The author's prompts are fighting against what Nano Banana was optimized for. Saying "British Museum" to MJv2 worked because it blurred all images tagged with museums into the aesthetic. NBP interprets it literally: show me something IN a museum.
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.
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.
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.
> It's not X - it's Y, it's Z.
> Consider: consideration. That's what you should consider.
Come on man
Have to agree that is sounds GPT-generated. Why so many colons? And the incurable marketing-speak.