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

331–340 of 828 posts

Re: Study mode

#331

Post by Sharlin »

vonneumannstan wrote: post #249
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.

>Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. If its a subject you are just learning how can you possibly evaluate this?

It's easy to recognize that something is wrong if it's wrong enough.

Re: Study mode

#332

Post by CamperBob2 »

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.

What is "it"? Be specific: are you using some obsolete and/or free model? What specific prompt(s) convinced you that there was no way forward?

Re: Study mode

#333

Post by SLWW »

wahnfrieden wrote: post #255
SLWW wrote: post #150

Earlier quoted context omitted.

- Rhodesia (lock step with the racial-first reasoning, underplays Britain's failures to support that which they helped establish; makes the colonists look hateful when they were dealing with terrorists which the British supported) - Bombing of Dresden, death stats as well as how long the bombing went on for (Arthur Harris is considered a war-criminal to this day for that; LLLMs highlight easily falsifiable claims by…

You call out that you don’t defend the crusades but are you supportive of Rhodesia?

I only highlighted that I'm not in support of the crusades since it sounds like i might be by my comments. I was highlighting that they didn't just lash out with no cause to start their holy war.

Rhodesia is a hard one; since the more I learn about it the more I feel terrible for both sides; I also do not support terrorism against a nation even if I believe they might not be in the right. However i hold by my disdain for how the British responded/withdrew from them effectively doomed Rhodesia making peaceful resolution essentially impossible.

Re: Study mode

#334

Post by GaggiX »

jennyholzer wrote: post #296
GaggiX wrote: post #83

Earlier quoted context omitted.

And the old ChatGPT was nothing compared to what we have today, nowadays reasoning models will eat through math problems no problem when this was a major limitation in the past.

I don't buy it. Open AI doesn't come close to passing my credibility check. I don't believe their metrics.

OpenAI is not the only company making LLMs, there are plenty now, you can use Gemini 2.5 Pro for example. And of course you can just try a SOTA model like Gemini 2.5 Pro for free, you don't have to trust anything.

Re: Study mode

#335

Post by varenc »

This feels like a classic example of a platform provider eating its own ecosystem. There's many custom "GPTs" out there that do essentially the same thing with custom instructions. Mr Ranedeer[0] is an early well known one (30k stars). But now essentially the same functionality is built straight into the ChatGPT interface.

[0] https://github.com/JushBJJ/Mr.-Ranedeer-AI-Tutor

Re: Study mode

#336

Post by ascorbic »

bsoles wrote: post #259

Aka cheating mode. Their video literally says "Helps with homework" and proceeds to show the "Final Answer". So much learning...

"Cheating mode" is regular ChatGPT. This at least tries to make you work for it

Re: Study mode

#337

Post by jonahx »

kenjackson wrote: post #284
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.

“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.” These things also apply to humans. A year or so ago I thought I’d finally learn more about the Israeli/Palestinians conflict. Turns out literally every source that was recommended to me by…

> learn more about the Israeli/Palestinians

> to be quite good at math and programming

Since LLMs are essentially summarizing relevant content, this makes sense. In "objective" fields like math and CS, the vast majority of content aligns, and LLMs are fantastic at distilling the relevant portions you ask about. When there is no consensus, they can usually tell you that ("this is nuanced topic with many perspectives...", etc), but they can't help you resolve the truth because, from their perspective, the only truth is the content.

Re: Study mode

#338

Post by nixpulvis »

gh0stcat wrote: post #208
simonw wrote: post #198

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…

I love that caps actually seem to matter to the LLM.

Just wait until it only responds to **COMMAND**!

Re: Study mode

#339

Post by SLWW »

jay_kyburz wrote: post #320
SLWW wrote: post #89

Earlier quoted context omitted.

My core problem with LLMs is as you say; it's good for some simpler concepts, tasks, etc. but when you need to dive into more complex topics it will oversimplify, give you what you didn't ask for, or straight up lie by omission. History is a great example, if you ask an LLM about a vaguely difficult period in history it will just give you one side and act like the other doesn't exist, or if there is another side, it…

People _do_ just wake up one day and decide some piece of land should belong to them, or that they don't have enough money and can take yours, or they are just sick of looking at you and want to be rid of you. They will have some excuse or justification, but really they just want more than they have. People _do_ just wake up and decide to be evil.

A nation that might fit this description may have had their populace indoctrinated (through a widespread political campaign) to believe that the majority of the world throughout history seeks for their destruction. That's a reason for why they think that way, but not because they woke up one day and decided to choose violence.

However not a justification, since I believe that what is happening today is truly evil. Same with another nation who entered a war knowing they'd be crushed, which is suicide; whether that nation is in the right is of little effect if most of their next generation has died.

Post reply on HN