tech
December 19, 2025
Meta is developing a new image and video model for a 2026 release, report says
The company is working on an image and video model and new text-based model, which aids with coding.

TL;DR
- Meta's superintelligence lab is developing new AI models, codenamed "Mango" (image/video) and "Avocado" (text-based).
- The new models are planned for release in the first half of 2026.
- The text-based model aims to improve coding capabilities and explore world models for reasoning and action.
- Meta is striving to keep pace with AI leaders like OpenAI, Anthropic, and Google.
- The company's AI division has undergone restructurings, including leadership changes and researcher recruitment.
- Meta currently lacks a distinct, leading AI product, relying on its social network user base for its AI assistant's reach.
Continue reading
the original article