I'm really impressed with how the model is able to reduce the concept of the original image to something so minimal
@fofrai
-
Evaluating AI capabilities in complex multi-user interaction scenarios
By
–
Very impressive. I wonder if this passes the test of successfully interacting with two shouting kids that are each asking it different things and interrupting each other. https://t.co/ruaRJZ2gWI
— fofr (@fofrAI) 12 mai 2026Very impressive. I wonder if this passes the test of successfully interacting with two shouting kids that are each asking it different things and interrupting each other.
-
Exploring linear algebra and axolotls via Google AI Studio
By
–
Morning @GoogleAIStudio explorations with @fofrAI about the unexpected connections between linear algebra and axolotls have uncovered the following gems of a @MATLAB algorithm and @Nature paper:
-
Nano Banana Pro recreates image with JSON prompt
By
–
I had Nano Banana Pro recreate this kind of image with a JSON prompt:
-
Using Image Search as Creative Muse in Nano Banana 2
By
–
If you're just looking to explore, you can enable image search in Nano Banana 2 and prompt for something like: > Use image search to get [some theme and medium], they should act like a muse for context. With that context, make an original new [thing]. A single cohesive piece,
-
Freepik Acquires Magnific AI Image Generation Platform
By
–
Freepik acquired Magnific, both based in Spain
-
AI-Generated Images Detection and Transparency in Social Media
By
–
No mention of that image being AI in the comments.
-
AI Image Detection: Identifying Generated Content vs Real Photos
By
–
The left image is AI, it's Images v2. The noise pattern is unmistakeable. Probably prompted with "make a zoomed out version of this". The right image is real, it's a crop. I've added the original uncropped Reuters one from 2016.
-
Images v2 Model Creates Subtle Pareidolia from User Images
By
–
You can give images v2 an image and ask it to make a subtle pareidolia from it, and it kinda works
