Home · Technology · Sep 4 archive
The sameness problem behind those unappetizing AI-generated menus
Developing
In Short: Researchers at the University of Duisburg-Essen in Germany found that AI-generated food images exhibited an “uncanny valley” effect, where images of food that looked almost real elicited more disgust and unease than
Researchers at the University of Duisburg-Essen in Germany found that AI-generated food images exhibited an “uncanny valley” effect, where images of food that looked almost real elicited more disgust and unease than images that were obviously fake.
On X, a user named Labtec showed what happens when you make a menu in ChatGPT, then edit it 100 times to see how the food continues to look less and less like it should. (We replicated the experiment and found similar results.) “The end result actually makes me uncomfortable,” Labtec wrote.
“People have an almost unexplainable sense about when they’re looking at something that’s AI-generated, compared with something that was real in the first place,” Rainie said.
“The optimization of the data sets is for pleasingness, or you know, not being offensive, and so there’s a way that turns into homogenization,” Lee Rainie, Director of the Imagining the Digital Future Center at Elon University, told TechCrunch.
“Model collapse is almost like a mad cow disease… when you feed the outputs from one model back into itself, eventually the inbreeding becomes too much, and the whole thing collapses,” Alex Lisle explained.
“A lot of this stuff looks like a Chili’s menu from 2015, and there’s a reason for that,” Alex Lisle said.
What's confirmed
What's still developing
- Single-source account; further confirmation still arriving.
Sources
- TechCrunchlink