Kimi k2.5
76.8% SWE-bench, vision, agent swarm, free access paths.
What changed from speed-first AI drafting in 2023 to verification-first publishing in 2026, with a practical playbook for durable authority.
Evidence-based guide to writing AGENTS.md files that AI agents actually follow. Lessons from Vercel's evals, multi-tool testing, and production usage across Python, TypeScript, and documentation projects.
What we got wrong about AI-generated content in 2023, what actually worked, and how the vibe coding era shaped modern AI security thinking.
Strategic analysis of Moonshot AI's playbook: open weights + aggressive promotional pricing ($0.99 first month via AI agent) to capture developers from closed-source incumbents. Includes agent swarm impressiveness framework and market positioning vs Codex/Claude.
How to decide between local and cloud, pick a runtime, and size hardware for fast, private LLMs.
76.8% SWE-bench, vision, agent swarm, free access paths.
78% SWE-bench, 1M context, free input tokens.
Secure agent deployment without exposing infrastructure.
| Date | Category | Title | Description |
|---|---|---|---|
| 2026-02-11 | posts | Vibe Coding Lessons (2023-2026): A Production Playbook | What changed from speed-first AI drafting in 2023 to verification-first … |
| 2026-02-07 | posts | AGENTS.md: What Actually Works (And What Doesn't) | Evidence-based guide to writing AGENTS.md files that AI agents actually follow. … |
| 2026-02-04 | posts | Three Years in the Vibe Coding Trenches: A 2023-2026 Retrospective | What we got wrong about AI-generated content in 2023, what actually worked, and … |
| 2026-02-03 | posts | Kimi K2.5's Open-Source Pricing Strategy: How Moonshot AI Is Buying Market Share | Strategic analysis of Moonshot AI's playbook: open weights + aggressive … |
| 2026-02-03 | posts | Running LLMs Locally: A Practical Guide | How to decide between local and cloud, pick a runtime, and size hardware for … |