Yet another open-source project from China: Chitu! A high-performance inference framework for LLMs, designed for efficiency, flexibility, and availability. Chitu supports various mainstream models, including DeepSeek, the LLaMA series, Mixtral, and more.
CODE
-
Ten Thousand Pi Digits Visualized in MATLAB
By
–
Ten thousand digits of pi visualized in MATLAB 😮 Happy Pi Day! pic.twitter.com/cA4CVQgGcN
— MathWorks (@MathWorks) 14 mars 2025Ten thousand digits of pi visualized in MATLAB Happy Pi Day!
-
ReAct: Synergizing Reasoning and Acting in Language Models
By
–
ReAct: Synergizing Reasoning and Acting in Language Models Yao et al.: https://
arxiv.org/abs/2210.03629 #ArtificialIntelligence #ChatGPT #ReinforcementLearning -
ChatGPT Work with Apps Now Available on macOS
By
–
Work with Apps on macOS is now available to everyone, including Enterprise, Edu, and Free users. ChatGPT can read and edit content in your coding apps, bringing you smarter answers tailored to your work and helping you stay in flow. But don't forget to update the app!
-
SambaNova Launches Open-Source AI Agents Community Initiative
By
–
Bring Your Own Agents AI Style We’re all about open-source contributions! Deploy your SambaNova-powered agent, share your breakthroughs, tag us, & stay tuned for contests & prizes! Details here https://
sambanova.ai/blog/open-sour
ce-deep-research-agents
… #AIGameOn -
Deep Work: Multi-Agent AI Tasks for Pro Users
By
–
Convergence released Deep Work for Pro users. Deep Work operates with multiple AI agents to complete multi-step tasks.
— 🚨 AI News | TestingCatalog (@testingcatalog) 13 mars 2025
This is Operator and Deep Research in one 👀 https://t.co/JTqpnBSkhM pic.twitter.com/8172wbrCI5Convergence released Deep Work for Pro users. Deep Work operates with multiple AI agents to complete multi-step tasks. This is Operator and Deep Research in one https://
t.co/JTqpnBSkhM -
MIT’s Exo 2: High-Performance Programming Language Reduces Code Requirements
By
–
A new programming language from MIT could enable high-performance coding that can compete w/state-of-the-art libraries w/a few hundred lines of code, instead of tens or hundreds of thousands. Called "Exo 2," the approach enables reusable scheduling libraries external to
-
LLM Distillation: Training Efficient Models for Specialized Tasks
By
–
LLM distillation helps train SLMs that retain the reasoning power of large models, while slashing inference costs. Join us to learn: Fine-tuning vs. distillation Training SLMs for specialized tasks Reducing latency & compute costs Register: https://
snorkel.ai/webinar/improv
ing-the-accuracy-of-domain-specific-tasks-with-llm-distillation/
… -
Claude Controls Blender for 3D Scene Creation at Speed
By
–
Claude can now control and talk directly to blender, create 3D scenes at lightning speeds
— Linus ✦ Ekenstam (@LinusEkenstam) 13 mars 2025
who will build an MPC for Unreal or Unity?
pic.twitter.com/7aalSoh3XuClaude can now control and talk directly to blender, create 3D scenes at lightning speeds who will build an MPC for Unreal or Unity?
-
Official MCP Server Launch Consideration
By
–
worth adding a cheeky lil official MCP server for it ?