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']

Official site ↗

Applications 🇷🇺

Contract-First as Protection Against LLM Agents: API-First Returns to Keep Frontend and Backend Aligned

The author describes the problem of project degradation when using LLM agents for development: agents often ignore the actual contracts between frontend and backend, creating dummy data and leading to runtime errors. The solution is to return to the contract-first approach, where the OpenAPI specification is the primary artifact from which server interfaces and clients are generated, making any deviation from the contract a compilation error.

Moonshot AI

Habr — хаб ИИ27.07 · 04:03

Research 🇷🇺

Mamba: The Architecture That Set Out to Kill Transformers

The Mamba architecture, based on selective state spaces (SSM), was introduced as an alternative to transformers, promising linear complexity instead of quadratic. In practice, however, Mamba did not replace transformers but entered hybrid models, where it is combined with attention layers: roughly one attention layer per seven Mamba layers.

Moonshot AI

Habr — хаб NLP27.07 · 03:03

Show more ↓