Re:Coarse Is Better
by speedgoose on Sunday December 21, 2025 @02:02PM
(#46347269)
Thanks ChatGPT. I’m wondering about the motivation to spam HN with LLM generated comments. Not the worst comments though.
I don't think that comment is LLM generated. I would've certainly written it like that myself.
> It's not X - it's Y, it's Z.
> Consider: consideration. That's what you should consider.
Come on man
The second point I agree with, but I hate that the "It's not ... it's ..." construct is a sign of LLMs now, because I use it all the time
Re:Coarse Is Better
by speedgoose on Monday December 22, 2025 @12:59AM
(#46351758)
Check the account comments history. A lot of good comments of a similar length posted very closely in time. I don’t think a human can write that well, so quickly, on so many topics.
This isn't worse - it's different. MJv2 was a happy accident machine. NBP is a precision tool.
If you want the coarse aesthetic, prompt for it: "rough brushstrokes, visible canvas texture, unfinished edges, painterly, loose composition". NBP will give you exactly that because it actually understands what you're asking for.
The real lesson: we're in a transition period where prompting strategies that exploited old model quirks no longer work. That's fine - we just need to adapt our prompting to match what the model was designed to do.