Moonshot AI

Latest AI news, models and releases from Moonshot AI. ['GLM 5.2', 'GLM-5.2', 'Hermes', 'K2', 'K2.6', 'K2.7', 'K3', 'K3-mini', 'K3-MoE', 'Kimi', 'Kimi 2.6', 'Kimi-2.6', 'Kimi 3', 'Kimi 3T', 'Kimi Hosted Agent', 'Kimi k1.5', 'Kimi K1.5', 'kimi-k2', 'Kimi K2', 'kimi-k2-0711-preview', 'Kimi K2.5', 'Kimi-K2.5-1T-A32B', 'Kimi K2.6', 'Kimi K2.7', 'Kimi K2.7 Code', 'Kimi K2 Thinking', 'Kimi K3', 'Kimi-K3', 'Kimi K3.5', 'Kimi K4', 'Kimi K5', 'Kimi Linear', 'Kivine', 'Krea 2', 'Krea 2 Turbo', 'Mamba', 'Mamba-2', 'Mamba-3', 'MiniCPM-RobotManip', 'MiniCPM-RobotTrack']

Agents 🇷🇺

MCP for Agent Commerce: What Could Go Wrong

Tutu and Alexander Polyakov released an MCP server for agent-based commerce, enabling AI agents to search real travel data. The article shares seven practical lessons from development, including landing page handling, context optimization (74% reduction), authorization support, and legal considerations.

Moonshot AIMoonshot AI OpenAIOpenAI Alibaba/QwenAlibaba/Qwen AnthropicAnthropic
Habr — хаб ИИ28.07 · 16:01
Research 🇺🇸

A Visual Guide to Attention Variants in Modern LLMs

This article provides a visual overview of attention mechanisms in modern large language models, covering from standard multi-head attention (MHA) to grouped-query attention (GQA), multi-head latent attention (MLA), sparse attention, and hybrid architectures. It is accompanied by an LLM architecture gallery with 45 entries and poster versions.

OpenAIOpenAI Allen Institute for AIAllen Institute for AI MetaMeta Alibaba/QwenAlibaba/Qwen Google/DeepMindGoogle/DeepMind MistralMistral Hugging FaceHugging Face CohereCohere
Sebastian Raschka28.07 · 15:05
Fresh news