Dec 9, 2025 · 6 min read · Why Inspect LLM Requests This project started with a simple question: “Does Claude Code load CLAUDE.md as a system prompt or a user prompt?” Online answers hinted it was added as a user prompt, but I wanted proof—not assumptions. With agent-based cod...
Join discussionNov 20, 2025 · 5 min read · My previous blog post was about using Claude Code with Kimi-K2 model. Today I’m excited to write about how I tested the new Gemini 3 Pro model by Google, wired into Claude Code via OpenRouter. The goal was simple: can I run Claude Code with Gemini 3 ...
Join discussion
Nov 19, 2025 · 15 min read · In the last days there's been a lot of buzz around the new Kimi K2 model. I've been reading people's enthusiastic comments. Every time a new frontier model comes out, the hype cycle starts again. According to the authors, their kimi-K2-thinking model...
Join discussion