this post was submitted on 02 Jul 2024
57 points (100.0% liked)
Technology
37740 readers
482 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
It's generative AI, not magic. Repeating the patterns it was trained on is what it was designed to do, even if those patterns aren't always entirely obvious.
I think the model has been overfitted on its training set, but you can't expect the types of generative AI we have today to be creative.
I'm guessing it should've been trained on more pattens, and increase that temperature a bit.
To be somewhat creative, it should have a large training set, and an iterative approach to the output. From the looks of it, this one is just a single step LLM, picking design elements one by one.