🧵(2/2)
#AI models are currently a pure extract of human symbolic worlds, and it will be interesting if they ever manage to leave them - into the non-symbolic layer.

/image by symbolic model Imagen 4

🚀 #What is the main #skill you will need if you want to implement a #multimodal LLM? It is definitely not #prompt engineering... 🧵(1/6)

🤖For several months now, we have been #developing a robust #prompt at Carl Data Company that, thanks to its connection to #Gemini, can analyze more than 40 categories for each #video or #photo.

🧾Current status: More than 30 pages of production prompt

#ai #llm #multimodal #python
#image by #imagen3

🧩 #weekend #puzzle
😱 #strangerthings

🤖🐍Approximately 8 thousand lines of code for analyzing #videos and #photos built around #Gemini. This year, Carl Data Company managed to get a comprehensive #AI system for analyzing #content on social networks into production. 🔌

Church of Saint James
Kutná Hora, Czechia
#
#kutnahora #czechia #church #travel #city

📢 #AI video analysis is in the Carl app! Our model observes almost 40 different perspectives of each analysed #video. Currently we use advanced analysis for both - image and video. Stay tuned!
🌐 carlforsocial.com

#google #gemini #socialnetwork #business
/image by #dalle

📢 #AI image description is in production! Our model observes more than 30 different perspectives of each analysed #photography. Users can see the first part of the implementation in the Carl app. Stay tuned!
🌐 carlforsocial.com

#carl #app #gemini #image
/image by #dalle