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

721–730 of 880 posts

Re: I'd rather read the prompt

#721

Post by walleeee »

phamilton wrote: post #685
walleeee wrote: post #655

Earlier quoted context omitted.

I don't think form and function can be separated so cleanly in natural language. However you encode what's between your ears into text, you've made (re)presentational choices. A piece of text does not have a single inherently correct interpretation. Its meaning is a relation constructed at run- (i.e. read-)time between the reader, the writer, and (possibly) the things the text refers to, that is if both sides are wel…

My LLM workflow involves a back-and-forth clarification (verbose input -> LLM asks questions) that results in a rich context representing my intent. Generating comments/docs from this feels lossy. What if we could persist this final LLM context state? Think of it like a queryable snapshot of the 'why' behind code or docs. Instead of just reading a comment, you could load the associated context and ask an LLM question…

It sounds worthwhile. I just wonder how you envision the author encoding their reasoning state. If as (terse) text, how would the author know the LLM successfully unpacks its meaning without interrogating it in detail, and then fine-tuning the prompt? And at that point, it would probably be faster to just write more verbose docs or comments?

What about a tool that simply allows other developers to hover over some code and see any relevant conversations the developer had with a model? Version the chat log and attach it to the code basically.

Re: I'd rather read the prompt

#722

Post by firesteelrain »

tcmart14 wrote: post #415
bumby wrote: post #356

Earlier quoted context omitted.

This attitude is part of a more general cultural shift. Back in the 1960s, the majority of students said the primary motivation for going to college was to develop a philosophy of life, and a minority said the main goal was to be very financially successful. Somewhere around the 1980s this started to shift and the proportions are now inverted. * according to the UCLA CIRP freshman survey

I would also say some of the attitude shift is also contradictory. The amount of people I interact with who have a lot of bad things to say about the education who tell me universities should focus on education in a general meanwhile also say that schools to should focus on student getting jobs. Probably one that has been heard before, something along the lines of, "why don't high schools teach plumbers courses." I m…

Where I am at, you can learn a skill in high school either via elective or a career technical track like working on airplanes, HVAC, construction, etc. Back in the 90s, I took automotive electives because I liked to work on cars back then. It would prepare you to work at a small automotive shop or as a hobby. I realized that it didn't make that much money so switched to computers.

Re: I'd rather read the prompt

#723

Post by vishnugupta »

nine_k wrote: post #436
animal_spirits wrote: post #424

Earlier quoted context omitted.

Further, if a student can get a diploma without work, then the diploma does not have value anymore. If diplomas are no longer valuable, the signal they provide in the labor market will turn into noise. If employers no longer look for the diploma-signal in an employee, what will be the reason an employer will hire an employee? I think this story will become true, and society will radically shift into one where critica…

In a medieval guild, to be admitted as a master, an apprentice had to create a chef d'oevre, or masterpiece, so called for this reason. In the computer engineering industry, you increasingly have to demonstrate the same: either as a part of your prior work for hire, or a side project, or a contribution to something open-source. A diploma is still a useful signal, but not sufficient, except maybe for very junior posit…

I was somewhat aware that in medieval period most started out as an apprentice in mid teens. Essentially work slaves in the house of a master. Then after a decade or so of toiling and gaining the skill they would go on to become individual business owners.

But I wasn’t aware about the master peace. Thank you for sharing that!

Re: I'd rather read the prompt

#724

Post by vishnugupta »

animal_spirits wrote: post #424
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.

Further, if a student can get a diploma without work, then the diploma does not have value anymore. If diplomas are no longer valuable, the signal they provide in the labor market will turn into noise. If employers no longer look for the diploma-signal in an employee, what will be the reason an employer will hire an employee? I think this story will become true, and society will radically shift into one where critica…

I was somewhat downvoted for saying something similar recently here [1].

Four year degree is a very expensive investment in the current environment. We should push younger people to face the real world as soon as possible. Apprenticeship is indeed a great way to achieve that IMO. As a great side effect the young people won’t have to start out their careers saddled with huge debt.

[1] https://news.ycombinator.com/item?id=43768903

Re: I'd rather read the prompt

#725

Post by tptacek »

necovek wrote: post #522
tptacek wrote: post #150

Earlier quoted context omitted.

LLMs don't make bad programmers into good programmers. If your team is comfortable merging "crap", you have deeper problems.

If you don't want to engage in an honest discussion, please refrain from making assumptions: nobody mentioned "merging crap". I stopped clearly at guiding an LLM to make a code change, which is at best, a pull request.

How is that better? As a team lead, what would you think of a team member who consistently generated "crap" pull requests?

You see the same thing in every argument with LLM skeptics. 'The code is bad. You don't even know what the code is doing." This is obviously false. A professional reads the code they commit and push. A professional doesn't push code they know to be bad.

Re: I'd rather read the prompt

#726

Post by austin-cheney »

> Don’t let a computer write for you!

To play devil's advocate original code alienates you from many programming jobs. This was true before LLMs, and remains true now. Many developers abhor original code. They need frameworks or packages from Maven, NPM, pip, or whatever. They need to be told exactly what to do in the code, but copy/paste is better, and a package that already does it for you is better still. In these jobs, yes, absolutely let a computer write it for you (or at least anybody that is an untrusted outside stranger). Writing the code yourself will often alienate you from your peers and violate some internal process.

Re: I'd rather read the prompt

#727

Post by Gracana »

ineptech wrote: post #86

Relatedly, there was a major controversy at work recently over the propriety of adding something like this to a lengthy email discussion: > Since this is a long thread and we're including a wider audience, I thought I'd add Copilot's summary... Someone called them out for it, several others defended it. It was brought up in one team's retro and the opinions were divided and very contentious, ranging from, "the summar…

Maybe your co-worker will see the responses here and learn their lesson.

Nobody will call you a lazy and incompetent coward for taking the default option: Hit reply-all, write your one-sentence response above all 50 quoted emails, hit send.

Re: I'd rather read the prompt

#728

Post by thugthrasher »

Balgair wrote: post #511
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 we have to hold off a bit on the whole thing here. Look, we have no idea what the feedback is like that this grad student gives, what the class sizes are like, what the cadence is, what the grade percentages are, etc. All we know is that Clayton Ramsey is a grad student at Rice in the robotics department and that he wrote a hot take here. For me, the most important thing is if this grader is bothering to real…

We will never reduce all class sizes to under 10 people. Large R1 schools are not going to reduce their number of students by a factor of 10 or increase their hiring by a factor of 10.

Re: I'd rather read the prompt

#729

Post by insane_dreamer »

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…

> let their brains atrophy only to get a piece of paper

this isn't the root of the problem

the root of the problem is that higher education has become, for the most part, an exercise in getting a piece of paper, so that you can check a box on a form or pass first level screening for a job

Re: I'd rather read the prompt

#730

Post by qwertox »

I write my emails to people like the HoA myself, but always feed it into an LLM to make sure the point comes across. There are always so many corrections suggested, that I'd end up writing a precise mail, but one which I'd never had written that way. It's just not me in that mail. So I have the task to find a middle ground of what I need to remove from mine in order for it to be as easily understandable as the one the LLM suggests.

Am I alone with this?

Post reply on HN