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-k3-free', 'Kimi K4', 'Kimi K5', 'Kimi Linear', 'Kivine', 'Krea 2', 'Krea 2 Turbo', 'Mamba', 'Mamba-2', 'Mamba-3', 'MiniCPM-RobotManip']

Official site ↗

Agents 🇷🇺

How to make Claude Code run tests: hooks against agent forgetfulness

The author suggests moving critical rules from Claude Code's context window into code via lifecycle hooks. Three gates are described: blocking a commit without a fresh green run, tracking test edits, and forbidding ending a turn with untested changes. In a direct experiment, the hook beat the user instruction 'don't run tests'.

Anthropic

Moonshot AI

Habr — хаб ИИ27.07 · 01:02

Models 🇨🇳

Rumor: DeepSeek V4 'Full Version' to Launch Today; Can It Surpass Kimi K3?

According to unconfirmed reports, the 'full version' of DeepSeek V4 will be released today. Discussion is underway on whether it can surpass the Kimi K3 model from Moonshot AI.

DeepSeek

Moonshot AI

DeepSeek (GNews)27.07 · 00:03

Show more ↓