I build AI-native applications, developer tools, and human-centered systems that connect research, interaction, and real-world implementation.
My current question: how can AI become part of human memory, work, research, and everyday thinking?
I use multimodal data to estimate and analyze human states, exploring how to detect and understand changes over time.
Full-stack prototypes, local AI workflows, and tools that move quickly from idea to real use.
Starting with what I want to use every day, I build and refine tools that support everyday life and learning.
Explore productsEssays, notes, and devlogs in one stream
A linear model can rank, but it can never enclose. Starting from a rule as ordinary as "comfortable between 18 and 24 degrees", this post shows what one straight line cannot do, and how a single bend fixes it.
从公开 API 的输入、推理、结构化输出、工具、状态、实时与异步接口出发，重新理解现代模型的能力，以及模型与平台之间的边界。
从规则、数据与参数的边界出发，沿人工神经元的历史走到一个可训练的 Sigmoid 神经元。
从批处理、分时系统、命令行、图形界面、Web 到移动设备，追踪人与计算机如何从提交任务走向连续操作。
当自然语言成为计算入口，人与系统的关系如何从调用预设功能，转向对表达、意图与共同任务的持续解释。
从“交互”、interaction 与日语中的「交互」「相互作用」「インタラクション」出发，追溯交互如何从彼此作用生长为一门设计学科。