Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Do your own writing

alexhwoods.com

Post reply on HN
Print view View original

11–20 of 265 posts

Re: Do your own writing

#11

Post by fleebee »

You quote this:

> LLM-generated writing undermines the authenticity of not just one’s writing but of the thinking behind it as well. If the prose is automatically generated, might the ideas be too?

Given your endorsement of using LLMs for generating ideas, isn't this the inverse of your thesis? The quote's issue with LLMs is the ideas that came out of them; the prose is the tell. I don't think they'd be happy with LLM generated ideas even if they were handwritten.

I feel like this post is missing the forest for the trees. Writing is thinking alright, but fueling your writing by brainstorming with an LLM waters down the process.

Re: Do your own writing

#12

Post by nerevarthelame »

I agree with most of this, but my one qualm is the notion that LLMs "are particularly good at generating ideas."

It's fair enough that you can discard any bad ideas they generate. But by design, the recommendations will be average, bland, mainstream, and mostly devoid of nuance. I wouldn't encourage anyone to use LLMs to generate ideas if you're trying to create interesting or novel ideas.

Re: Do your own writing

#13

Post by bluepeter »

Nowadays my writing (and maybe all of ours) has totally devolved into "prompt-ese." Much like days of yore where we all approached Google searches with acrobatic language knowing how to specifically get something done.

Now? I am pushing so much of my writing into prompts into AI where I know the AI will understand me even with lots of typos and run-on sentences... Is that a bad thing? A good thing? I am able to be so much more effective by sheer volume of words, and the precision and grammar is mostly irrelevant. But I am able to insert nuances and sidetracks that ARE passing vital context to AI but may be lost on people. Or at least pre-prompt-writing people.

Re: Do your own writing

#14

Post by paulpauper »

Letting an LLM write for you is like paying somebody to work out for you.

The problem with writing is the feedback tends to be inconsistent. With going to the gym you can track your progress quantitatively such as how fast or far you can run or weight lifted, but it's sometimes hard to know if you're improving at writing.

Re: Do your own writing

#15

Post by gbro3n »

I fully agree with the sentiment of the article. I will say that I feel I've had some success in having an LLM outline a document, provided that I then go through and read / edit thoroughly. I think there's even an argument that this a) possibly catches areas you I have forgotten to write about, and b) hooks into my critique mode which feels more motivated than author mode sometimes (I'm slightly ashamed to say). This does come at the cost however of not putting my self in 'researcher' mode, where I go back through the system I'm writing about and follow the threads, reacquainting myself and judging my previous decisions.

Re: Do your own writing

#16

Post by dummydummy1234 »

nerevarthelame wrote: post #12

I agree with most of this, but my one qualm is the notion that LLMs "are particularly good at generating ideas." It's fair enough that you can discard any bad ideas they generate. But by design, the recommendations will be average, bland, mainstream, and mostly devoid of nuance. I wouldn't encourage anyone to use LLMs to generate ideas if you're trying to create interesting or novel ideas.

I have found the one of the better use cases of llms to be a rubber duck.

Explaining a design, problem, etc and trying to find solutions is extremely useful.

I can bring novelty, what I often want from the LLM is a better understanding of the edge cases that I may run into, and possible solutions.

Re: Do your own writing

#17

Post by atmosx »

fleebee wrote: post #11

You quote this: > LLM-generated writing undermines the authenticity of not just one’s writing but of the thinking behind it as well. If the prose is automatically generated, might the ideas be too? Given your endorsement of using LLMs for generating ideas, isn't this the inverse of your thesis? The quote's issue with LLMs is the ideas that came out of them; the prose is the tell. I don't think they'd be happy with LL…

I take it ideas to mean “well scoped replies” like “list pro and con if this vs that got flow”. While someone might think of N issues the LLM might present another six out of which three or four don’t make sense but one or two do. Might be worth adding these in the document.

Re: Do your own writing

#18

Post by j45 »

nerevarthelame wrote: post #12

I agree with most of this, but my one qualm is the notion that LLMs "are particularly good at generating ideas." It's fair enough that you can discard any bad ideas they generate. But by design, the recommendations will be average, bland, mainstream, and mostly devoid of nuance. I wouldn't encourage anyone to use LLMs to generate ideas if you're trying to create interesting or novel ideas.

Asking the LLM better will return better than average and bland and mainstream results.

Re: Do your own writing

#19

Post by dgxyz »

nerevarthelame wrote: post #12

I agree with most of this, but my one qualm is the notion that LLMs "are particularly good at generating ideas." It's fair enough that you can discard any bad ideas they generate. But by design, the recommendations will be average, bland, mainstream, and mostly devoid of nuance. I wouldn't encourage anyone to use LLMs to generate ideas if you're trying to create interesting or novel ideas.

All LLM output is always dry as fuck quite frankly. At all levels from ideas and concepts through to the actual copy. And that’s dotted with pure excrement.

I think the only reason it’s seen as good anywhere is there are a lot of tasteless and talentless people who can pretend they created whatever was curled out. This goes for code as well.

If I offend anyone I will not be apologising for it.

Re: Do your own writing

#20

Post by paulryanrogers »

j45 wrote: post #18
nerevarthelame wrote: post #12

I agree with most of this, but my one qualm is the notion that LLMs "are particularly good at generating ideas." It's fair enough that you can discard any bad ideas they generate. But by design, the recommendations will be average, bland, mainstream, and mostly devoid of nuance. I wouldn't encourage anyone to use LLMs to generate ideas if you're trying to create interesting or novel ideas.

Asking the LLM better will return better than average and bland and mainstream results.

How does one ask better? Does better vary per model?
Post reply on HN