Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I'd rather read the prompt

claytonwramsey.com

Post reply on HN
Print view View original

631–640 of 880 posts

Re: I'd rather read the prompt

#631

Post by Ekaros »

mike_hearn wrote: post #611
lazide wrote: post #556

Earlier quoted context omitted.

Notably, the late 70’s and early 80’s is when large scale social changes started to happen due to high inflation and major problems in the US economy. Also a lot of social unrest, and a pretty unhinged president (Tricky Dick).

The same issues are seen in other countries. It's not specific to US presidents or policy. The insistence on maximizing university attendance was a widespread idea coming out of the left, e.g. in Britain it was heavily pushed by Tony Blair. The Blair government also raised tuition fees considerably. The stated rationale at the time was that degree holders earn more, so if everyone gets a degree, everyone will earn mo…

Also I think massaging unemployment numbers for a while is reasonable goal. After all those in education are not counted as unemployed.

Re: I'd rather read the prompt

#632

Post by landgenoot »

lqr wrote: post #513

For math and writing, we still have in-class exams as an LLM-free evaluation tool. I wish there was some way to do the same for programming. Imagine a classroom full of machines with no internet connection, just a compiler and some offline HTML/PDF documentation of languages and libraries.

This is perfectly possible.

+-12 years ago I took a course on concepts of programming languages. The exam consisted out of programming exercises in a classroom without internet access.

Grading was based on the number of (hidden) unit tests that succeeded.

https://eelcovisser.org/blog/teaching/2014/02/05/programming...

Re: I'd rather read the prompt

#634

Post by SebFender »

Maybe ridiculous from my part - but I think if they at least had to go hand written with these it could transfer a bit more knowledge back to the brain...

Simply blaming models is an easy way out and creates little value - Maybe changing the medium and exercise to which it transfers could be a thing?

It's time to get creative.

Re: I'd rather read the prompt

#635

Post by elzbardico »

justinclift wrote: post #213
FridgeSeal wrote: post #143

Earlier quoted context omitted.

> creating bloat until it becomes so unproductive it kills the host Maybe we should let/encourage this to happen. Maybe letting bloated zombie-like organisations bloat themselves to death would thin the herd somewhat, to make space for organisations that are less “broken”.

"But at what price?" is probably the right question here, and that'd be a case by case basis thing. ;)

I am on the mind that every organization should eventually die before it becomes a monster. I am also not a huge fan of inheritance for the same reason.

Re: I'd rather read the prompt

#636

Post by palata »

tpmoney wrote: post #630
palata wrote: post #223

Earlier quoted context omitted.

> We use calculators and computers for a reason. No one hires people to respond to API requests by hand; we run the code on servers We were talking about writing, not about vibe coding. We don't use calculators for writing. We don't use API requests for writing (except when we make an LLM write for us). > Using the right tool for the job is just doing my job well. I don't know what your job is. But if your job is to…

> We were talking about writing, not about vibe coding. We don't use calculators for writing. We don't use API requests for writing (except when we make an LLM write for us). We do however use them to summarize and transform data all the time. Consider the ever present spreadsheet. Huge amounts of data are thrown into spreadsheets and formulas are applied to that data to present us with graphs and statistics. You cou…

You seem to not make the difference between maths and, say, literature or history.

Do you actually think that an LLM can take, say, a Harry Potter book as an input, and give it a grade in such a way that everybody will always agree on?

And to go further, do you actually use LLMs to generate graphs and statistics from spreadsheet? Because that is probably a bad idea given that there are tools that actually do it right.

Re: I'd rather read the prompt

#637

Post by mFixman »

jameshart wrote: post #329
sn9 wrote: post #221

> I should hope that the purpose of a class writing exercise is not to create an artifact of text but force the student to think; a language model produces the former, not the latter. It's been incredibly blackpilling seeing how many intelligent professionals and academics don't understand this, especially in education and academia. They see work as the mere production of output, without ever thinking about how that…

I’ve come across this analogy that I think works well: Using an LLM to do schoolwork is like taking a forklift to the gym. If all we were interested in was moving the weights around, you’d be right to use a tool to help you. But we’re doing this work for the effect it will have on you . The reason a teacher asks you a question is not because they don’t know the answer.

The tragedy is not that some students are going to college to get a diploma while learning as little as possible. It is that the boards of many private universities see their students' cash as more important than their education, and force the professors to pass everybody who went to higher education to buy a diploma.

This has a negative feedback loop where universities have to lower standards to bring dumber and lazier students to compete with other diploma mills.

Re: I'd rather read the prompt

#638

Post by valenterry »

palata wrote: post #240
valenterry wrote: post #209

Earlier quoted context omitted.

They are also useful for association. Imagine an LLM trained on documentation. Then you can retrieve info associated with your question. This can go beyond just specific documentation but also include things like "common knowledge" which is what the other poster meant when they talked about "teaching you things".

In my experience, if the information I need is in the documentation, then I don't need the LLM. If it is not in the documentation, then the LLM will invent stuff that could be there but that isn't, and it's actually a loss of time.

> In my experience, if the information I need is in the documentation, then I don't need the LLM

need is a strong word. Do you need to be able to do ctrl+F? Not really, you can just read it all. But maybe it's easier to do ctrl+F. Same with LLM. Just imagine it as a fuzzy ctrl+F. Can be useful.

Re: I'd rather read the prompt

#639

Post by klibertp »

rohansood15 wrote: post #400
ChadNauseam wrote: post #358

Earlier quoted context omitted.

If students went to college only to learn, colleges wouldn't bother giving diplomas. Compare: My piano teacher doesn't give diplomas because none of her students would care, her students actually want to learn. When my piano teacher cancels class, I am disappointed because I wanted to learn. My piano teacher doesn't need to threaten me with bad grades to get me to practice outside of class (analogous to homework), be…

Students want the diploma because it has value. It has value because a student can only get it by learning and problem-solving. If students find a way to get a diploma without doing the work, it will soon be worth less than the paper on which it is printed.

> It has value because a student can only get it by learning and problem-solving.

No. That's how it should be, but the reality looks different: it has value because it shows that someone spent 3+ years doing what they were told to do, enduring all the absurdities they were subjected to in the meantime. Whatever means they used to cheat don't matter, since they still worked on what someone told them to and produced results satisfying the expectations.

There are, perhaps, institutions where learning and problem-solving are seen as the most important while "following orders" and "staying in line" are deemphasized. For the students of all the others, putting up with an utterly absurd environment is often one of the biggest barriers to learning. Yet, it's a requirement without fulfilling which you can forget about graduating. Hence my conclusion: the diploma from most learning institutions certifies you as a good corporate drone - and that's enough of a signal in many situations, so why bother trying to fix it?

Re: I'd rather read the prompt

#640

Post by scsh »

expensive_news wrote: post #459
bost-ty wrote: post #4

I like the author's take: it isn't a value judgement on the individual using ChatGPT (or Gemini or whichever LLM you like this week), it's that the thought that went into making the prompt is, inevitably, more interesting/original/human than the output the LLM generates afterwards. In my experiments with LLMs for writing code, I find that the code is objectively garbage if my prompt is garbage. If I don't know what I…

I have mixed feelings. Generally I don’t think that LLM output should be used to create anything that a human is supposed to read, but I do carve out a big exception for people using LLMs for translation/writing in a second language. At the same time, however, the people who need to use an LLM for this are going to be the worst at identifying the output’s weaknesses, eg just as I couldn’t write Spanish text, I also c…

I actually feel very strongly that code is very much written for us humans. Sure, it's a set of instructions that is intended to be machine read and executed but so much of _how_ code is written is very much focused on the human element that's been a part of software development. OOP, design patterns, etc. don't exist because there is some great benefit to the machines running the code. We humans benefit as the ones maintaining and extending the functionality of the application.

I'm not making a judgement about the use of LLMs for writing code, just that I do think that code serves the purpose of expressing meaning to machines as well as humans.

Post reply on HN