Hacker News: thelucent

New comment by thelucent in "ChatGPT Images 2.0"

thelucent — Tue, 21 Apr 2026 20:46:03 +0000

It seems to still have this gpt image color that you can just feel. The slight sepia and softness.

New comment by thelucent in "The Grand Line"

thelucent — Sun, 12 Apr 2026 21:06:57 +0000

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.

New comment by thelucent in "The Grand Line"

thelucent — Sun, 12 Apr 2026 05:33:30 +0000

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 this style.

So I opened my kindle and looking through the recommended popular novels. Just reading through its free samples.

And the similarities are striking. Now, I dont know whether the recommended novel is the training data, or its actually written by LLM. Or maybe its just how novelist writes.

I even tried writing full chapter from scratch. And asked Claude to ghost write the second chapter for me using my writing style. It still wont follow my style and keeps writing in this kind of style from the article.

Not accusing the article of using an LLM to ghost write. Even so its fine to use LLM to ghost write. Its just one anecdote from my side, on how LLM fails to follow my writing style and keeps coming back to its training data.

New comment by thelucent in "Spotify is full of AI music"

thelucent — Sat, 28 Dec 2024 01:57:59 +0000

I used to write music in the past, and I mostly do it to tell stories or a songification of a poem. When I lived alone, it was easy because I can record anytime I wanted in full silence. Now that I am with family, I can’t record without a background noise seeping on my vocals.

I found that AI helped a lot, I can still write the story, the poem, the lyrics - and just let AI find a melody that represent the story as close as how I imagined it on my mind.

I mostly design and write the story first, then captures the story as poem or lyrics, then let AI “cover” it for me. I don’t want AI to write for me because the story and lyrics is what I cared about, and I like to put metaphors and hidden messages on it.

For example, this album that tells about the phases of life as seasons is AI generated.

https://youtu.be/RlCY67Nbubk?si=2HQEyH5MiAnGeW4r