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

61–70 of 265 posts

Re: Do your own writing

#61

Post by jrowen »

monkaiju wrote: post #25
dummydummy1234 wrote: post #16

Earlier quoted context omitted.

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.

I always find folks bringing up rubber ducking as a thing LLMs are good at to be misguided. IMO, what defines rubber ducking as a concept is that it is just the developer explaining what their doing to themselves. Not to another person, and not to a thing pretending to be a person. If you have a "two way" or "conversational" debugging/designing experience it isnt rubber ducking, its just normal design/debugging. The…

I feel I've had the most success with treating it like another developer. One that has specific strengths (reference/checklists/scanning) and weaknesses (big picture/creativity). But definitely bouncing actual questions that I would say to a person off it.

Re: Do your own writing

#62

Post by deevelton »

jonathaneunice wrote: post #29

Agree with the underlying point: "don't let an LLM do your thinking, or interfere with processes essential to you thinking things clearly through." My own experience, however, is that the best models are quite good and helping you with those writing and thinking processes. Finding gaps, exposing contradictions or weaknesses in your hypotheses or specifications, and suggesting related or supporting content that you mi…

was curious how it might look if we started seeing prompts/steering inline with the finished product: https://dvelton.github.io/trace/examples/the-post.html

Re: Do your own writing

#63

Post by j45 »

paulryanrogers wrote: post #20
j45 wrote: post #18

Earlier quoted context omitted.

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

How does one ask better? Does better vary per model?

Yes, its context based.

It's like asking a coworker. Providing too little information, or too much context can give different responses.

Try asking the model to not provide it's most common or average answer.

Been using it this way for 2, almost 3 years.

Re: Do your own writing

#64

Post by Waterluvian »

monkaiju wrote: post #25
dummydummy1234 wrote: post #16

Earlier quoted context omitted.

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.

I always find folks bringing up rubber ducking as a thing LLMs are good at to be misguided. IMO, what defines rubber ducking as a concept is that it is just the developer explaining what their doing to themselves. Not to another person, and not to a thing pretending to be a person. If you have a "two way" or "conversational" debugging/designing experience it isnt rubber ducking, its just normal design/debugging. The…

Maybe it’s just a semantic distinction, which, sure. I guess I’d just call it research? It’s basically the “I’m reading blogs, repos, issue trackers, api docs etc. to get a feel for the problem space” step of meaningful engineering.

But I definitely reach for a clear and concise way to describe that my brain and fingers are a firewall between the LLM and my code/workspace. I’m using it to help frame my thinking but I’m the one making the decisions. And I’m intentionally keeping context in my brain, not the LLM, by not exposing my workspace to it.

Re: Do your own writing

#65

Post by borski »

Writing well is a superpower, and even better in a world where “no one” is writing well.

LLMs write poorly because most people write poorly. They didn’t cause it, they simply emulate it.

Re: Do your own writing

#66

Post by j45 »

contagiousflow wrote: post #21
j45 wrote: post #18

Earlier quoted context omitted.

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

Why would they return "better" results?

Because AI is not a search engine. It does not return the best search result every time.

What it considers best, is what occurs most often, which can be the most average answers. Unless the service is tuned for search (perplexity, or google itself for example), others will not provide as complete an answer.

How well we ask can make all the difference. It's like asking a coworker. Providing too little information, or too much context can give different responses.

Try asking the model to not provide it's most common or average answer.

Been using it this way for 2, almost 3 years.

Re: Do your own writing

#67

Post by jasoneckert »

For me, drawing the line as to when you will leverage AI and when you won't comes down to a quote from Kurt Vonnegut: "Practicing an art, no matter how well or badly, is a way to make your soul grow, for heaven's sake. Sing in the shower. Dance to the radio. Tell stories. Write a poem to a friend, even a lousy poem. Do it as well as you possibly can. You will get an enormous reward. You will have created something."

Art is where I choose to draw the line, for both ideation and content generation. That work report I leveraged AI to help flush out isn't art, but my personal blog is, as is anything I must internalize (that is thoroughly understand and remember). This is why I have the following disclaimer on my blog (and yes, the typo on this page is purposeful!): https://jasoneckert.github.io/site/about-this-site/

Re: Do your own writing

#68

Post by smallerfish »

Bad AI writing is bad, and obvious once you know what you're looking for. Nobody wants to read it.

Good AI writing takes time, can be valuable, and can inspire readers to send in praise about how insightful or thorough a particular article was (speaking from experience). Why do it? The same reason we all use Claude all day to write code - it is faster / you can do more of it. But in the same way that a junior engineer vibing code is a lot more likely to produce slop than a grizzled senior who is doing the same thing, you have to know what you are doing to get good results out of it.

Pushing back against AI writing in 2026 is like the people pushing back against AI coding in 2024. It's not a question of if it will happen. It's a question of how to do it well. ;)

Re: Do your own writing

#69

Post by rrherr »

CharlesW wrote: post #5

The title and of this article is Don't Let AI Write For You , when its point seems to be closer to Don't Let AI Think For You (see "Thinking"). This distinction is important, because (1) writing is not the only way to faciliate thinking, and (2) writing is not neccessarily even the best way to facilitate thinking. It's definitely not the best way (a) for everyone, (b) in every situation. Audio can be a great way to c…

> Audio can be a great way to capture ideas and thought processes ... This can work especially well for people who are distracted by form and "writing correctly" too early in the process, for people who are intimidated by blank pages, for non-neurotypical people, etc. Self-recording is a great way to set all of those artifacts of the medium aside and capture what you want to say.

Yes, this is my process:

Record yourself rambling out loud, and import the audio in NotebookLM.

Then use this system prompt in NotebookLM chat:

> Write in my style, with my voice, in first person. Answer questions in my own words, using quotes from my recordings. You can combine multiple quotes. Edit the quotes for length and clarity. Fix speech disfluencies and remove filler words. Do not put quotation marks around the quotes. Do not use an ellipsis to indicate omitted words in quotes.

Then chat with "yourself." The replies will match your style and will be source-grounded. In fact, the replies automatically get footnotes pointing to specific quotes in your raw transcripts.

This workflow may not save me time, but it helps me get started, or get unstuck. It helps me stop procrastinating and manage my emotions. I consider it assistive technology for ADHD.

Re: Do your own writing

#70

Post by fallinditch »

The rational response to document overload is to mostly ignore it.

Workers and managers in organizations are being overwhelmed by large numbers of documents because it's so easy to bang something off that's 'about right' and convincing enough.

But there's still some value in writing documents. I agree with the original article - it's all about thinking. My take on it is this: it's possible to use LLMs to write decent documents so long as you treat the process as a partnership (man and machine), and conduct the process iteratively. Work on it, and yes, think.

Post reply on HN