Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches

Computer scientist Yann LeCun says we will have AI architectures in 2032 that could reach human intelligence.

Yesterday we released the first public beta of plugovr.ai. #plugovr easily interacts with all your applications. Use #anthropic haiku model where ever you need it or try llama 3.2 as local model. Let us know what features you would like to get next.

It’s insane how good kosmos 2.5 is on screenshots. I wish someone would provide a #rust or #candle implementation. github.com/microsoft/unil…

We released PlugOvr.ai now also for macOS. PlugOvr.ai can now be used on all major OSes (Windows, Linux and macOS). For macOS you get the full Metal speedup if you use Llama 3.2 1B or 3B as local LLM.

Meet Tülu 3 -- a set of state-of-the-art instruct models with fully open data, eval code, and training algorithms. We invented new methods for fine-tuning language models with RL and built upon best practices in the community to scale synthetic instruction and preference data.

OpenAI’s biggest competitor just gave AI the ability to control computers We gave 250+ hackers 24 hours to see what it’s capable of Here’s what we saw at the Nexgen Computer Use Agents Hackathon w/ Anthropic + AgentOps 🖇️ Notable Capital at AGI House SF (🧵):

Thanks to ollama and #ollama-rs it was super easy to integrate #ollama in #plugovr. With the newest release v0.1.65 you can use all ollama models inside plugovr.ai.

Meet OLMo 2, the best fully open language model to date, including a family of 7B and 13B models trained up to 5T tokens. OLMo 2 outperforms other fully open models and competes with open-weight models like Llama 3.1 8B — As always, we released our data, code, recipes and more 🎁

🚀 A sneak peek at a new feature coming soon to PlugOvr.ai: leveraging #Anthropic's #computer_use capabilities for screen understanding to automate form filling. 👉 What features would you love to see next? Drop your suggestions in the comments—we’re all ears! 👇

ollama run llama3.3 🤯🤯🤯 llama 3.3 70B has similar performance as the 405B model ollama.com/library/llama3…

We just released PlugOvr to the open source community. github.com/PlugOvr-ai/Plu… PlugOvr is an AI Assistant that lets you directly interact with your favorite applications. You can define templates for your own use cases and select individual LLMs per template.

Eine neue KI-Generation soll den Sprung von der Sprache zur Handlung schaffen. Microsoft zeigt mit einem ersten "Large Action Model", wie KI-Systeme Windows-Programme selbstständig bedienen können. the-decoder.de/microsoft-zeig…

New LLMs that control UIs! ByteDance Research releases UI-TARS, fine-tuned GUI agent that integrates reasoning, and action capabilities into a single vision-language model. Think of computer use but open. 👀 TL;DR; 3️⃣ Available in 3 sizes: 2B, 7B, and 72B parameters 🧠

pack it up boys, it's over

Fuck it, today we're open-sourcing the codebase used to train SmolVLM from scratch on 256 H100s🔥 Inspired by our team's effort to open-source DeepSeek's R1 training, we are releasing the training and evaluation code on top of the weights 🫡 Now you can train any of our

Microsoft just released an impressive tool OmniParser V2 can turn any LLM into an agent capable of using a computer 🔥 You can enable GPT-4o, DeepSeek R1, Sonnet 3.5, Qwen... to understand what's on your screen and take actions. 100% free & open source

Today we’re releasing a prototype of Genesys, an autonomous multi-agent LLM discovery system that aims to discover new types of language model architectures. We found Genesys can discover novel architectures competitive with the industry-standard transformer. 🧵

It’s easy to fine-tune small models w/ RL to outperform foundation models on vertical tasks. We’re open sourcing Osmosis-Apply-1.7B: a small model that merges code (similar to Cursor’s instant apply) better than foundation models. Links to download and try out the model below!

1/7 We're launching Tongyi DeepResearch, the first fully open-source Web Agent to achieve performance on par with OpenAI's Deep Research with only 30B (Activated 3B) parameters! Tongyi DeepResearch agent demonstrates state-of-the-art results, scoring 32.9 on Humanity's Last Exam,