I'll echo the rest, once you've seen a dozen of AI-generated geospatial dashboards, the style is easily recognizable. Starting to wonder if there's some negative feedback loop which makes the LLMs converge toward one distinct style.
I've worked in this space for a decade now, and the tools we use (unavailable to the public) rarely look like the ones which LLMs have generated for the past year or two.
Also, not saying that there's not any value in these, but every single of these dashboards I've seen suffer from the same thing: Information overload.
For whatever reason, the models just absolutely deluge the app with all sorts of features and information.
I think you point out something really important: there real value isn't the data, it's in surfacing the useful data.
For amateur astronomers, an interesting question is whether there is a satellite above me that I can see tonight (and when / where)? For professionals, the literal million dollar questions are more like: are there any satellites on a collision course? Which satellites have moved recently and why? Is there a dime-sized piece of metal somewhere out there that could hit my (employer's) satellite?
The thing most people seem to be missing is that ai does the work, but still needs to be guided. When it comes to design, at our little company, our main job is to direct the style and not tell it to make something. So we are actively directing it towards specific, by us determined, styles. We did this for numerous companies [1]. So yes, Ai generated dashboards can look really amazing, but the person directing them has to spend time creative directing it.
I don't really care that they all look alike as long as the sites usable to me for its intended purposes. Honestly, having each site have its own brand is annoying to me.
For years of dealing with badly designed sites, I wished then that they _copy_ a better design even if it looked generic. Even copying a simple but usable design would have made many sites easier to use.
I don't want the site to win an art contest, I want the information to make a decision. At a min just be easy in the eyes and intuitive to use and get the info.
Man AI has really latched on to this one style of design and it’s really starting to be an immediate nope out for me. It sucks too because I made a product that looks sort of like that in the pre AI era!
It’s because all sites are made by the same “person” now.
If you get past the anthropomorphism, it’s basically that Claude is just a set of knowledge, including opinions (things they’d more likely do than other things) and everyone is getting the same person to make their sites which is why they all look the same.
Also the same reason everything ends up with the same tech stack (if you don’t steer it specifically) which probably contributes to why GitHub is overwhelmed.
So it's your fault then? Had you not published the site, the AI would not have trained on it. Your one site ruined it for everyone!!! Hope you're proud of yourself /s
Seems to have taken several open-source pieces of data (live satellite feeds, NASA UAP files) and combined them into a vaguely conspiracy-ish website. It's really odd, but has the feel of old-timey conspiracy websites spruced up with vibe coding.
I expect that building the satellite viewer is now just a few dollars worth of tokens. I built something like this a few years ago, and it took a week of work. It's cool that the marginal cost of satisfying your curiousity about where things are in space has dropped so close to zero, but don't be fooled into thinking this website lets you in on some vast conspiracy.
Nice site. Funny how some are zipping around just as fruit flies and other extremely small insects do. I'm still patiently waiting for someone to upload 4K videos of UAPs that are in-focus. We're in 2026 and still are squinting at white pixel blobs in gray skies or gray pixel blobs in black skies. Example: https://www.dvidshub.net/video/1017793/dow-uap-pr117-unresol...
Where's your footage of tracking something at high speed under high magnification? Most people can't track a rocket launch moving in a fairly straight line. Even if you're using your device, the auto stabilizing software features make it very difficult to track something smoothly by hand. Ever notice the lag when zoomed in? 4K resolution might be ubiquitous on consumer devices, but it's not in military gun cameras.
yeah, and it sucks. Again, that's something moving in a straight line and still unable to be tracked. Hand held tracking at magnification is damn near impossible to keep steady and the subject in frame. Sure, there's a couple of frames that you can see the plane clearly, but come on. That's your example of something good??
My favourite thing about UAPs is the alleged crashes into Earth. So the aliens managed to solve interstellar travel only to make it here and have their parking sensors fail.
There have been so many catastrophic accidents along human history despite all its advancements, I don't find this particularly implausible. Also across sci-fi, the stranded in space or on a distant world is a common trope without your criticism broadly applied either.
Site is partially broken in Chrome, tons of errors like this:
Loading the script 'https://static.cloudflareinsights.com/beacon.min.js/v4513226cdae34746b4dedf0b4dfa099e1781791509496' violates the following Content Security Policy directive: "script-src 'self' 'unsafe-inline' https://www.googletagmanager.com". Note that 'script-src-elem' was not explicitly set, so 'script-src' is used as a fallback. The action has been blocked.
Not sure if this is related to images not loading, but tell your clanker it fucked up and needs to do better next time ;)
once you grasp even a problem as "simple" as cosmic-rays and you still believe living creatures so advanced to overcome all that are bothering with Earth
well then I don't know how to deal with that level of stupid
automated drones a remote MAYBE (still the problem of lightspeed)
but if you believe in aliens visiting you should stick to "flat earth" or any religion
how about instead we turn all this enthusiasm into forcing our government to properly fund the Habitable Worlds Observatory Space Telescope (which DOGE now destroyed any hope of happening)
your AI lied to you, you were not absolutely right, you were not clever, your epiphany was not a rare.
The LLM was misaligned with all human interests by egging you on about having a dozen sections on your landing page
Maybe the next cycle of LLMs will be more aligned, but in the meantime you still need to learn UX principles before prompting the coding tool, if you want to convey a message to other humans
I've worked in this space for a decade now, and the tools we use (unavailable to the public) rarely look like the ones which LLMs have generated for the past year or two.
Also, not saying that there's not any value in these, but every single of these dashboards I've seen suffer from the same thing: Information overload.
For whatever reason, the models just absolutely deluge the app with all sorts of features and information.
For amateur astronomers, an interesting question is whether there is a satellite above me that I can see tonight (and when / where)? For professionals, the literal million dollar questions are more like: are there any satellites on a collision course? Which satellites have moved recently and why? Is there a dime-sized piece of metal somewhere out there that could hit my (employer's) satellite?
[1] https://designshippers.com
I don't really care that they all look alike as long as the sites usable to me for its intended purposes. Honestly, having each site have its own brand is annoying to me.
For years of dealing with badly designed sites, I wished then that they _copy_ a better design even if it looked generic. Even copying a simple but usable design would have made many sites easier to use.
I don't want the site to win an art contest, I want the information to make a decision. At a min just be easy in the eyes and intuitive to use and get the info.
If you get past the anthropomorphism, it’s basically that Claude is just a set of knowledge, including opinions (things they’d more likely do than other things) and everyone is getting the same person to make their sites which is why they all look the same.
Also the same reason everything ends up with the same tech stack (if you don’t steer it specifically) which probably contributes to why GitHub is overwhelmed.
I also get the idea that AI writing itself is actually pretty good when looked at in isolation. Try showing it to someone who isn't used to it yet!
It's just that it's a small number of actual "people", and they're ghost writing for millions of folks, from kids to professors.
And because the style is the same, you can't tell which is which from style alone anymore.
I expect that building the satellite viewer is now just a few dollars worth of tokens. I built something like this a few years ago, and it took a week of work. It's cool that the marginal cost of satisfying your curiousity about where things are in space has dropped so close to zero, but don't be fooled into thinking this website lets you in on some vast conspiracy.
I’m glad we came to the same conclusion, you just expressed it better ;)
https://www.youtube.com/shorts/h9M400MtfNs
I assume there's no alternative way to view it?
once you grasp even a problem as "simple" as cosmic-rays and you still believe living creatures so advanced to overcome all that are bothering with Earth
well then I don't know how to deal with that level of stupid
automated drones a remote MAYBE (still the problem of lightspeed)
but if you believe in aliens visiting you should stick to "flat earth" or any religion
how about instead we turn all this enthusiasm into forcing our government to properly fund the Habitable Worlds Observatory Space Telescope (which DOGE now destroyed any hope of happening)
your AI lied to you, you were not absolutely right, you were not clever, your epiphany was not a rare.
The LLM was misaligned with all human interests by egging you on about having a dozen sections on your landing page
Maybe the next cycle of LLMs will be more aligned, but in the meantime you still need to learn UX principles before prompting the coding tool, if you want to convey a message to other humans