Cool project, but I hate how every new site has this obviously LLM generated copy :(
I feel like most people who use it for their copy don’t realize how obvious it is.
At this point we should be sharing prompts not code for solutions like OpenLogi. Reverse engineering many things can typically be one-shotted (ignoring things like.. capturing a pcap or whatever to aid the effort). Let others add their own taste to the solution.
Isn't it wasteful to have everyone go off and remake the same software with slightly different bugs in it instead of one that fixes almost all of the bugs
Please no, I couldn’t care about your prompts, there is nothing special about them. Anyone can look at the generated artifact and reverse engineer their own prompt in no time
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
If it matters is subjective. But personally I stop reading when I notice it’s AI text because there is never anything in it worth reading. It’s just a prompt expanded in to paragraphs of filler text.
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'd rather read some well written LLM text over some poorly written human effort
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.
Your LLM text is obviously not well written if we spot it after 2 seconds. I won’t read it, doesn’t matter how beautiful it is, it’s just pure cringe, I notice, roll my eyes, close the tab. Please give me the poorly written human effort. Is it really that hard to spend 10minutes reading what you produced to see if that feels genuine?
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?
It's not that hard if you put in the effort and practice.
But if you don't want to and still want to use an LLM, there are low-bar choices you can make (using a technical writing skill, using ASD-STE100 Simplified Technical English, choosing your audience, proofreading at the end with human eyes to make sure it makes sense and doesn't repeat itself uselessly).
I think it shows either a) low respect or consideration for your audience or yourself, or b) laziness.
Trust yourself to write even if it's bad. At least it's human.
I assure you it won't be as bad as this (answer to FAQ: "Will OpenLogi support Logitech Flow?")
> It's on the roadmap, at the far end: a cross-computer pointer and clipboard bridge is a very large feature. The half that lives in the protocol already ships. OpenLogi drives Easy-Switch host switching over HID++ (0x1814/0x1815), and paired mice follow the keyboard when it switches hosts. If the rest lands, it will be opt-in and local-network only.
A great example of why Claude's writing is terrible is the sentence "The half that lives in the protocol already ships". I cannot imagine any human writing this.
I don't really care about the site but it's an indication that the software might include a trojan or serious flaw. I'm not downloading code with deep system access and risk losing my data/money.
