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

What if AI didn't make you a bad writer, but a better thinker?

slite.com

Post reply on HN
Print view View original

31–40 of 127 posts

Re: What if AI didn't make you a bad writer, but a better thinker?

#31

Post by now__what »

rqtwteye wrote: post #7

I look forward to most tech writing done with AI. Writing documentation and requirements requires a lot of effort to keep consistent and up to date. Having an AI look at your code and config and then write a nice report will easily beat 99% of all tech docs in companies.

I'd love for this to be the case, but often the most(/only) important part of a tech doc is the "why," i.e. the background knowledge about the business itself, or the conceptual framework that underlies the code. Even more so for writing requirements. How would AI be able to help with that? Maybe by parsing through all related meeting transcripts as well?

Re: What if AI didn't make you a bad writer, but a better thinker?

#32

Post by melanieb421 »

mistermann wrote: post #23
Whitespace wrote: post #20

Earlier quoted context omitted.

That is quite literally what the article talks about.

It seemed rather light on details to me, like do you upload a whole bunch of documents onto the site and then it builds a model based upon that that it uses to query?

Slite's a knowledge base tool(similar to N*tion) so the idea is that all your internal documentation already lives there.

(and yes, there is an import feature for the aforementioned other tool).

Re: What if AI didn't make you a bad writer, but a better thinker?

#33

Post by nerdponx »

rcme wrote: post #17

I’ve been using AI to write with great success. Mostly business documents. My general process is this: Think of the concept I want to write about as well as the supporting evidence for the topic. Ask ChatGPT to write me something in my target format using the topic and supporting evidence as input. What I get back is essentially a well-written skeleton that I can use to fill in additional details. Finally, I pass my…

It sounds like crafting the prompt is still 99% of the work here.

Re: What if AI didn't make you a bad writer, but a better thinker?

#34

Post by twobitshifter »

This is my first time hearing about Slite knowledge base. I think this is a great idea based on search summaries. However, the access privilege bit covered in the video seems technically tricky. How do you know that chatgpt isn’t leaking out some private information in its responses, unless every user has their own private model?

Re: What if AI didn't make you a bad writer, but a better thinker?

#35

Post by sandkoan »

mistermann wrote: post #23
Whitespace wrote: post #20

Earlier quoted context omitted.

That is quite literally what the article talks about.

It seemed rather light on details to me, like do you upload a whole bunch of documents onto the site and then it builds a model based upon that that it uses to query?

No, the basic model already exists. You could throw together something like this yourself: encode your documents with a Transformers model into a series of vectors. Then you're merely a nearest neighbor search away from finding the most semantically relevant documents. Feed those documents to GPT-3 or some such LLM as contextual state, along with the query, et voila! you have Q&A on documentation.

Re: What if AI didn't make you a bad writer, but a better thinker?

#36

Post by popinman322 »

RhodesianHunter wrote: post #30
moonchrome wrote: post #21

Earlier quoted context omitted.

So you are providing sensitive business information/facts to a third party service that's likely going to use those for training, analysis, store it, etc. ? It should be fine for most places I guess - but I suspect a decent amount will have a problem with this. This is my main reservation about copilot as well (quality issues aside).

I didn't think copilot was actually sending your source code back to GitHub? It's trained on OSS.

Snippets of your local code are sent to the API as part of the Copilot request context.

Re: What if AI didn't make you a bad writer, but a better thinker?

#37

Post by now__what »

JKCalhoun wrote: post #15

The spate of AI "artwork" I have seen over the past few months has seemed to me to be good "prompts" for artists. Many of what I have seen has a germ of something interesting in it — but is often missing in other regards. An obvious example that comes to mind are the recent "Jordowsky Tron" images [1]. Any art director could comb those images, consider changes here, there — and end up with something better than the A…

I've already been using AI art to help brainstorm/conceptualize my own artworks. It's a great tool to use alongside others, but you're right that most of it is extremely derivative. It's easy to end up with something that looks hackneyed (and reminiscent of hotel art) if you're not careful. That said, I do feel it allows me to push past my previous limits of composition, because it helps me to single out what creates interest in a piece and "rapid prototype" concepts.

Re: What if AI didn't make you a bad writer, but a better thinker?

#39

Post by rom-antics »

RhodesianHunter wrote: post #30
moonchrome wrote: post #21

Earlier quoted context omitted.

So you are providing sensitive business information/facts to a third party service that's likely going to use those for training, analysis, store it, etc. ? It should be fine for most places I guess - but I suspect a decent amount will have a problem with this. This is my main reservation about copilot as well (quality issues aside).

I didn't think copilot was actually sending your source code back to GitHub? It's trained on OSS.

Copilot sends chunks of your code to the server for every suggestion (whether or not you accept it). That's the only way it could possibly work, since the model is running on a remote server.

https://thakkarparth007.github.io/copilot-explorer/posts/cop...

Re: What if AI didn't make you a bad writer, but a better thinker?

#40

Post by popinman322 »

now__what wrote: post #31
rqtwteye wrote: post #7

I look forward to most tech writing done with AI. Writing documentation and requirements requires a lot of effort to keep consistent and up to date. Having an AI look at your code and config and then write a nice report will easily beat 99% of all tech docs in companies.

I'd love for this to be the case, but often the most(/only) important part of a tech doc is the "why," i.e. the background knowledge about the business itself, or the conceptual framework that underlies the code. Even more so for writing requirements. How would AI be able to help with that? Maybe by parsing through all related meeting transcripts as well?

> Maybe by parsing through all related meeting transcripts as well?

Those and design docs. It can also reason over code somewhat; it may be possible for the model to intuit design constraints from code.

Post reply on HN