https://blog.chuanxilu.net/en/tags/gpt/Recent content in Gpt on Chuanxilu for Skilled Homo sapiensHugoen-USTue, 30 Jun 2026 07:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day9/Tue, 30 Jun 2026 07:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week2-day9/L1→L2 Week 2 Day 9: Understand how API caching works, evaluate providers by cache hit rate and pricing, and pick a provider that fits your workload.https://blog.chuanxilu.net/en/posts/2026/06/opencode-fallback-chains/Sun, 07 Jun 2026 08:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/06/opencode-fallback-chains/oh-my-openagent (omo) and oh-my-opencode-slim (oms) have different fallback mechanisms: omo uses a 5-layer pipeline, oms uses startup selection + runtime abort retry. Source-code deep dive.https://blog.chuanxilu.net/en/posts/2026/06/opencode-triple-config-switch/Fri, 05 Jun 2026 10:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/06/opencode-triple-config-switch/Three parallel OpenCode configs from real pain points—omo full version, oms slim version, clean mode. Environment variable switching for the right tool in each scenario.https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1/Mon, 01 Jun 2026 07:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/06/ai-path-l1-l2-week1/First part of the AI Path L1→L2 Upgrade Guide series. Learn what APIs are, how they differ from chat windows, register for API accounts (DeepSeek/OpenRouter/Claude), set up Python, run your first API call, and build intuition for token, temperature, context window, and max_tokens.https://blog.chuanxilu.net/en/posts/2026/05/ai-tip-which-ai-to-use/Fri, 15 May 2026 06:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/05/ai-tip-which-ai-to-use/Tried ChatGPT, Claude, Gemini, DeepSeek, still not sure which one to use? A scenario-based framework to find the right fit.https://blog.chuanxilu.net/en/posts/2026/05/ai-path-l0-l1-week1/Mon, 11 May 2026 08:00:00 +0800https://blog.chuanxilu.net/en/posts/2026/05/ai-path-l0-l1-week1/First part of the AI Path L0→L1 Upgrade Guide series. LLMs aren't search engines; they generate answers rather than retrieve them. Understand the difference between working memory and long-term memory, learn the strengths of mainstream platforms, and build the cognitive foundation for the next 4 weeks of practice.