Does it matter? People get caught up on LLM this and sure, a professional beats an LLM currently but I'd rather read some well written LLM text over some poorly written human effort
This kind of tool doesn’t need a whole Apple style marketing page to sell you on it.
It also signals effort to me, when I see vibeslop text I know the project most likely is a one shot weekend project full of issues which won’t be resolved. I’ve seen good examples of AI use in open source, and those projects write the readme and website copy without AI.
I think it depends a bit what's meant by "poorly" but I don't think I share that preference at all.
I would 100% rather read a developers copy explaining why they wanted to build something and what they think is useful about it, even if it isn't particularly polished.
As a comparison, LLM generated "marketing schlock" is polished, but it's normally pretty empty and doesn't convey much of it's value.
As an example, I use lazygit (a TUI git interface) - at least at the time I looked at it, the main intro was a youtube video of the developer talking through the features. It wasn't polished at all, but it did a great job of convincing me that lazygit was a project with a lot of love and thought put into it.
I could not disagree more.
I read plenty of not-obviously-AI-generated text and I much prefer doing that, even if it’s not from a professional.
It’s not about the quality of the text itself. If Claude was one person with a human level of output, Claude would probably be considered decent at writing.
But when I have to read the same genre of slop on 1 million different sites it gets really really annoying imo.
If you didn't even spend a minute writing a couple sentences about your own project, how much effort did you put into actually building and testing it? Or are you just letting others do the hard parts: Review and verification that your vibe-slop actually works as claimed, and then feed their feedback back into an LLM?