621–630 of 828 posts
When I studied I found out that being able to speak with a fellow student of the subject we needed to learn was so much more effective than the usual method of reading /trying to remember over and over. So much that first method would take me an hour as opposed to an entire evening when reading/repeating. Having such a tool would have been a game changer to me. I don’t know tho if it’s possible to throw at it entire…
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…
Agrée, it would have been a godsend for those of us who were not as fast as the other and were eventually left over in usual schooling system. Beside there isn’t any of the usual drawback with privacy because no one care if OpenAI learn about some bullshit you were told to learn.
you didn't see the Hacker News threat talking about the ChatGPT subpeona, did you? I was a bit shocked that 1) a tech community didn't think a company would store data you submit to their servers and 2) that they felt like some lawyers and judges reading their chat logs was some intimate invasion of privacy.
Let's just say I certainly cannot be arsed to read anyone else's stream of conscious without being paid like a lawyer. I deal with kids and it's a bit cute when they babble about semi-coherent topics. An adult clearly loses that cute appeal and just sounds like a madman.
That's not even some dig, I sure suck at explaining my mindspace too. It's a genuinely hard skill to convert thoughts to interesting, or even sensible, communication.
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…
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…
> I'm puzzled (but not surprised) by the standard HN resistance & skepticism. It happens with many technological advancements historically. And in this case there are people trying hard to manufacture outrage about LLMs.
Earlier quoted context omitted.
I learned Rust in a couple of weeks by reading the book.
Yeah regardless of time taken the study plan for Rust already exists ( https://doc.rust-lang.org/book/ ). You don't need ChatGPT to regurgitate it to you.
To get to a reasonably proficient level in rust I did the following.
1. Use the book as the reference.
2. Angela Yu's 100 days of python has a 100 projects to help you learn python (highly recommended if you want to learn python). Tried creating those projects from scratch in Rust.
3. I'd use the book as a reference, then chatGPT to explain more details why my code is not working, or which is the best approach.
Earlier quoted context omitted.
How are you supposed to spot errors if you don't know the material? You're telling people to be experts before they know anything.
> How are you supposed to spot errors if you don't know the material? By noticing that something is not adding up at a certain point. If you rely on an incorrect answer, further material will clash with it eventually one way or another in a lot of areas, as things are typically built one on top of another (assuming we are talking more about math/cs/sciences/music theory/etc., and not something like history). At that…
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.
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…
The freedom to ask "dumb" questions without judgment is huge, and it's something even the best classrooms struggle to provide consistently
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…
Humans who have heard of Monty Hall might also say you should always switch without noticing that the situation is different. That's not evidence that they can't think, just that they're fallible. People on here always assert LLMs don't "really" think or don't "really" know without defining what all that even means, and to me it's getting pretty old. It feels like an escape hatch so we don't feel like our human speci…
Sure.
To Think: able to process information in a given context and arrive at an answer or analysis. an LLM only simulates this with pattern matching. It didn't really consider the problem, it did the equivalent of googling a lot of terms and then spat something that sounded like an answer
To Know: To reproduce information based on past thinking, as well as to properly verify and reason about with the information. I know 1+1 = 2 because (I'm not a math major, feel free to inject number theory instead) I was taught that arithmatic is a form of counting, and I was taught the mechanics of counting to prove how to add. Most LLM models don't really "know" this to begin with for the reasons above. Maybe we'll see if this study mode is different.
Somehow I am skeptical if this will really change minds, though. People making swipes at the community like this often are not really engaging in a conversation with ideas they oppose.