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

731–740 of 880 posts

Re: I'd rather read the prompt

#731

Post by thugthrasher »

tpmoney wrote: post #612
zeroq wrote: post #255

Earlier quoted context omitted.

You're missing trees for forest. When I was a kid and got an assignement for writing an essey about "why good forces prevailed in Lords of the Rings" as a gate check to see if I actually read the novel I had three choices: (a) read the novel and write the essey myself (b) find an already written essey - not an easy task in pre-internet era but we had books with esseys on most common topics you could "copy-paste" - an…

> Today I can ask ChatGPT to write me a 4 pages essay about a novel I've never heard of and call it a day. There's no value gained in the process. If we take the original article at face value, no you can't do that. ChatGPT will apparently produce something that is obviously ChatGPT produced and fail to fool even the most absent minded of instructors that you have read the material. So even with a ChatGPT LLM to help…

ChatGPT and the like are in a weird position at the moment. It's usually pretty clear that you have written it using an LLM, but it's hard to PROVE. And you need to be able to prove it (to some degree, which varies depending on the institution) to reliably count off for it, otherwise the student will challenge your finding that they cheated and the Honor Court (or administrator, or other equivalent) will tell you that you can't do that.

So, you can usually get away with it if there is not some way the professor/TA can prove it.

As things change, this will change, but that's the situation the author of the original article finds themself in, because it's the current situation.

Re: I'd rather read the prompt

#732

Post by 49531 »

austin-cheney wrote: post #726

> 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…

I don't think using dependencies or frameworks is any different than using a word processor for writing. They're tools that get you to the real work of writing original code.

Re: I'd rather read the prompt

#733

Post by zhyder »

Strongly agree with the author that the original prompt is much more substantive, but I think they're mistaken that "skin in the game" is a small motivating factor for human written text. It's the entire motivation: we all want to look like we've done more (get better grades at school, or get better compensation at work) while minimizing effort. We're not incentivized to produce just the substance, coz effort scales O(substance).

Re: I'd rather read the prompt

#734

Post by thomasfedb »

zhyder wrote: post #733

Strongly agree with the author that the original prompt is much more substantive, but I think they're mistaken that "skin in the game" is a small motivating factor for human written text. It's the entire motivation: we all want to look like we've done more (get better grades at school, or get better compensation at work) while minimizing effort. We're not incentivized to produce just the substance, coz effort scales…

I would argue against “entire”. As an academic I (and I believe many of my colleagues also) take much pride in what we write - both the content and the prose itself.

Re: I'd rather read the prompt

#735

Post by austin-cheney »

49531 wrote: post #732
austin-cheney wrote: post #726

> 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…

I don't think using dependencies or frameworks is any different than using a word processor for writing. They're tools that get you to the real work of writing original code.

Frameworks and language code packages are not code editors or IDEs.

Re: I'd rather read the prompt

#736

Post by necovek »

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's no accident most of the software development world gravitated toward free and open source tooling: proprietary tool-specific code and build recipes have the same gotchas as the model-specific context would have today.

So perhaps switching to open-source models of sufficient "power" will obsolete that particular concern (they would be a "development dependency", just like a linter, compiler or code formatter are today).

Re: I'd rather read the prompt

#737

Post by necovek »

Falimonda wrote: post #317
necovek wrote: post #54

I've already asked a number of colleagues at work producing insane amount of gibberish with LLMs to just pass me the prompt instead: if LLM can produce verbose text with limited input, I just need that concise input too (the rest is simply made up crap).

And you do what with the prompt once you have it?

Get all the information of value that was hidden behind 2-10k words generated by an LLM.

Re: I'd rather read the prompt

#738

Post by normyguy »

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…

Dangers of Intelligence and Other Scientific Essays by Asimov predicted all this hullabaloo quite a while ago. So, yeah, seems like evidence to support your position. Welcome to the party. :)

Re: I'd rather read the prompt

#739

Post by normyguy »

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.

Dangers of Intelligence and Other Scientific Essays by Asimov predicted all this hullabaloo quite a while ago. So, yeah, seems like evidence to support your position. Welcome to the party. :)

Re: I'd rather read the prompt

#740

Post by indymike »

doctorwho42 wrote: post #704
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…

But the thing you are missing is that one needs a solid foundation of knowledge of the actual work to be able to manage it well. Someone with years of coding experience is going to be able to laser guide an AI agent to the answer/result than someone who has muddled their way through comp sci 101 using an AI chatbot.

No one is saying they don't need a solid foundation of knowledge. The knowledge needed is different. What we're seeing now is lot like teaching people to care for a horse even though the automobile is now the dominant form of transportation
Post reply on HN