More spatial dimension puzzles for GPT4 Vision. Yes there are 9 cubes and yes you can only see 6. This is wild.
MULTIMODAL AI
-

Google Transforms Image Search with Generative AI Capabilities
By
–
Google Strikes Back.
— Linus β¦ Ekenstam (@LinusEkenstam) 14 octobre 2023
Google Image search just became Google Image Generator
π€― https://t.co/tnd23157eNGoogle Strikes Back. Google Image search just became Google Image Generator
-

Use Vision AI Models to Understand Mathematical Equations Easily
By
–
If you're like me and find it easier to read *code* than *math*, and you have access to @OpenAI GPT 4V (or use @bing or @google Bard), try pasting a image of an equation you wanna understand in there. It might just blow your mind.
1/ -

GPT-4 Vision Explains Exam Results in Meta Application
By
–
This is so wild. Using GPT4 Vision to explain GPT exam results. Super meta.
-

GPT4 Underestimates GTA5 Cover Art Recognition
By
–
GPT4 is selling it self short here, this is indeed GTA5 cover art.
-

GPT-4 Painting Dating Error Highlights AI Limitations
By
–
Yup, GPT4 nailed it, except it got the year wrong by 2 years, this painting is painted in 1853… Let's confront it.
-

Exploring GPT-4 Vision Capabilities and Applications
By
–
Let's see what more we can get out of GPT4 with Vision…
-

GPT-4 Vision Accurately Identifies Historical Painting Subject
By
–
Then GPT4 with vision get's on to nail the painting. "The painting depicts a historical event involving Queen Christina of Sweden and Gian Rinaldo Monaldeschi." This is absolutely correct
-

GPT-4 Vision as Perfect Art Historian Exploration
By
–
GPT4 with Vision is the "perfect" Art Historian. Let's explore whats possible today… here is some art. A thread
-

Multi-modal LLMs Integration with Leading AI Frameworks
By
–
Multi-modal #LLMs with: @UnstructuredIO @Nomic_ai @TryChroma and ofc @langchain
!
