Image created with OpenAI GPT-Image-1. Image prompt: Cheesy late-night infomercial freeze-frame—living-room rug with plush camelid mascot “LLAMA LANGUAGE-LOOM™”; cozy tungsten, scan scratches, high-resolution
Introducing “”Building with Llama 4.”” This short course is created with @Meta @AIatMeta, and taught by @asangani7, Director of Partner Engineering for Meta’s AI team. Meta’s new Llama 4 has added three new models and introduced the Mixture-of-Experts (MoE) architecture to its https://x.com/AndrewYNg/status/1935350552692658202
🧠 New in LlamaIndex: Custom Multi-Turn Memory for Agents We’ve just added a new example that shows how to build your own multi-turn memory implementation in LlamaIndex — perfect for agentic workflows that need control, transparency, and customization. Why it matters: 💬 Most https://x.com/llama_index/status/1932173369858003304
Outlines v1.0 is out!”” / X https://x.com/ollama/status/1935712844701442245
6/ LlamaFS is a self-organizing file manager. It automatically renames and organizes your files based on their content and well-known conventions (e.g., time). It supports many file types , including images and audio. Super cool project by @AlexReibman! https://x.com/AtomSilverman/status/1932988830904365480
stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 > has support for multiple VLMs: Gemma 3, Qwen2.5VL, Llama4 > recommend us new models or inputs, we’ll add 🫡 https://x.com/mervenoyann/status/1935708014645784713
The response to our first-ever Llama Startup Program was astounding, and after reviewing over 1,000 applications we’re thrilled to announce our first group. This eclectic group of early-stage startups are ready to push the boundaries of what’s possible with Llama and drive https://x.com/AIatMeta/status/1935004555210846271
Upgraded from Llama 3 to Qwen3 as my go-to model for research experiments, so I implemented qwen3 from scratch: https://x.com/rasbt/status/1936041873099063333
2/ @llama_index provides a data framework for LLM applications, facilitating efficient data indexing and retrieval. It is the simplest framework for connecting custom data sources to large language models. https://x.com/AtomSilverman/status/1932988797115117740
