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

861–870 of 880 posts

Re: I'd rather read the prompt

#861

Post by articsputnik »

In times of AI Writing, writing manually is more important than ever. As with many AI Generated texts, I’d rather see the prompts, it would have more soul and character than the output.

I couldn’t agree more with the sentiment of this article.

Writing yourself, _writing manually_ is much nicer, to hear your unfiltered thoughts, than condensing them through an LLM, and get average-sounding sentences with no soul. To me, LLM writing is soulless. I even started to turn to Grammarly and Copilot, as these were a mere distraction to the actual task at hand: writing. Instead of writing, I was constantly grammar fixing, and ultimately, nothing got done. I love the gym-analogy https://news.ycombinator.com/item?id=43888803 gave.

Re: I'd rather read the prompt

#862

Post by bumby »

godelski wrote: post #847
bumby wrote: post #832

Earlier quoted context omitted.

You realize employers are sometimes regulated by who they can hire, right? A nurse often must be licensed. An engineer who stamps designs (ie one who isn’t under an exemption) has to be licensed. One of the major steps in that process is getting an accredited degree. (Yes, there are edge cases where you may be licensed without an engineering degree, but those are so vanishingly rare as to not really be a factor). The…

You are pointing out exceptions rather than the norms. Do not cherry-pick. I'm pretty confident that most people in these threads are thinking about computer programmers, white color jobs, and blue color jobs. Things that don't obviously need a degree . Depending on the type of nurse, you do not need a degree. Some will need to pass an exam though. You can become a lawyer without a degree, only needing to pass the BA…

I’m not moving the goalposts. Your words were that employers have “complete autonomy”. That’s obviously not the case, and those are pretty large swaths of professions to pretend like they are edge cases. And FWIW, if you read up on engineer licensure, you’ll realize it isn’t just a small subset of engineers falling under the purview of the regulations but there are carve-outs for “industrial exemptions”. Most people don’t even realize they’re working under an exemption. But many states are bring these exemptions into questions due to high profile failures like Boeing etc. (and the exam is national, but the license is state).

We agree on most, I just think you tend to think on absolutes and I do not. I don’t think most current degree progressions need degrees, but I’m willing to recognize there is a large subset what do. And colleges still hold a monopoly on those degree. But the fact you can’t follow HN guidelines because you’re proved to argue makes further discussion boring and fruitless.

Re: I'd rather read the prompt

#863

Post by robertlagrant »

jama211 wrote: post #375
natebc wrote: post #156

Earlier quoted context omitted.

Honestly I think we'll get back there. I remember ... fondly(?) exams from my history courses in undergrad in the mid 90s. 3-4 questions, 3 hours, anything less than what would amount to a pretty decent length and moderately thorough term paper would fail and have to be made up with an absolutely BRUTAL multiple choice + fill in the blank exam at the end of the term. Those classes are what taught me how to study and…

You might be the only person in history who remembers fondly being stressfully forced to write essays in exams.

I don't think so. If you're able to write essays and know the subject matter, it's not too bad. It's stressful because of what the essay stands for in terms of your future, but so is solving a simultaneous equation in that sense.

Re: I'd rather read the prompt

#864

Post by senordevnyc »

palata wrote: post #667
senordevnyc wrote: post #664

Earlier quoted context omitted.

* I think you missed the point of the article. They did not mean it literally: it's a way to say that they are interested in what you have to say.* Maybe an LLM could have helped the writer say what they meant to.

Maybe if people were more used to reading and less to copy-pasting into LLMs, they would understand the article.

If your readers don’t understand what you’re writing, it’s your fault as the author. There’s so much good stuff to read, why waste time on someone who can’t organize or articulate their thoughts?

Re: I'd rather read the prompt

#865

Post by StefanBatory »

thugthrasher wrote: post #728
Balgair wrote: post #511

Earlier quoted context omitted.

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.

I have classes like these, but at a small Masters programme and only on our courses directly related to specialisation :D

Re: I'd rather read the prompt

#866

Post by zamadatix »

AdieuToLogic wrote: post #826
zamadatix wrote: post #349

Earlier quoted context omitted.

At times there is value in that kind of approach, especially when the learning is specifically about those kinds of lower layers instead of higher concepts. As such, it's not that certain tools should be used in every assignment or never ever used, just whether they should be used commonly. For most continued learning it's better if the university uses calculators, compilers, prepared learning materials, and other th…

> For most continued learning it's better if the university uses calculators, compilers, prepared learning materials, and other things that do stuff on behalf of the students instead of setting the bar permanently to "the student should want to engage everything at a base level or they must not be here to learn". IMHO, the example of using calculators in a learning environment is a great topic to explore. Using calcu…

While I agree with nearly everything you say here, 90% of college isn't about sticking to the fundamentals like how elementary students didn't use calculators at first. This leads to the disagreement this discussion is related to the statement "Am I here to learn or to get a passing grade?". We both agree students need to be there to learn to get anything useful out of the university, what we're disagreeing on is how they best do that for the majority of university level content.

Re: I'd rather read the prompt

#867

Post by ascorbic »

simonask wrote: post #546
ascorbic wrote: post #520

Earlier quoted context omitted.

Most people don't go to college to learn for the sake of learning – that would be a very expensive luxury. They go for the opportunities that it opens up. The learning itself helps with that, but so does being able to prove that they've learned it. That what the diploma is meant to be for.

That's a US-centric view. A huge number of people in the world have access to high level education free of charge.

I'm not American. I said most people, and most people in the world don't have free university education.

Re: I'd rather read the prompt

#868

Post by whattheheckheck »

johnnyanmac wrote: post #818
indymike wrote: post #681

Earlier quoted context omitted.

> Using an LLM to do schoolwork is like taking a forklift to the gym. I'm sure the time has come for college students to master using LLMs. It's just as important as grammar or basic math now. The software I build (and the entire tech industry) automates huge swaths of business processes with AI. Students need to be able to understand, work with, and manage swarms of AI agents doing work. To stick to the analogy: I n…

If you need forkloft drivers, don't recruit at the gym and be mad no one is forklift certified there. This isn't even an opinion on LLMs, it's recruiting 101. You're free to convince the gym to train forklift drivers, but don't be surprised when you're laughed out the room.

It's the other way around... people will happily pay to be "forklift driver certified" and a piece of paper that gets them a bit higher in the hiring line. Especially when they'll pay way more for that than ethereal "thinking skills" that they can't even reason why they'd need that in the first place

Re: I'd rather read the prompt

#869

Post by necovek »

dcre wrote: post #742
necovek wrote: post #523

Earlier quoted context omitted.

"Saying" vs "demonstrating": I am careful with the words I am using. It's not just nitpicking: maybe it's only their perception they are more productive? Or maybe they are. But saying it is not convincing enough for me.

That's a good point, though it's worth thinking about what would count as a demonstration. Pointing to a PR that an LLM helped with is not enough because you don't know how long it would have taken without the use of LLMs. The counterfactual never really exists. What is the hard evidence vim or emacs makes people more productive? Using git over svn? Using search engines? Over time, we expect people to use the things…

I would assume honesty, so someone showing with a blog post their incremental progress, prompting or code assistant use, rough time spent on each iteration... would be a great start.

I am not looking for formal study level of trust (though even that is frequently debatable), but multiple accounts of this where there is clear quality of output and significant (estimated) time savings would be wonderful.

I don't need much convincing that for many engineers, an LLM can bring incremental speed up (10-20%), though I think that really depends on the personality (eg. do you prefer to fix stuff not created by you or write it nicely from the start?).

Re: I'd rather read the prompt

#870

Post by remich »

WatchDog wrote: post #443
vunderba wrote: post #31

Earlier quoted context omitted.

This is the CRUX of the issue. Even with SOTA models (Sonnet 3.5, etc) - the more open-ended your prompt - the more banal and generic the response. It's GIGO turtles all the way down. I pointed this out a few weeks ago with respect to why the current state of LLMs will never make great campaign creators in Dungeons and Dragons. We as humans don't need to be "constrained" - ask any competent writer to sit quietly and…

When using Claude Sonnet 3.7 for coding, I often find that constraints I add to the prompt, end up producing unintended side effects. Some examples: - "Don't include pointless comments." - The model doesn't keep track of what it's doing as well, I generally just do another pass after it writes the code to simplify things. - "Keep things simple" - The model cuts corners(often unnecessarily) on things like type safety.…

The unfortunate implication to this is that many codebases Claude has been trained on just choose not to handle errors...
Post reply on HN