GLM-5
🔥 This release made it to our blog
Z.ai Launches GLM-5.2: A 753B Open-Source MoE with a True 1M Context Window
Z.ai has open-sourced GLM-5.2, a flagship 753B parameter MoE model boasting a 1M-token context window, variable thinking-effort levels, and an MIT license.
### TL;DR
GLM-5 is Z.AI's latest flagship foundation model, designed for complex system engineering and long-range agentic tasks. It features a parameter scale of 744 billion, an expanded pre-training dataset of 28.5 trillion tokens, and integrates DeepSeek Sparse Attention for efficient long-context processing.
Key Insights & Metrics
Key Features
- 744 billion parameters
- 28.5 trillion tokens pre-training data
- DeepSeek Sparse Attention for efficient long-context processing
→ Related Releases
AIBuildAI
AIBuildAI is an AI agent that autonomously constructs AI models. Given a specific task, it initiates an agent loop to analyze the problem, design models, and execute training processes, all without human intervention.
MiroThinker
MiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.
Letta Code SDK
The Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.
OB-1
OB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.
Discussion
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!