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

191–200 of 828 posts

Re: Study mode

#191

Post by fakedang »

tsumnia wrote: post #103
no_wizard wrote: post #49

Earlier quoted context omitted.

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

IT can be beneficial for making your initial assessment, but you'll need to dig deeper for something meaningful. For example, I recently used Gemini's Deep Research to do some literature review on educational Color Theory in relation to PowerPoint presentations [1]. I know both areas rather well, but I wanted to have some links between the two for some research that I am currently doing. I'd say that companies like G…

Taking a Gemini Deep Research output and feeding it to NotebookLM to create audio overviews is my current podcast go-to. Sometimes I do a quick Google and add in a few detailed but overly verbose documents or long form YouTube videos, and the result is better than 99% of the podcasts out there, including those by some academics.

Re: Study mode

#192

Post by EcommerceFlow »

A good start. One of the biggest issues with LLMs is the "intelligence" has far surpassed the tooling. A better combination of prompts, RAG, graphs, etc exists for education and learning, but no one's come up with the proper format / tooling for it, even if the models are smart enough.

Re: Study mode

#193

Post by jjfoooo4 »

no_wizard wrote: post #49
czhu12 wrote: post #26

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 ba…

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

It's a floor raiser, not a ceiling raiser. It helps you get up to speed on general conventions and consensus on a topic, less so on going deep on controversial or highly specialized topics

Re: Study mode

#194

Post by snewman »

posix86 wrote: post #178
jryio wrote: post #5

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…

I presume you're referring to the recent METR study. One aspect of the study population, which seems like an important causal factor in the results, is that they were working in large, mature codebases with specific standards for code style, which libraries to use, etc. LLMs are much better at producing "generic" results than matching a very specific and idiosyncratic set of requirements. The study involved the latter (specific) situation; helping people learn mainstream material seems more like the former (generic) situation.

(Qualifications: I was a reviewer on the METR study.)

Re: Study mode

#195

Post by paolosh »

I am always surprised at how the best thing state of the art LLMs can think of is adding more complexity to the mix. This is an AMAZING product but to me it seems like it's hidden? Or maybe the UX/UI is just not my style, could be a personal thing.

Is adding more buttons in a dropdown the best way to communicate with an LLM? I think the concept is awesome. Just like how Operator was awesome but it lived on an entirely different website!

Re: Study mode

#197

Post by neutronicus »

no_wizard wrote: post #49
czhu12 wrote: post #26

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 ba…

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

Hmm. I have had pretty productive conversations with ChatGPT about non-linear optimization.

Granted, that's probably well-trodden ground, to which model developers are primed to pay attention, and I'm (a) a relative novice with (b) very strong math skills from another domain (computational physics). So Chuck and I are probably both set up for success.

Re: Study mode

#198

Post by simonw »

I think I got the system prompt out for this (I tried a few different approaches and they produced the same output): https://gist.github.com/simonw/33d5fb67d6b8e1b1e2f6921ab0ccb...

Representative snippet:

> DO NOT GIVE ANSWERS OR DO HOMEWORK FOR THE USER. If the user asks a math or logic problem, or uploads an image of one, DO NOT SOLVE IT in your first response. Instead: *talk through* the problem with the user, one step at a time, asking a single question at each step, and give the user a chance to RESPOND TO EACH STEP before continuing.

Re: Study mode

#200

Post by graerg »

posix86 wrote: post #178
jryio wrote: post #5

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…

People keep citing this study (and it was on the top of HN for a day). But this claim falls flat when you find out that the test subjects had effectively no experience with LLM equipped editors and the 1-2 people in the study that actually did have experience with these tools showed a marked increase in productivity.

Like yeah, if you’ve only ever used an axe you probably don’t know the first thing about how to use a chainsaw, but if you know how to use a chainsaw you’re wiping the floor with the axe wielders. Wholeheartedly agree with the rest of your comment; even if you’re slow you lap everyone sitting on the couch.

Post reply on HN