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

471–480 of 828 posts

Re: Study mode

#471

Post by chrsw »

breve wrote: post #455
mediaman wrote: post #454

Earlier quoted context omitted.

This is endlessly brought up as if the human operating the tool is an idiot. I agree that if the user is incompetent, cannot learn, and cannot learn to use a tool, then they're going to make a lot of mistakes from using GPTs. Yes, there are limitations to using GPTs. They are pre-trained, so of course they're not going to know about some easter egg in DDG. They are not an oracle. There is indeed skill to using them.…

The ability to say "I don't know" is not a high bar. I would say it's a basic requirement of a system that is not magic.

> The ability to say "I don't know" is not a high bar.

For you and I, it's not. But for these LLMs, maybe it's not that easy? They get their inputs, crunch their numbers, and come out with a confidence score. If they come up with an answer they're 99% confident in, by some stochastic stumbling through their weights, what are they supposed to do?

I agree it's a problem that these systems are more likely to give poor, incorrect, or even obviously contradictory answers than say "I don't know". But for me, that's part of the risk of using these systems and that's why you need to be careful how you use them.

Re: Study mode

#472

Post by j2kun »

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 Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions.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.

If the last time you saw a wrong answer was a year ago, then you are definitely regularly getting them and not noticing.

Re: Study mode

#473

Post by throwawaylaptop »

noosphr wrote: post #447
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.

Two days ago when my boomer mother in law tried to justify her anti-cancer diet that killed Steve Jobs. On the bright side my partner will be inheriting soon by the looks of it.

The anti cancer diet absolutely works if you want to reduce the odds of getting cancer. It probably even works to slow cancer compared to the average American diet. Will it stop and reverse a cancer? Probably not.

Re: Study mode

#474

Post by filoleg »

noosphr wrote: post #447
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.

Two days ago when my boomer mother in law tried to justify her anti-cancer diet that killed Steve Jobs. On the bright side my partner will be inheriting soon by the looks of it.

Not defending your mother-in-law here (because I agree with you that it is a pretty silly and maybe even potentially harmful diet), afaik it wasn’t the diet itself that killed Steve Jobs. It was his decision to do that diet instead of doing actual cancer treatment until it was too late.

Re: Study mode

#475

Post by chpatrick »

no_wizard wrote: post #440
chpatrick wrote: post #435

Earlier quoted context omitted.

Computers might be accurate but statistical models never were 100% accurate. That doesn't imply that no reasoning is happening. Humans get stuff wrong too but they certainly think and reason. "Pattern matching" to me is another one of those vague terms like "thinking" and "knowing" that people decide LLMs do or don't do based on vibes.

Pattern matching has a definition in this field, it does mean specific things. We know machine learning has excelled at this in greater and greater capacities over the last decade The other part of this is weighted filtering given a set of rules, which is a simple analogy to how AlphaGo did its thing. Dismissing all this as vague is effectively doing the same thing as you are saying others do. This technology has lim…

> Pattern matching has a definition in this field, it does mean specific things.

Such as?

> They’re fundamentally wholly understandable systems that work on a consistent level in terms of the how they do what they do (that is separate from the actual produced output)

Multi billion parameter models are definitely not wholly understandable and I don't think any AI researcher would claim otherwise. We can train them but we don't know how they work any more than we understand how the training data was made.

> I think reasoning, as any layman would use the term, is not accurate to what these systems do.

Based on what?

Re: Study mode

#476

Post by ImaCake »

sen wrote: post #359
lbrito wrote: post #220

Earlier quoted context omitted.

>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.

That was relevant when you were learning to search through “information” for the answer to your question, eg the digital version of going through the library or digging through a reference book. I don’t think it’s so valuable now that you’re searching through piles of spam and junk just to try find anything relevant. That’s a uniquely modern-web thing created by Google in their focus of profit over user. Unless Googl…

> searching through piles of spam and junk

In the same way that I never learnt the Dewey decimal system because digital search had driven it obsolete. It may be that we just won't need to do as much sifting through spam in the future, but being able to finesse Gemini into burping out the right links becomes increasingly important.

Re: Study mode

#477

Post by teleforce »

LLM foremost killer application is what I called context searching whereby it utilized RAG and other techniques to reduce hallucinations and provide relevant results in which arguably ChatGPT is one of the pioneers.

LLM second killer application is for studying for a particular course or subject in which OpenAI ChatGPT is also now providing the service. Probably not the pioneer but most probably one of the significant providers upon this announcement. If in the near future GenAI study assistant can adopt and adapt 3 Blue One Brown approaches for more visualization, animation and interactive learning it will be more intuitive and engaging.

Please check this excellent LLM-RAG AI-driven course assistant at UIUC for an example of university course [1]. It provide citations and references mainly for the course notes so the students can verify the answers and further study the course materials.

[1] AI-driven chat assistant for ECE 120 course at UIUC (only 1 comment by the website creator):

https://news.ycombinator.com/item?id=41431164

Re: Study mode

#478

Post by throwawaylaptop »

breve wrote: post #455
mediaman wrote: post #454

Earlier quoted context omitted.

This is endlessly brought up as if the human operating the tool is an idiot. I agree that if the user is incompetent, cannot learn, and cannot learn to use a tool, then they're going to make a lot of mistakes from using GPTs. Yes, there are limitations to using GPTs. They are pre-trained, so of course they're not going to know about some easter egg in DDG. They are not an oracle. There is indeed skill to using them.…

The ability to say "I don't know" is not a high bar. I would say it's a basic requirement of a system that is not magic.

Based on your example, basically any answer would be "I don't know 100%".

You could ask me as a human basically any question, and I'd have answers for most things I have experience with.

But if you held a gun to head and said "are you sure???" I'd obviously answer "well damn, no I'm not THAT sure".

Re: Study mode

#479

Post by teleforce »

romaniitedomum wrote: post #412
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…

> 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…

Please check this excellent LLM-RAG AI-driven course assistant at UIUC for an example of university course [1]. It provide citations and references mainly for the course notes so the students can verify the answers and further study the course materials.

[1] AI-driven chat assistant for ECE 120 course at UIUC (only 1 comment by the website creator):

https://news.ycombinator.com/item?id=41431164

Re: Study mode

#480

Post by baby »

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…

Skepticism is great, it means less competition. I'm forcing everyone around me to use it.
Post reply on HN