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

731–740 of 828 posts

Re: Study mode

#731

Post by tim333 »

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 Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions.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

>But now, you're wondering if ... hallucinated

A simple solution is just to take and cut and paste it into Google and see if articles confirm it.

Re: Study mode

#732

Post by otabdeveloper4 »

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…

> A tireless, capable, well-versed assistant

Correction: a tireless, capable, well-versed, sycophantic assistant that is often prone to inventing absolute bullshit.

> ...is an autodidact's dream

Not so sure about that, see above.

Re: Study mode

#735

Post by a2128 »

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…

It does go both ways. You can ask stupid questions without fear of embarrassment or ruined reputation, and it can respond with stupid answers without fear of embarrassment or ruined reputation.

It can confidently spew completely wrong information and there's no way to tell when it's doing that. There's a real risk that it will teach you a complete lie based on how it "thinks" something should work, and unlearning that lie will be much harder than just learning the truth initially

Re: Study mode

#736

Post by otabdeveloper4 »

flir wrote: post #647
ricardobeat wrote: post #590

Earlier quoted context omitted.

This is meaningless without knowing which model, size, version and if they had access to search tools. Results and reliability vary wildly. In my case I can’t even remember last time Claude 3.7/4 has given me wrong info as it seems very intent on always doing a web search to verify.

There's something darkly funny about that - I remember when the web wasn't considered reliable either. There's certainly echoes of that previous furore in this one.

> I remember when the web wasn't considered reliable either

It still isn't.

Re: Study mode

#737

Post by mvieira38 »

ink_13 wrote: post #526
teleforce wrote: post #479

Earlier quoted context omitted.

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

Given the propensity of LLMs to hallucinate references, I'm not sure that really solves anything

I haven't seen it happen at all with RAG systems. I've built one too at work to search internal stuff, and it's pretty easy to make it spit out accurate references with hyperlinks

Re: Study mode

#738

Post by phailhaus »

ants_everywhere wrote: post #433
phailhaus wrote: post #413

Earlier quoted context omitted.

HN is resistant because at the end of the day, these are LLMs. They cannot and do not think. They generate plausible responses. Try this in your favorite LLM: "Suppose you're on a game show trying to win a car. There are three doors, one with a car and two with goats. You pick a door. The host then gives you the option to switch doors. What is the best strategy in this situation?" The LLM will recognize this as SIMIL…

That's because the LLM assumes you mean for the host to open the door. As an autistic person I can assure you that people filling in information you neither gave nor implied is the norm for human conversations. In that sense, the LLMs are being human-like. If you explicitly tell it you didn't forget to have the host open the door it gives you the right answer: > There is a game show with three closed doors. One has a…

> That's because the LLM assumes you mean for the host to open the door.

LLM's cannot "assume". There is no thinking involved. It sees that the prompt looks like the monty hall problem and it just goes full steam ahead.

>If you explicitly tell it you didn't forget to have the host open the door it gives you the right answer:

That should not be necessary. I asked it a very clear question. I did not mention Monty Hall. This is the problem with LLM's: it did not analyze the problem I gave it, it produced content that is the likely response to my prompt. My prompt was Monty Hall-shaped, so it gave me the Monty Hall answer.

You are saying "ah but then if you prepare for the LLM to get it wrong, then it gets it right!" as if that is supposed to be convincing! Consider the millions of other unique questions you can ask, each with their own nuances, that you don't know the answer to. How can you prevent the LLM from making these mistakes if you don't already know the mistakes it's going to make?

Re: Study mode

#739

Post by threecheese »

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…

> you're wondering if the answer the AI gave you is correct or something it hallucinated

Worse, more insidious, and much more likely is the model is trained on or retrieves an answer that is incorrect, biased, or only conditionally correct for some seemingly relevant but different scenario.

A nontrivial amount of content online is marketing material, that is designed to appear authoritative and which may read like (a real example) “basswood is renowned for its tonal qualities in guitars”, from a company making cheap guitars.

If we were worried about a post-truth era before, at least we had human discernment. These new capabilities abstract away our discernment.

Re: Study mode

#740

Post by tiahura »

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…

Fear causes defensive behavior.
Post reply on HN