Re:Built an AI that brutally roasts your website designs
by davidthewatson on Saturday June 14, 2025 @08:21AM
(#44275967)
This is a good idea. It reminds me of the need for better visual debugging or visualization of the masked complexity in these products. I'm sure they exist inside tech titans, but I haven't seen them outside terrain visualization in open source.
Thanks for the highlight. I wasn't aware that Apple had released a new AR interface though I have used the previous VisionPro generation.
FWIW, I find the whole experience disconcerting from a design perspective.
Why?
1) We have been stuck at a Cartesian lossy limit of blocks world keyhole problems for 50 years on desktop and poor imitations of it found in tap interfaces.
2) That edge remains liminal and uncanny, precisely because it is lossy in terms of dimensions and their implied dimensionality and lack of scalability, ignorance of zoomable interface research and so on, from pixels at 2d to voxels at 3d, to 4-tuples (XYZT) in 4D and beyond.
3) Just like LLMs, the exploding dot cloud, or vector spaces of n-dimensional data found in our reality from inner space to outer space haven't really received the quantum-leaning, mirror world treatment they deserve - one which scales with the exploding complexity of its underlying dot cloud of vector spaces in all dimensions.
We are in need of a topos theoretic leap in UX/UI for decades - one which can incorporate the need for disconnected spaces that provide a localized logic to bridge the lack of unification from one uncanny valley to another. Sadly, what I've seen from the dichotomy of dominance in tech titans has not provided a compelling answer, at least not in public. I remain hopeful that R&D labs are still breathing in these sadly corporate places and simply are far more secretive since Steve.
Problem is, outside tiny pizza-team-sized labs, the number of R&D labs realizing the problem of synthesizing hybrids at 2.5d or the like is infinitesimally small.
Re:Built an AI that brutally roasts your website designs
by jayantrao94 on Saturday June 14, 2025 @07:12AM
(#44275644)
I’m a design agency founder + a recent indie builder, and I recently launched a tool that uses AI to roast website designs. Brutally. Trust me when I say it's brutal.
It’s called UGH.design (gotta roll the eyes when u see crappy designs), this AI gives your site a score (the higher the UGH, the worse you did) and flags your worst design crimes, like “Font Size Felony” or “Contrast Denial.”
Right now you can:
- Upload up to 5 screenshots
- Choose your roast level (Honest, Brutal, Undigestable)
- Get a roast with scoring + violations
- See it on the public gallery
I’d love feedback from from everyone here:
- The concept itself (too weird? too fun?)
- How to improve the roast logic or interface
- looks and feels like a Chatgpt wrapper
Maybe you need to get roasted? :)
No one who has "built an AI" and posted it here on HN has actually trained a LLM. They're all wrappers for some service.
This one is at least funny.
Waiting for someone to have it evaluate Apple's new "AR" interface.
Thanks for the highlight. I wasn't aware that Apple had released a new AR interface though I have used the previous VisionPro generation.
FWIW, I find the whole experience disconcerting from a design perspective.
Why?
1) We have been stuck at a Cartesian lossy limit of blocks world keyhole problems for 50 years on desktop and poor imitations of it found in tap interfaces.
2) That edge remains liminal and uncanny, precisely because it is lossy in terms of dimensions and their implied dimensionality and lack of scalability, ignorance of zoomable interface research and so on, from pixels at 2d to voxels at 3d, to 4-tuples (XYZT) in 4D and beyond.
3) Just like LLMs, the exploding dot cloud, or vector spaces of n-dimensional data found in our reality from inner space to outer space haven't really received the quantum-leaning, mirror world treatment they deserve - one which scales with the exploding complexity of its underlying dot cloud of vector spaces in all dimensions.
We are in need of a topos theoretic leap in UX/UI for decades - one which can incorporate the need for disconnected spaces that provide a localized logic to bridge the lack of unification from one uncanny valley to another. Sadly, what I've seen from the dichotomy of dominance in tech titans has not provided a compelling answer, at least not in public. I remain hopeful that R&D labs are still breathing in these sadly corporate places and simply are far more secretive since Steve.
Problem is, outside tiny pizza-team-sized labs, the number of R&D labs realizing the problem of synthesizing hybrids at 2.5d or the like is infinitesimally small.
I mean the stupid translucent iphone UI they threatened us with...
Firefox and safari, iPhone.
Useless website. 0/10.
It’s called UGH.design (gotta roll the eyes when u see crappy designs), this AI gives your site a score (the higher the UGH, the worse you did) and flags your worst design crimes, like “Font Size Felony” or “Contrast Denial.”
Right now you can:
- Upload up to 5 screenshots - Choose your roast level (Honest, Brutal, Undigestable) - Get a roast with scoring + violations - See it on the public gallery
I’d love feedback from from everyone here:
- The concept itself (too weird? too fun?) - How to improve the roast logic or interface
Was this vibe-coded?
Your comment seems to be.. just putting someone down..