Live data from Hacker News

The Grand Line

pilgrima.ge

41–48 of 48 posts

Re: The Grand Line

#41
post #15

I actually loved this, and felt moved. While reading, my mind fired rapidly through dozens of personal memes (i.e. tags for my regularly trod thought-paths) that I keep in my knowledge-base. This is the 30mb text corpus where I log all my work and peer conversations and thoughts, and (amongst other things) where I think through what I would consider my spiritual practices... my sensemaking around complex systems, inc…

Agreed, I found this essay engaging and emotional. While I can see why the unusual style might not be someone's cup of tea, I don't agree at all with the criticism that this is bad writing. It had a Haruki Murakami ethereal feel that I am quite fond of.

Regarding other comments in this thread, the moral panic over AI writing has mostly passed me by. While I certainly have a philosophical preference for things written by an actual human, I don't care to invest the bandwidth in analyzing every single thing I read for hints of llm patterns. If I like it, I'll keep reading. If not, I won't. Sometimes discontinuing a piece of writing also aligns with obvious AI use, but that is generally a secondary issue.

Re: The Grand Line

#43
I try not to be too critical of things by strangers on the internet, but I feel compelled to say that as a big fan of the type of fiction this seems to be going for - a kind of Franzen/DeLillo/Ishigoro aka mystical non momentousness - I found this really dull.

In reading, which I did before reading the comments here, I wondered too if it was LLM written or assisted. It has the hallmarks of an LLM; the "this but not this" - the proclivity to be profound. In this case as if it had been told "I want to make something meaningful out of these events, but it shouldn't mean anything."

There is not about page. No links to other socials. The entire site could be LLM generated for all we can tell.

If anything at all, this "essay" and site serve as a reminder that there is an uncanny valley to LLM writing, and that real authentic human communication will likely become rarer and more valuable as this slop proliferates.

edit: from the OP's profile it looks like this is probably a well-meaining person interested in post-structuralism and meditation, but is likely using LLM to achieve that goal. Maybe they wrote in Japanese and are translating to English? Also I kind of like coming across stuff like this on HN but I feel it should still be adjacent or at least peripheral to the topics we normally discuss

Re: The Grand Line

#44

I tried writing a short novel using Claude Opus 4.6, I gave it outline and raw draft, and the style is very similar to this writing. I tried to steer it away from this kind of writing because it feels weird. But it always try to output something similar to this. Or maybe I am just not used to reading novel. So I was curious, what kind of training data was Claude trained on, that its very hard to steer it out from thi…

I agree it's hard to get it to output things in different styles... I started doing a side project for writing with LLMs (ailivrum.com -- my main focus being doing some writing/reading for my younger daughter right now, although I'm structuring for others to use it too).

So far what I found is that doing prompt engineering does not yield great results. LLMs just go with their own style regardless and I had not much luck changing it... it can do some interesting stories though, but it's far from just outline + prompt > gen story to get something that's readable (on the good side, there are many LLMs, so testing a different provider may give better results).

Re: The Grand Line

#45
post #29

“I wish there was a way to know you're in the good old days before you've actually left them”. — Andy Bernard

We have a print on our wall that says "These are the good old days" - when I'm going through it with newborns, chaotic toddler tantrums and work stress...it's a good reminder that I will desperately wish to return to this stage of life one day in the future.

Re: The Grand Line

#46
post #15

I actually loved this, and felt moved. While reading, my mind fired rapidly through dozens of personal memes (i.e. tags for my regularly trod thought-paths) that I keep in my knowledge-base. This is the 30mb text corpus where I log all my work and peer conversations and thoughts, and (amongst other things) where I think through what I would consider my spiritual practices... my sensemaking around complex systems, inc…

Do you mind me asking what type of system do you use for keeping these notes, the 30mb text corpus with conversations and journaling? Are you using txt, an app like Logseq? I flip flop between apps for this sort of thing and then annoyingly the building of a "system" sucks up my time rather than writing and logging and reflecting. It's a struggle for me any advice would be much appreciated :)

Thanks for asking! I have become an infinitely better human and friend since starting.

I used Roam, but would like to migrate to Logseq for reasons of privacy and self-sovereignty :)

My most helpful meta tags are:

[[People I Meet]] for quick descriptions of everyone I meet, even if they don't get their own page

[[versus]] for dualities I notice and want to track, like [[expansion vs collapse]] [[away vs toward]] [[linear vs cloud narrative]] etc

[["as" metaphors]] metaphors that return a lot, like [[religion as seed]] or [[god as hologram]] or [[empathy as gravity]] etc

[[reminds me of]] which I sometimes use to make connection, but often just crossed

[[self comment]] for tracking my comments around the internet

[[new tag]] for tracking when a significant new tag occurs to me for first time

[[methinks]] (for my inline thoughts on articles whose content I paste into a page, which I do for most things I read, so I can always find the content that shapes me, and my own thoughts/highlights in relation to that)

[[toread]] [[towatch]] for books and films/video

[[tears]] [[fears]] [[fave snacks]] [[star sign]] [[faves]] and a "family" bullet for things that are important in their family life.

And every day, my optional top-level bullets are: todos, finds, logs, thoughts (pretty much everything fits under these, and most under "logs", because I like to track context of where I was, who I was with)

I started just using logs every day to keep track of things I did, because during pandemic I felt like I was doing nothing at all every day except being depressed. Everything grew from that :)

Re: The Grand Line

#47
post #41
post #15

I actually loved this, and felt moved. While reading, my mind fired rapidly through dozens of personal memes (i.e. tags for my regularly trod thought-paths) that I keep in my knowledge-base. This is the 30mb text corpus where I log all my work and peer conversations and thoughts, and (amongst other things) where I think through what I would consider my spiritual practices... my sensemaking around complex systems, inc…

Agreed, I found this essay engaging and emotional. While I can see why the unusual style might not be someone's cup of tea, I don't agree at all with the criticism that this is bad writing. It had a Haruki Murakami ethereal feel that I am quite fond of. Regarding other comments in this thread, the moral panic over AI writing has mostly passed me by. While I certainly have a philosophical preference for things written…

Thanks! Added Haruki Murakami to my #toread list! :)

Re: The Grand Line

#48

I tried writing a short novel using Claude Opus 4.6, I gave it outline and raw draft, and the style is very similar to this writing. I tried to steer it away from this kind of writing because it feels weird. But it always try to output something similar to this. Or maybe I am just not used to reading novel. So I was curious, what kind of training data was Claude trained on, that its very hard to steer it out from thi…

Don't take this as a defense of LLMs, because it absolutely isn't, but: >Or maybe I am just not used to reading novel. If you're not even used to reading novels, how can you judge the results of writing one? That is one hell of a confession for someone who's trying to write fiction.

Thanks for sharing your perspective.

The quote you referenced is about “the weird” feelings. Maybe its weird because I didn’t read too many novels. So its totally something personal to me. Not that weird for me = bad writing.

However, I do read a lot of LLM generated output. I spent weeks tinkering with LLM while I was asking it to ghostwrite my novels. So I was exposed to a lot of text that has this weird feelings. Which I eventually felt when I read this article.

Its like hearing a song that has the same chords so many times, and then you listen to another song that had the same chords, you might be able to know that they are kinda the same, even when you don’t listen to a lot of songs.

Post reply on HN