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

461–470 of 880 posts

Re: I'd rather read the prompt

#461

Post by nojs »

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…

> it's that the thought that went into making the prompt is, inevitably, more interesting/original/human than the output the LLM generates afterwards

I think you are overestimating the people who submit this slop. It’s more like “here’s my assignment, what’s the answer”

Re: I'd rather read the prompt

#462

Post by Ma8ee »

7bit wrote: post #425
rohansood15 wrote: post #400

Earlier quoted context omitted.

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. It has value, because companies value it. It sets the starting point for your first salary and then for every salary negotiation moving forward. As someone who did not go to university, but has the same knowledge self-taught I can tell you that this piece of paper would have opened so many doors and made life so much easier. It took…

And companies value it because it signals that the holder of that paper can do the work and isn’t completely stupid.

Re: I'd rather read the prompt

#464

Post by I-M-S »

beAroundHere wrote: post #460
jameshart wrote: post #329

Earlier quoted context omitted.

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.

I think you're quoting the Sci Fi author - Ken Liu from his article in some major news outlet. I related with that analogy too, infact that whole piece is worth reading. I can't seem to find it's link though!

It's because you've mixed him up with Ted Chiang - the article in question is Why A.I. Isn’t Going to Make Art [1]

[1] https://archive.is/kS8NY

Re: I'd rather read the prompt

#465

Post by genewitch »

agentultra wrote: post #217
torben-friis wrote: post #128

Earlier quoted context omitted.

“Someone sent me this ai generated message. Please give me your best shot at guessing the brief prompt that originated the text”. Done, now ai is just lossy prettyprinting.

An incredible use of such advanced technology and gobs of energy.

What will me make the rocks with lightning in do next?!

Re: I'd rather read the prompt

#467

Post by ijidak »

ChadNauseam wrote: post #358
jameshart wrote: post #329

Earlier quoted context omitted.

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.

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…

Absolutely. Also, the level of cheating in college, even pre-AI is often overlooked in these articles.

For the exact reasons you state, pre-AI homework was often copied and then individuals just crammed for the tests.

AI is not the problem for these students, it's that many students are only in it for the diploma.

If it wasn't AI it would just be copying the assignment from a classmate or previous grad.

And I imagine the students who really want to learn are still learning because they didn't cheat then, and they aren't letting AI do the thinking for them now.

Re: I'd rather read the prompt

#468

Post by ijidak »

The level of cheating in college, pre-AI, is often overlooked in these articles.

Pre-AI, homework was often copied and then individuals just crammed for the tests.

AI is not the problem for these students, it's that many students are only in it for the diploma.

If it wasn't AI it would just be copying the assignment from a classmate or previous grad.

And I imagine the students who really want to learn are still learning because they didn't cheat then, and they aren't letting AI do the thinking for them now.

Re: I'd rather read the prompt

#469

Post by sussmannbaka »

People defending this are wrong in an additional, more pathetic way: Even if you insist on “cheating” and using an LLM to communicate, you are using it badly. You manage to be obviously incompetent at using the tool you are evangelizing.

Re: I'd rather read the prompt

#470

Post by mikepurvis »

derefr wrote: post #13

> They are invariably verbose, interminably waffly, and insipidly fixated on the bullet-points-with-bold style. No, this is just the de-facto "house style" of ChatGPT / GPT models, in much the same way that that that particular Thomas Kinkade-like style is the de-facto "house style" of Stable Diffusion models. You can very easily tell an LLM in your prompt to respond using a different style. (Or you can set it up to…

I was surprised to see such world-weary criticism of the bullet-points-with-bold style in TFA— it's long been what I've reached for when writing for a technical audience, whether that's in a wiki page, a design doc, a README, a PR, or even a whole book.

I feel like for most of my audiences it provides the proper anchor points for effective skimming while still giving me room to include further detail and explanation so that it's there as desired by the reader.

(And responding to my sibling comment, I also use em dashes and semicolons all the time. Has my brain secretly always been an LLM??)

Post reply on HN