like YouTube into safe mode. Many students use ChatGPT, often without permission, to do work for them instead of helping them do the work themselves. I see a lot of potential for a study mode like this, helping students individually without giving direct answers.

Re: Study mode

#300

Post by qualeed »

ZYbCRq22HbJ2y7 wrote: post #118
tekno45 wrote: post #101

Earlier quoted context omitted.

how are you checking its correctness if you're learning the topic?

This is important, as benchmarks indicate we aren't at a level where a LLM can truly be relied upon to teach topics across the board. It is hard to verify information that you are unfamiliar with. It would be like learning from a message board. Can you really trust what is being said?

>we aren't at a level where a LLM can truly be relied upon to teach topics across the board.

You can replace "LLM" here with "human" and it remains true.

Anyone who has gone to post-secondary has had a teacher that relied on outdated information, or filled in gaps with their own theories, etc. Dealing with that is a large portion of what "learning" is.

I'm not convinced about the efficacy of LLMs in teaching/studying. But it's foolish to think that humans don't suffer from the same reliability issue as LLMs, at least to a similar degree.

Post reply on HN