An engineering notebook on AI, systems, and everyday experiments.

分析AI学习者的四道流失阶梯，提出用工程化平台消除配置、实验、部署等摩擦，让学员专注于核心技能练习。介绍AI Builder Space如何通过统一API、一键部署和MCP自动化实现这一目标。

Analyzes the four-step attrition ladder in AI learning and proposes using engineering platforms to eliminate configuration, experimentation, and deployment friction. Introduces AI Builder Space's unified API, one-click deployment, and MCP automation.

用Claude Code替代API调用做翻译任务：利用agentic loop实现自我纠错，用evaluation-first定义验收标准，从过程确定性转向结果确定性获得新的安全感。

Why handing translation to Claude Code works better than calling APIs directly - leveraging the agentic loop, evaluation-first mindset, and the ecosystem's runtime layer to achieve outcome certainty over process certainty.

探索用生成式AI解决天文图像中CMOS灰尘去除难题。通过让AI生成灰尘遮罩而非直接修复图像，结合确定性数学平场校准，实现既保留科学严谨性又获得AI强大效果的工作流。

Explores using generative AI to remove CMOS dust from astronomical images. By having AI generate dust masks rather than direct corrections, then applying deterministic flat-field calibration, achieves both scientific integrity and AI's powerful recognition capabilities.

AI分析五年时间记录，揭示出"多线程人形算力节点"的生活模式——在带娃、工作和构建AI工具之间平衡，不自觉地走向人机融合的修仙之路。

AI analyzes five years of time logs and reveals a "multi-threaded human compute node" lifestyle—balancing parenting, work, and building AI tools while unconsciously becoming a human-system hybrid.

从拼凑到整体渲染的PPT制作范式转移，以及如何用代码骨架、资产约束和延迟渲染构建解决风格混乱、幻觉和成本问题的Generative Kernel。

Exploring the paradigm shift from assembling slides to holistic rendering with NBP, and building a Generative Kernel workflow to handle visual consistency, hallucination, and cost.