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

111–120 of 880 posts

Re: I'd rather read the prompt

#111

Post by satisfice »

_qswe wrote: post #78
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 think the author has a fair take on the types of LLM output he has experience with, but may be overgeneralizing his conclusion. As shown by his example, he seems to be narrowly focusing on the use case of giving the AI some small snippet of text and asking it to stretch that into something less information-dense — like the stereotypical "write a response to this email that says X", and sending that output instead o…

If you present your AI-powered work to me, and I suspect you employed AI to do any of the heavy lifting, I will automatically discount any role you claim to have had in that work.

Fairly or unfairly, people (including you) will inexorably come to see anything done with AI as ONLY done with AI, and automatically assume that anyone could have done it.

In such a world, someone could write the next Harry Potter and it will be lost in a sea of one million mediocre works that roughly similar. Hidden in plain sight forever. There would no point in reading it, because it is probably the same slop I could get by writing a one paragraph prompt. It would be too expensive to discover otherwise.

Re: I'd rather read the prompt

#112

Post by necovek »

tptacek wrote: post #41

I have a lot of sympathy for the author's position but I may have missed the point in the article where he explained why clarity of writing and genuineness of human expression was so vital to a robotics class. It's one thing for an instructor to appreciate those things; another for them to confound their own didactic purpose with them. This point seems obvious enough that I feel like I must have missed something. As…

I think they summed it up well in the section "Why do we write, anyway?" — they nowhere claimed it was vital for students' success in a robotic class. On the contrary as they title a subsection there with "If it’s worth doing, it’s worth doing *badly*" (emphasis mine) — so what they are looking for is to peer into the author's mind and their original thoughts.

The implication there is that this is acceptable to pass a robotics class, and potentially this gives them more information about students' comprehension to further improve their instruction and teaching ("...that they have some kind of internal understanding to share").

On that second point, I have yet to see someone demonstrate a "smart, professional programmer use LLMs" in a way where it produces high quality output in their area of expertise, while improving their efficiency and thus saving time for them (compared to them just using a good, old IDE)!

Re: I'd rather read the prompt

#113

Post by sillysaurusx »

topkai22 wrote: post #49
sillysaurusx wrote: post #22

I think people who don’t like writing shouldn’t be forced to write, just like people who don’t like music shouldn’t be forced to play music. Ditto for math. Forcing people to do these things supposedly results in a better, more competitive society. But does it really? Would you rather have someone on your team who did math because it let them solve problems efficiently, or did math because it’s the trick to get the r…

Many of the things we teach in school aren’t just for the direct knowledge or skill. We largely don’t need to do arithmetic any more, but gaining the skill at doing it really improves our ability to deal with symbolic manipulation and abstraction. I remember another parent ranting about their 3rd grade kids “stupid homework” since it had kids learning different ways of summing numbers. I took a look at the homework a…

Then your friend spent 20 years not needing math skills. If someone spent years doing something useless to them for two decades, we wouldn’t call them efficient. But for some bizarre reason, we celebrate it as a point of honor in academia.

One counter argument to yours is that when you do need the skills, you can learn them later. It’s arguably easier than it has been at any point in human history. In that context, why front load people with something they hate doing, just because their parents think it’s a good idea? Let them wait and learn it when they need it.

Re: I'd rather read the prompt

#114

Post by doright »

sillysaurusx wrote: post #22

I think people who don’t like writing shouldn’t be forced to write, just like people who don’t like music shouldn’t be forced to play music. Ditto for math. Forcing people to do these things supposedly results in a better, more competitive society. But does it really? Would you rather have someone on your team who did math because it let them solve problems efficiently, or did math because it’s the trick to get the r…

People just have to want to like things. If they don't like something enough then a near-ubiquitous form of outsourcing is now available for them to get carried away with.

The "wanting to like things" is a highly undervalued skill/trait. It comes down to building a habit through repetition - not necessarily having fun or getting results, but training your mind like a muscle to think putting in effort isn't that bad an activity.

For those growing up I think this is not something that is taught - usually it is already there as a childlike sense of wonder that gets pruned by controlling interests. If education forcing you to do math removes any enthusiasm you had for math, that's largely determined by circumstance. You'd need someone else to tell you the actual joys of X to offset that (and I'd guess most parents/teachers don't practice math for fun), or just spontaneously figuring out how interesting X is totally on one's own which is even rarer.

I didn't have either so I'm a mathophobe, but I'm alright with that since I have other interests to focus on.

Re: I'd rather read the prompt

#115

Post by neilv »

> [...] but not so distinctive to be worth passing along to an honor council. Even if I did, I’m not sure the marginal gains in the integrity of the class would be worth the hours spent litigating the issue.

The school should be drilling into students, at orientation, what some school-wide hard rules are regarding AI.

One of the hard rules is probably that you have to write your own text and code, never copy&paste. (And on occasions when copy&paste is appropriate, like in a quote, or to reuse an off-the-shelf function, it's always cited/credited clearly and unambiguously.)

And no instructors should be contradicting those hard rules.

(That one instructor who tells the class on the first day, "I don't care if you copy&paste from AI for your assignments, as if it's your own work; that just means you went through the learning exercise of interacting with AI, which is what I care about"... is confusing the students, for all their other classes.)

Much of society is telling students that everything is BS, and that their job is to churn BS to get what they want. Early "AI' usage popular practices so far looks to be accelerating that. Schools should be dropping a brick wall in front of that. Well, a padded wall, for the students who can still be saved.

Re: I'd rather read the prompt

#116

Post by squigz »

bruce511 wrote: post #15
Ancalagon wrote: post #8

I fully support the author’s point but it’s hard to argue with the economics and hurdles around obtaining degrees. Most people do view obtaining a degree as just a hurdle to getting a decent job, that’s just the economics of it. And unfortunately the employers these days are encouraging this kind of copy/paste work. Look at how Meta and Google claim the majority of the new code written there is AI created? The world…

You get what you measure, and you should expect people to game your metric. Once upon a time only the brightest (and / or richest) went to college. So a college degree becomes a proxy for clever. Now since college graduates get the good jobs, the way to give everyone a good job is to give everyone a degree. And since most people are only interested in the job, not the learning that underpins the degree, well, you get…

> you get a bunch of students that care only for the pass mark and the certificate at the end.

This is because that is what companies care about. It's not a proxy for cleverness or intelligence - it's a box to check.

Re: I'd rather read the prompt

#117

Post by Herring »

robwwilliams wrote: post #106

I ask Claude to respond like Hemingway would. It works.

I think half the population of the world wants just the facts, the other half wants long flowing beautiful content like on apple.com, and neither group knows the other exists. Of course this is the right way to do it!

Re: I'd rather read the prompt

#118

Post by throwaway173738 »

closewith wrote: post #77
bee_rider wrote: post #66

Earlier quoted context omitted.

I think, rather than saying they can’t do their job without an LLM, we should just say some can’t do their jobs. That is, the job of a professional programmer includes having produced code that they understand the behavior of. Otherwise you’ve failed to do your due diligence. If people are using LLMs to generate code, and then actually doing the work of understanding how that code works… that’s fine! Who cares! If pe…

> That is, the job of a professional programmer includes having produced code that they understand the behavior of. I have met maybe two people who truly understood the behaviour of their code and both employed formal methods. Everyone else, including myself, are at varying levels of confusion.

If you want to put the goalposts there, why program instead of building transistor networks?

Re: I'd rather read the prompt

#119

Post by patrickmay »

tomjen3 wrote: post #34

I wish the author had state out right that they were not using LLMs much, since their opinion on them and their output has no value (its a new technology, and different enough that you do have to spend some time with them in order to be able to find out what value they have for your particluar work[0]. The is especially the case when you are about to complain about style, since that can easily be adjusted, by simply…

If an LLM is better at writing than you are, you should work on improving your writing.

This is especially true for students.

Re: I'd rather read the prompt

#120

Post by oncallthrow »

cortesoft wrote: post #82
oncallthrow wrote: post #46

Earlier quoted context omitted.

> Do you really want to read the students original thought? Why else would you become a teacher, if you didn't care about what your students think?

Because you want to pass on knowledge? I am not saying there aren't ANY situations where a teacher cares about what their students think, but the example given isn't really one of those times. The question is not one that has many opportunities for original thought; it is a basic question that everyone who knows the answer will answer similarly. The entire purpose is to ascertain if the person understands what was ta…

How do you know if you have passed on your knowledge without knowing what your students think/know?
Post reply on HN