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…
> Certainly, and this technology won't help or hinder them any more than a good old fashioned textbook.
Except that the textbook was probably QA’d by a human for accuracy (at least any intro college textbook, more specialized texts may not have).
Matters less when you have background in the subject (which is why it’s often okay to use LLMs as a search replacement) but it’s nice not having a voice in the back of your head saying “yeah, but what if this is all nonsense”.
I'm really waiting for somebody to figure out the correct interface for all this. For example, study mode will present you with a wall of text containing information, examples, and questions. There's no great way to associate your answers with specific questions. The chat interface just isn't good for this sort of interaction. ChatGPT really needs to build its own canvas/artifact interface wherein questions/responses…
Agree, one thing that brought this home was the example where the student asks to learn all of game theory. There seems to be an assumption on both sides that this will be accomplished in a single chat session by a linear pass, necessarily at a pretty superficial level.
I'm currently learning Janet and using ChatGPT as my tutor is absolutely awful. "So what is the difference between local and var if they are both local and not global variables (as you told me earlier)?" "Great question, and now you are really getting to the core of it, ... " continues to hallucinate. It's a great tutor for things it knows, but it really needs to learn its own limits
For these unfortunately you should dump most of the guide/docs into its context
"Under the hood, study mode is powered by custom system instructions we’ve written in collaboration with teachers, scientists, and pedagogy experts to reflect a core set of behaviors that support deeper learning including: "
Wonder what the compensation for this invaluable contribution was
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…
Yeah, I've been a game-dev forever and had never built a web-app in my life (even in college) I recently completed my 1st web-app contract, and gpt was my teacher. I have no problem asking stupid questions, tbh asking stupid questions is a sign of intelligence imo. But where is there to even ask these days? Stack Overflow may as well not exist.
Super good idea!! Luc Julia (one of the main Siri's creators) describe a very similar exercice in this interview [0](It's in french, although the au translation isn't too bad) The gist of it, is that he describes this exercice he does with his students, where they ask chatgpt about Victor Hugo's biography, and then proceed to spot the errors made by Chatgtp. This setup is simple, but there are very interesting mechan…
forgot the link :)
Arf seems I'm one of those :).. thanks for the heads up!
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…
There's studies showing that LLM makes experienced devs slower in their work. I wouldn't be surprised if it was the same for self study. However consider the extent to which LLMs make the learning process more enjoyable. More students will keep pushing because they have someone to ask. Also, having fun & being motivated is such a massive factor when it comes to learning. And, finally, keeping at it at 50% the speed f…
It was a 16 person study on open source devs that found 50 hours of experience with the tool made people more productive
"Screwed" = spending hours sifting through poorly-written, vaguely-related documents to find a needle in a haystack. Why would I want to continue doing that?
> "Screwed" = spending hours sifting through poorly-written, vaguely-related documents to find a needle in a haystack. From the parent comment: > it was pretty much impossible ... hope at some point, it'll make sense to you Not sure where you are getting the additional context for what they meant by "screwed", but I am not seeing it.
as a professor i'm tentatively pleased. it's hard to shake out the edge cases for anything like this so it may break down or cause annoying problems, who knows.
but even with this feature in this very early state, it seems quite useful. i dropped in some slides from a class and pretended to be a student, and it handled questions reasonably. Right now it seems I will be happy for my students to use this.
taking a wider perspective, I think it is a good sign that OpenAI is culturally capable of making a high-friction product that challenges and frustrates, yet benefits, the user. hopefully this can help with the broader problem of sycophancy.
Study mode should be for any account with an age under 18. It's more worrying that a student must uphold a trust transaction and not just cheat with the same chatbot without the study mode selected. To this day, as an AI researcher, digital anthropologist, and front-end dev, I love to learn, study, and work. But I would never recommend a student to use unmonitored ChatGPT. I literally built a whole effing agent and platform for finding academic sources and using those sources to answer my questions, specifically because I couldn't trust or learn with ChatGPT when conducting research. SMH study mode, please stop trying to redo teaching and learning. We should be trying to modernize already proven effective methods of learning that go hand in hand with teachers and classrooms. We are not in lockdown; this is not 2020. Teachers are irreplaceable, study mode is just a crutch or a brace for a problem created by irresponsible AI development. Ik that if I was a student right now (especially middle to high school) I would be cheating like you are lying to yourself if you think you wouldn't be, and at a certain point the definition of cheating changes from cheating the teacher to cheating yourself of the critical steps and thinking it takes to actually study and learn. No amount of conversation alone with a chatbot is as valuable as reading coursework and engaging with that coursework in a facilitated environment with a professional. Why are we going down the WALL-E path?