159 comments

[ 1.8 ms ] story [ 92.8 ms ] thread
Ah, the advancing of humanity. A bespoke professor-quality instructor in everyone’s pocket (or local library) available 24/7.

Happy Tuesday!

Not seeing it on my account, guess the roll out is actively happening (or gradual)?
Why do I still feel like I'll be paying hundreds of thousands of dollars for my children's education when all they're going to do is all learn through AI anyway.
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 repetition tools like Mochi [1] or Anki.

See Andy's talk here [2]

[1] https://mochi.cards

[2] https://andymatuschak.org/hmwl/

(comment deleted)
Interesting. I don’t use GPT for code but I have been using it to grade answers to behavioral and system design interview questions, lately. Sometimes it hallucinates, but the gists are usually correct.

I would not use it if it was for something with a strictly correct answer.

I'm not sure about the audience for this, if you're already willing to learn the material you probably already engage with AI in a way that isn't "please output the answers for me" because you're likely self-aware enough to know that "answering" isn't always "understanding." Maybe this mode makes that a little easier? but I doubt it's significant

If you're the other 90% of students that are only learning to check the boxes and get through the courses to get the qualification at the end... are you going to bother using this?

Of course, maybe this is "see, we're not trying to kill education... promise!"

Modern day Cliff's Notes.

There is no way to learn without effort. I understand they are not claiming this, but many students want a silver bullet. There isn't one.

(comment deleted)
If current AI is good enough to teach you something, spending time learning that thing seems to be a really bad investment...
I truly believe AI will change all of education for the better, but of course it can also hinder learning if used improperly. Those who want to genuinely learn will learn while those looking for shortcuts will cause more harm to themselves. I just did a show HN today about something semi related.

I made A deep research assistant for families. Children can ask questions to explain difficult concepts and for parents to ask how to deal with any parenting situation. For example a 4 year old may ask “why does the plate break when it falls?”

example output: https://www.studyturtle.com/ask/PJ24GoWQ-pizza-sibling-fight...

app: https://www.studyturtle.com/ask/

Show HN: https://news.ycombinator.com/item?id=44723280

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 basically has a personal TA, ready to go at all hours of the day.

I get the commentary that it makes learning too easy or shallow, but I doubt anyone would think that college students would learn better if we got rid of TA's.

I have been very skeptical of AI. But getting unstuck when studying. Its a huge help. This is the first I see the benifit with AI. I take a picture of a formula and ask chatgpt to explain the steps.
I’m curious what these features like study mode actually are. Are they not just using prompts behind this (of which I’ve used many already to make LLMs behave like this) ?
i wonder how Khan Academy feels about this...don't they have a similar assistant that uses OpenAI under the hood?
Indeed, that's what khanmigo is using, and they were involved in testing chatgpt before it was released for that purpose, to test/try/improve chatgpt as a tutor (that performs fact checking and doesn't hallucinate).
OpenAI, please stop translating your articles into the most sterile and dry Danish I have ever read. English is fine.
tried it and couldn't really tell between a good prompt to "teach me" and this.
In the blog post they say as much that it just is a system prompt. Still nice to have easy access, and for more users to discover that use case.
(comment deleted)
I honestly don't know how they convince employees to make features like this - like, they must dogfood and see how wrong the models can be sometimes. Yet there's a conscious choice to not only release this to, but actively target, vast swathes of people that literally don't know better.
OpenAI has an incredible product team. Deep Mind and Anthrpoic (and maybe xai) are competitive at the model level but not at product
An acquaintance of mine has a start-up in this space and uses OpenAI to do essentially the same thing. This must look like, and may well be, the guillotine for him...

It's my primary fear building anything on these models, they can just come eat your lunch once it looks yummy enough. Tread carefully

This is actually a public validation for your friend's startup.

A proper learning tool will have history of conversation with the student, understand their knowledge level, have handcrafted curricula (to match whatever the student is supposed to learn), and be less susceptible to hallucination.

OpenAI have a bunch of other things to worry about and won't just pivot to this space.

This risk should be priced in on day one.

All bigco today, not only foundational model providers but also in media and other vertical, tend to be a platform for end user. They don’t want middle man.

If you are trying to be a middle man, you should be prepared.

The point is that you can have a highly advanced teacher with infinite patience, available 24/7—even when you have a question at 3 a.m is game changer and people that know how to use that will have a extremaly leverage in their life.
This is great. When it first came out I was going through Strang’s linalg course and got it to do “problem mode” where it would talk me through a problem step by step, waiting for me respond.

A more thought through product version of that is only a good thing imo.